Step 1 | loss:18.943639755249023 lr:2.5e-06 tokens_per_second_per_gpu:793.7078529858711 
Step 2 | loss:18.93146514892578 lr:5e-06 tokens_per_second_per_gpu:2008.2208791802336 
Step 3 | loss:17.575828552246094 lr:7.5e-06 tokens_per_second_per_gpu:2021.5922056637407 
Step 4 | loss:13.963201522827148 lr:1e-05 tokens_per_second_per_gpu:1995.7489971592522 
Step 5 | loss:14.509130477905273 lr:1.25e-05 tokens_per_second_per_gpu:2198.303470349062 
Step 6 | loss:13.574084281921387 lr:1.5e-05 tokens_per_second_per_gpu:2168.299657551201 
Step 7 | loss:13.247751235961914 lr:1.75e-05 tokens_per_second_per_gpu:2174.055322219254 
Step 8 | loss:13.07095718383789 lr:2e-05 tokens_per_second_per_gpu:2191.186598338188 
Step 9 | loss:12.950408935546875 lr:2.25e-05 tokens_per_second_per_gpu:2148.5133763970457 
Step 10 | loss:12.836488723754883 lr:2.5e-05 tokens_per_second_per_gpu:2152.905017422581 
Step 11 | loss:12.723406791687012 lr:2.7500000000000004e-05 tokens_per_second_per_gpu:2192.805081241992 
Step 12 | loss:12.585577011108398 lr:3e-05 tokens_per_second_per_gpu:2210.9573887709203 
Step 13 | loss:12.377168655395508 lr:3.2500000000000004e-05 tokens_per_second_per_gpu:2171.0400887298324 
Step 14 | loss:12.233195304870605 lr:3.5e-05 tokens_per_second_per_gpu:2168.841600634961 
Step 15 | loss:12.064278602600098 lr:3.7500000000000003e-05 tokens_per_second_per_gpu:2230.2999248018264 
Step 16 | loss:11.914983749389648 lr:4e-05 tokens_per_second_per_gpu:2188.4036357686073 
Step 17 | loss:11.748600006103516 lr:4.25e-05 tokens_per_second_per_gpu:2215.7083942768045 
Step 18 | loss:11.62568473815918 lr:4.5e-05 tokens_per_second_per_gpu:2198.7289344527167 
Step 19 | loss:11.526670455932617 lr:4.75e-05 tokens_per_second_per_gpu:2231.6747709119118 
Step 20 | loss:11.408367156982422 lr:5e-05 tokens_per_second_per_gpu:2221.104558303348 
Step 21 | loss:11.292285919189453 lr:5.25e-05 tokens_per_second_per_gpu:2207.3392605063227 
Step 22 | loss:11.161432266235352 lr:5.500000000000001e-05 tokens_per_second_per_gpu:2197.452011805867 
Step 23 | loss:11.011418342590332 lr:5.7499999999999995e-05 tokens_per_second_per_gpu:2217.852371519795 
Step 24 | loss:10.831575393676758 lr:6e-05 tokens_per_second_per_gpu:2227.108012910017 
Step 25 | loss:10.614063262939453 lr:6.25e-05 tokens_per_second_per_gpu:2236.4493709192457 
Step 26 | loss:10.34518051147461 lr:6.500000000000001e-05 tokens_per_second_per_gpu:2224.0888022979066 
Step 27 | loss:10.009071350097656 lr:6.750000000000001e-05 tokens_per_second_per_gpu:2212.924496020194 
Step 28 | loss:9.59962272644043 lr:7e-05 tokens_per_second_per_gpu:2207.6699684293303 
Step 29 | loss:9.142838478088379 lr:7.25e-05 tokens_per_second_per_gpu:2226.322224221388 
Step 30 | loss:8.680657386779785 lr:7.500000000000001e-05 tokens_per_second_per_gpu:2191.0781012739603 
Step 31 | loss:8.209552764892578 lr:7.75e-05 tokens_per_second_per_gpu:2231.8135009954667 
Step 32 | loss:7.735126972198486 lr:8e-05 tokens_per_second_per_gpu:2192.380428180333 
Step 33 | loss:7.298317909240723 lr:8.25e-05 tokens_per_second_per_gpu:2221.1987482693767 
Step 34 | loss:6.919332981109619 lr:8.5e-05 tokens_per_second_per_gpu:2229.1499341161107 
Step 35 | loss:6.622148513793945 lr:8.75e-05 tokens_per_second_per_gpu:2196.7376122998744 
Step 36 | loss:6.395703315734863 lr:9e-05 tokens_per_second_per_gpu:2224.221136585979 
Step 37 | loss:6.275650501251221 lr:9.250000000000001e-05 tokens_per_second_per_gpu:2231.837209276319 
Step 38 | loss:6.182218074798584 lr:9.5e-05 tokens_per_second_per_gpu:2216.7292427839293 
Step 39 | loss:6.129483222961426 lr:9.75e-05 tokens_per_second_per_gpu:2186.8726511960795 
Step 40 | loss:6.085719585418701 lr:0.0001 tokens_per_second_per_gpu:2161.5717999111826 
Step 41 | loss:6.031839847564697 lr:0.0001025 tokens_per_second_per_gpu:2157.0030487910403 
Step 42 | loss:6.05197286605835 lr:0.000105 tokens_per_second_per_gpu:2152.768273812491 
Step 43 | loss:6.024497032165527 lr:0.0001075 tokens_per_second_per_gpu:2228.611094291482 
Step 44 | loss:6.0014448165893555 lr:0.00011000000000000002 tokens_per_second_per_gpu:2229.6514770675412 
Step 45 | loss:5.969542503356934 lr:0.00011250000000000001 tokens_per_second_per_gpu:2233.6331953321464 
Step 46 | loss:5.961199760437012 lr:0.00011499999999999999 tokens_per_second_per_gpu:2212.000067736563 
Step 47 | loss:6.048841953277588 lr:0.00011750000000000001 tokens_per_second_per_gpu:2236.9805899026846 
Step 48 | loss:5.957672595977783 lr:0.00012 tokens_per_second_per_gpu:2184.5647093911402 
Step 49 | loss:5.906917572021484 lr:0.00012250000000000002 tokens_per_second_per_gpu:2215.7816507398384 
Step 50 | loss:5.913396835327148 lr:0.000125 tokens_per_second_per_gpu:2120.743741256798 
Step 51 | loss:5.887764930725098 lr:0.0001275 tokens_per_second_per_gpu:2231.723978227304 
Step 52 | loss:5.930477142333984 lr:0.00013000000000000002 tokens_per_second_per_gpu:2234.3505406410063 
Step 53 | loss:5.912599086761475 lr:0.0001325 tokens_per_second_per_gpu:2200.7988919708587 
Step 54 | loss:5.948019981384277 lr:0.00013500000000000003 tokens_per_second_per_gpu:2235.803918434571 
Step 55 | loss:5.932744979858398 lr:0.0001375 tokens_per_second_per_gpu:2233.565084173762 
Step 56 | loss:5.937891006469727 lr:0.00014 tokens_per_second_per_gpu:2211.6272083280346 
Step 57 | loss:5.903974533081055 lr:0.00014250000000000002 tokens_per_second_per_gpu:2200.856800551214 
Step 58 | loss:5.901495933532715 lr:0.000145 tokens_per_second_per_gpu:2164.0087042902574 
Step 59 | loss:5.89754581451416 lr:0.0001475 tokens_per_second_per_gpu:2166.414608429925 
Step 60 | loss:5.903373718261719 lr:0.00015000000000000001 tokens_per_second_per_gpu:2186.4082587054913 
Step 61 | loss:5.907013893127441 lr:0.0001525 tokens_per_second_per_gpu:2220.817720818629 
Step 62 | loss:5.924228668212891 lr:0.000155 tokens_per_second_per_gpu:2198.2334024656247 
Step 63 | loss:5.907148361206055 lr:0.0001575 tokens_per_second_per_gpu:2217.600142790844 
Step 64 | loss:5.881990432739258 lr:0.00016 tokens_per_second_per_gpu:2220.2141959088094 
Step 65 | loss:5.886063575744629 lr:0.00016250000000000002 tokens_per_second_per_gpu:2235.506346945798 
Step 66 | loss:5.858996391296387 lr:0.000165 tokens_per_second_per_gpu:2226.160276645524 
Step 67 | loss:5.902133941650391 lr:0.0001675 tokens_per_second_per_gpu:2186.1168994202962 
Step 68 | loss:5.8636651039123535 lr:0.00017 tokens_per_second_per_gpu:2185.892178350302 
Step 69 | loss:5.869571208953857 lr:0.00017250000000000002 tokens_per_second_per_gpu:2170.6502173668628 
Step 70 | loss:5.894851207733154 lr:0.000175 tokens_per_second_per_gpu:2149.71613248218 
Step 71 | loss:5.901360511779785 lr:0.0001775 tokens_per_second_per_gpu:2228.847879323047 
Step 72 | loss:5.881728172302246 lr:0.00018 tokens_per_second_per_gpu:2238.5486970386514 
Step 73 | loss:5.841127395629883 lr:0.0001825 tokens_per_second_per_gpu:2233.870772213554 
Step 74 | loss:5.902477741241455 lr:0.00018500000000000002 tokens_per_second_per_gpu:2219.3730716037758 
Step 75 | loss:5.961294174194336 lr:0.0001875 tokens_per_second_per_gpu:2221.2295544376866 
Step 76 | loss:5.904571533203125 lr:0.00019 tokens_per_second_per_gpu:2082.1090542621314 
Step 77 | loss:5.89605712890625 lr:0.00019250000000000002 tokens_per_second_per_gpu:2205.1780594936517 
Step 78 | loss:5.87841272354126 lr:0.000195 tokens_per_second_per_gpu:2186.533361763338 
Step 79 | loss:5.907593250274658 lr:0.00019750000000000003 tokens_per_second_per_gpu:2182.6386876359165 
Step 80 | loss:5.874309539794922 lr:0.0002 tokens_per_second_per_gpu:2227.281743065078 
Step 81 | loss:5.9207377433776855 lr:0.0001999999922584364 tokens_per_second_per_gpu:2210.3917399361458 
Step 82 | loss:5.856893539428711 lr:0.0001999999690337467 tokens_per_second_per_gpu:2228.605145620059 
Step 83 | loss:5.877269744873047 lr:0.00019999993032593456 tokens_per_second_per_gpu:2195.516701086391 
Step 84 | loss:5.883194923400879 lr:0.00019999987613500596 tokens_per_second_per_gpu:2222.6808643347254 
Step 85 | loss:5.895882606506348 lr:0.00019999980646096926 tokens_per_second_per_gpu:2197.5380657084993 
Step 86 | loss:5.867829322814941 lr:0.00019999972130383528 tokens_per_second_per_gpu:2220.0639224423817 
Step 87 | loss:5.884827613830566 lr:0.0001999996206636172 tokens_per_second_per_gpu:2212.826346526384 
Step 88 | loss:5.881841659545898 lr:0.00019999950454033062 tokens_per_second_per_gpu:2215.9470062810215 
Step 89 | loss:5.961307525634766 lr:0.00019999937293399347 tokens_per_second_per_gpu:2234.7127202894067 
Step 90 | loss:5.85930061340332 lr:0.00019999922584462617 tokens_per_second_per_gpu:2180.2487996745335 
Step 91 | loss:5.925064563751221 lr:0.00019999906327225147 tokens_per_second_per_gpu:2212.0768303649 
Step 92 | loss:5.900991439819336 lr:0.00019999888521689456 tokens_per_second_per_gpu:2146.552792855148 
Step 93 | loss:5.895411014556885 lr:0.00019999869167858299 tokens_per_second_per_gpu:2239.5285562308113 
Step 94 | loss:5.916868209838867 lr:0.00019999848265734677 tokens_per_second_per_gpu:2237.2284364838188 
Step 95 | loss:5.848212718963623 lr:0.00019999825815321818 tokens_per_second_per_gpu:2210.133035769231 
Step 96 | loss:5.837786674499512 lr:0.00019999801816623203 tokens_per_second_per_gpu:2179.934016449167 
Step 97 | loss:5.875555515289307 lr:0.0001999977626964255 tokens_per_second_per_gpu:2215.225843648593 
Step 98 | loss:5.869253158569336 lr:0.00019999749174383813 tokens_per_second_per_gpu:2184.5514053617067 
Step 99 | loss:5.891525745391846 lr:0.00019999720530851183 tokens_per_second_per_gpu:2214.116773164012 
Step 100 | loss:5.864810943603516 lr:0.00019999690339049097 tokens_per_second_per_gpu:2219.9219705220985 
Step 101 | loss:5.876379013061523 lr:0.00019999658598982234 tokens_per_second_per_gpu:2123.7843798793992 
Step 102 | loss:5.872524738311768 lr:0.00019999625310655506 tokens_per_second_per_gpu:2229.344926421293 
Step 103 | loss:5.866449356079102 lr:0.00019999590474074067 tokens_per_second_per_gpu:2215.9360499210493 
Step 104 | loss:5.847005844116211 lr:0.00019999554089243304 tokens_per_second_per_gpu:2185.535618120925 
Step 105 | loss:5.867093563079834 lr:0.00019999516156168863 tokens_per_second_per_gpu:2125.6089768084066 
Step 106 | loss:5.8435258865356445 lr:0.00019999476674856608 tokens_per_second_per_gpu:2161.1683376302835 
Step 107 | loss:5.864365577697754 lr:0.00019999435645312653 tokens_per_second_per_gpu:2194.999441866815 
Step 108 | loss:5.881103038787842 lr:0.00019999393067543354 tokens_per_second_per_gpu:2218.574213787994 
Step 109 | loss:5.888385772705078 lr:0.00019999348941555301 tokens_per_second_per_gpu:2178.493790607069 
Step 110 | loss:5.83526611328125 lr:0.00019999303267355327 tokens_per_second_per_gpu:2212.1032688319924 
Step 111 | loss:5.84056282043457 lr:0.00019999256044950502 tokens_per_second_per_gpu:2185.67034466743 
Step 112 | loss:5.881134986877441 lr:0.00019999207274348142 tokens_per_second_per_gpu:2209.9812213068685 
Step 113 | loss:5.8444061279296875 lr:0.00019999156955555797 tokens_per_second_per_gpu:2187.6633737523252 
Step 114 | loss:5.880459785461426 lr:0.00019999105088581252 tokens_per_second_per_gpu:2195.824190994207 
Step 115 | loss:5.859341621398926 lr:0.00019999051673432543 tokens_per_second_per_gpu:2227.985808477743 
Step 116 | loss:5.851197242736816 lr:0.00019998996710117938 tokens_per_second_per_gpu:2228.2422825149747 
Step 117 | loss:5.832394599914551 lr:0.00019998940198645953 tokens_per_second_per_gpu:2162.253985589449 
Step 118 | loss:5.890263557434082 lr:0.0001999888213902533 tokens_per_second_per_gpu:2234.4707598966174 
Step 119 | loss:5.85722541809082 lr:0.0001999882253126506 tokens_per_second_per_gpu:2191.8597759904806 
Step 120 | loss:5.877830505371094 lr:0.00019998761375374376 tokens_per_second_per_gpu:2223.2800062042297 
Step 121 | loss:5.8792724609375 lr:0.00019998698671362742 tokens_per_second_per_gpu:2236.8309297507644 
Step 122 | loss:5.837070941925049 lr:0.0001999863441923987 tokens_per_second_per_gpu:2181.3465820926444 
Step 123 | loss:5.8704514503479 lr:0.00019998568619015704 tokens_per_second_per_gpu:2226.137893775026 
Step 124 | loss:5.808571815490723 lr:0.00019998501270700444 tokens_per_second_per_gpu:2201.1178497287665 
Step 125 | loss:5.795853614807129 lr:0.000199984323743045 tokens_per_second_per_gpu:2228.7654738380093 
Step 126 | loss:5.85749626159668 lr:0.0001999836192983855 tokens_per_second_per_gpu:2192.854855959896 
Step 127 | loss:5.849786758422852 lr:0.00019998289937313502 tokens_per_second_per_gpu:2229.8984913532486 
Step 128 | loss:5.821616172790527 lr:0.00019998216396740497 tokens_per_second_per_gpu:2230.21222085423 
Step 129 | loss:5.885591983795166 lr:0.00019998141308130927 tokens_per_second_per_gpu:2238.175088786336 
Step 130 | loss:5.839233875274658 lr:0.00019998064671496413 tokens_per_second_per_gpu:1980.0131733054052 
Step 131 | loss:5.9226155281066895 lr:0.00019997986486848822 tokens_per_second_per_gpu:2202.1363127955524 
Step 132 | loss:5.862414360046387 lr:0.00019997906754200262 tokens_per_second_per_gpu:2181.326367897639 
Step 133 | loss:5.811119556427002 lr:0.00019997825473563077 tokens_per_second_per_gpu:2219.5088268486315 
Step 134 | loss:5.857264518737793 lr:0.00019997742644949852 tokens_per_second_per_gpu:2165.8209697650263 
Step 135 | loss:5.857836723327637 lr:0.00019997658268373406 tokens_per_second_per_gpu:2232.9857005036624 
Step 136 | loss:5.846603870391846 lr:0.00019997572343846814 tokens_per_second_per_gpu:2225.2572201642943 
Step 137 | loss:5.8505706787109375 lr:0.00019997484871383368 tokens_per_second_per_gpu:2163.7456345634214 
Step 138 | loss:5.834619045257568 lr:0.0001999739585099662 tokens_per_second_per_gpu:2151.9699423992233 
Step 139 | loss:5.814691066741943 lr:0.0001999730528270035 tokens_per_second_per_gpu:2239.583647566921 
Step 140 | loss:5.855471611022949 lr:0.00019997213166508582 tokens_per_second_per_gpu:2217.577614375974 
Step 141 | loss:5.806656837463379 lr:0.00019997119502435578 tokens_per_second_per_gpu:2235.6679614669656 
Step 142 | loss:5.825304985046387 lr:0.00019997024290495835 tokens_per_second_per_gpu:2196.058328875634 
Step 143 | loss:5.862204551696777 lr:0.00019996927530704106 tokens_per_second_per_gpu:2238.148654185005 
Step 144 | loss:5.854912281036377 lr:0.00019996829223075361 tokens_per_second_per_gpu:2228.4902755077574 
Step 145 | loss:5.833133220672607 lr:0.00019996729367624826 tokens_per_second_per_gpu:2206.5292097023103 
Step 146 | loss:5.850004196166992 lr:0.00019996627964367965 tokens_per_second_per_gpu:2084.6981089335222 
Step 147 | loss:5.806539058685303 lr:0.00019996525013320473 tokens_per_second_per_gpu:2201.3886788027125 
Step 148 | loss:5.788273811340332 lr:0.00019996420514498296 tokens_per_second_per_gpu:2206.8017646377393 
Step 149 | loss:5.852132320404053 lr:0.00019996314467917605 tokens_per_second_per_gpu:2235.2168611784164 
Step 150 | loss:5.842820167541504 lr:0.00019996206873594826 tokens_per_second_per_gpu:2132.1096381597554 
Step 151 | loss:5.8482770919799805 lr:0.00019996097731546616 tokens_per_second_per_gpu:2184.319182165301 
Step 152 | loss:5.840559482574463 lr:0.00019995987041789874 tokens_per_second_per_gpu:2194.7100627020336 
Step 153 | loss:5.823376655578613 lr:0.00019995874804341738 tokens_per_second_per_gpu:2237.0256363923495 
Step 154 | loss:5.815722465515137 lr:0.00019995761019219585 tokens_per_second_per_gpu:2231.0739083483045 
Step 155 | loss:5.800573348999023 lr:0.00019995645686441034 tokens_per_second_per_gpu:2176.450802745902 
Step 156 | loss:5.792450904846191 lr:0.00019995528806023943 tokens_per_second_per_gpu:2220.75124323996 
Step 157 | loss:5.82640266418457 lr:0.00019995410377986406 tokens_per_second_per_gpu:2237.1662201627996 
Step 158 | loss:5.84779167175293 lr:0.0001999529040234676 tokens_per_second_per_gpu:2205.194122721779 
Step 159 | loss:5.77596378326416 lr:0.00019995168879123582 tokens_per_second_per_gpu:2185.6475426195802 
Step 160 | loss:5.820466995239258 lr:0.00019995045808335687 tokens_per_second_per_gpu:2203.447463518297 
Step 161 | loss:5.804755687713623 lr:0.00019994921190002129 tokens_per_second_per_gpu:2228.2903567085846 
Step 162 | loss:5.759709358215332 lr:0.00019994795024142208 tokens_per_second_per_gpu:2210.9934997248524 
Step 163 | loss:5.777256011962891 lr:0.0001999466731077545 tokens_per_second_per_gpu:2237.9455556746184 
Step 164 | loss:5.74899959564209 lr:0.00019994538049921637 tokens_per_second_per_gpu:2235.1364238445944 
Step 165 | loss:5.757157325744629 lr:0.00019994407241600778 tokens_per_second_per_gpu:2219.770576189663 
Step 166 | loss:5.665125846862793 lr:0.0001999427488583313 tokens_per_second_per_gpu:2197.915072765129 
Step 167 | loss:6.567975997924805 lr:0.0001999414098263918 tokens_per_second_per_gpu:2222.7140800205552 
Step 168 | loss:5.917037487030029 lr:0.00019994005532039663 tokens_per_second_per_gpu:2237.290542328497 
Step 169 | loss:5.893206596374512 lr:0.00019993868534055556 tokens_per_second_per_gpu:2222.9064051797873 
Step 170 | loss:5.8258256912231445 lr:0.00019993729988708063 tokens_per_second_per_gpu:2163.7011251091685 
Step 171 | loss:5.834731101989746 lr:0.0001999358989601864 tokens_per_second_per_gpu:2225.1187619436805 
Step 172 | loss:5.799461364746094 lr:0.00019993448256008973 tokens_per_second_per_gpu:2234.6744268874772 
Step 173 | loss:5.802532196044922 lr:0.00019993305068701 tokens_per_second_per_gpu:2229.6500364186672 
Step 174 | loss:5.696120738983154 lr:0.0001999316033411688 tokens_per_second_per_gpu:2226.395346771131 
Step 175 | loss:5.628111839294434 lr:0.00019993014052279034 tokens_per_second_per_gpu:2214.4069003964314 
Step 176 | loss:5.5724287033081055 lr:0.00019992866223210104 tokens_per_second_per_gpu:2188.0452333072726 
Step 177 | loss:5.517857551574707 lr:0.00019992716846932982 tokens_per_second_per_gpu:2174.3111078563393 
Step 178 | loss:5.490078926086426 lr:0.00019992565923470794 tokens_per_second_per_gpu:2132.684822185263 
Step 179 | loss:5.476701736450195 lr:0.00019992413452846907 tokens_per_second_per_gpu:2234.2288326231765 
Step 180 | loss:5.440088272094727 lr:0.00019992259435084927 tokens_per_second_per_gpu:2195.2527931631416 
Step 181 | loss:5.439018726348877 lr:0.00019992103870208707 tokens_per_second_per_gpu:2225.9889361464343 
Step 182 | loss:5.411572456359863 lr:0.00019991946758242328 tokens_per_second_per_gpu:2231.4523772582734 
Step 183 | loss:5.391805648803711 lr:0.0001999178809921012 tokens_per_second_per_gpu:2224.368739387961 
Step 184 | loss:5.369239330291748 lr:0.0001999162789313664 tokens_per_second_per_gpu:2208.112404297938 
Step 185 | loss:5.396924018859863 lr:0.000199914661400467 tokens_per_second_per_gpu:2232.3194896657365 
Step 186 | loss:5.313538551330566 lr:0.00019991302839965347 tokens_per_second_per_gpu:2206.637459811408 
Step 187 | loss:5.308732986450195 lr:0.00019991137992917858 tokens_per_second_per_gpu:2220.8608552600344 
Step 188 | loss:5.276400089263916 lr:0.0001999097159892976 tokens_per_second_per_gpu:2167.042527724307 
Step 189 | loss:5.24870491027832 lr:0.00019990803658026816 tokens_per_second_per_gpu:2227.5671868860877 
Step 190 | loss:5.231919765472412 lr:0.00019990634170235025 tokens_per_second_per_gpu:2224.7105502392915 
Step 191 | loss:5.268623352050781 lr:0.00019990463135580636 tokens_per_second_per_gpu:2232.759306995939 
Step 192 | loss:5.34552001953125 lr:0.00019990290554090123 tokens_per_second_per_gpu:2159.845282210439 
Step 193 | loss:5.923666954040527 lr:0.00019990116425790212 tokens_per_second_per_gpu:2208.992888007813 
Step 194 | loss:5.44459342956543 lr:0.00019989940750707864 tokens_per_second_per_gpu:2213.1283500033 
Step 195 | loss:5.357338905334473 lr:0.00019989763528870273 tokens_per_second_per_gpu:2174.7315946222825 
Step 196 | loss:5.329815864562988 lr:0.00019989584760304885 tokens_per_second_per_gpu:2217.5086856093385 
Step 197 | loss:5.323348045349121 lr:0.00019989404445039374 tokens_per_second_per_gpu:2218.913032634668 
Step 198 | loss:5.208459854125977 lr:0.00019989222583101664 tokens_per_second_per_gpu:2182.519409854744 
Step 199 | loss:5.24271297454834 lr:0.0001998903917451991 tokens_per_second_per_gpu:2225.4831047649504 
Step 200 | loss:5.228619575500488 lr:0.00019988854219322506 tokens_per_second_per_gpu:2220.875010292933 
Step 201 | loss:5.2260422706604 lr:0.00019988667717538093 tokens_per_second_per_gpu:2191.7789358889195 
Step 202 | loss:5.169045448303223 lr:0.0001998847966919555 tokens_per_second_per_gpu:2183.4721932047996 
Step 203 | loss:5.152097702026367 lr:0.0001998829007432398 tokens_per_second_per_gpu:2234.387953633899 
Step 204 | loss:5.131717681884766 lr:0.00019988098932952755 tokens_per_second_per_gpu:2172.8778585161617 
Step 205 | loss:5.095661163330078 lr:0.0001998790624511146 tokens_per_second_per_gpu:2200.4517144628385 
Step 206 | loss:5.108882904052734 lr:0.0001998771201082993 tokens_per_second_per_gpu:2231.4170247531933 
Step 207 | loss:5.045033931732178 lr:0.00019987516230138242 tokens_per_second_per_gpu:2129.7502413283164 
Step 208 | loss:5.1182098388671875 lr:0.00019987318903066706 tokens_per_second_per_gpu:2238.1919934430116 
Step 209 | loss:5.081399917602539 lr:0.0001998712002964587 tokens_per_second_per_gpu:2230.1134431480364 
Step 210 | loss:5.056526184082031 lr:0.00019986919609906538 tokens_per_second_per_gpu:2188.133665775402 
Step 211 | loss:5.025605201721191 lr:0.00019986717643879728 tokens_per_second_per_gpu:2233.8341388482454 
Step 212 | loss:5.022258758544922 lr:0.0001998651413159672 tokens_per_second_per_gpu:2220.0569376109597 
Step 213 | loss:5.033441543579102 lr:0.00019986309073089022 tokens_per_second_per_gpu:2187.2461665385144 
Step 214 | loss:4.998628616333008 lr:0.0001998610246838838 tokens_per_second_per_gpu:2213.9903726347625 
Step 215 | loss:5.004626274108887 lr:0.00019985894317526786 tokens_per_second_per_gpu:2213.1906593431872 
Step 216 | loss:4.982147693634033 lr:0.00019985684620536467 tokens_per_second_per_gpu:2214.09416389469 
Step 217 | loss:4.930451393127441 lr:0.0001998547337744989 tokens_per_second_per_gpu:2226.093144035889 
Step 218 | loss:4.980160713195801 lr:0.00019985260588299765 tokens_per_second_per_gpu:2157.5384863717695 
Step 219 | loss:4.944576263427734 lr:0.00019985046253119033 tokens_per_second_per_gpu:2180.3037733329616 
Step 220 | loss:4.952699661254883 lr:0.00019984830371940886 tokens_per_second_per_gpu:2189.5444624867623 
Step 221 | loss:4.9459452629089355 lr:0.00019984612944798746 tokens_per_second_per_gpu:2218.9911649388864 
Step 222 | loss:4.985442161560059 lr:0.00019984393971726278 tokens_per_second_per_gpu:2160.3190978078346 
Step 223 | loss:4.919863700866699 lr:0.00019984173452757386 tokens_per_second_per_gpu:2205.967710980577 
Step 224 | loss:4.896419048309326 lr:0.00019983951387926214 tokens_per_second_per_gpu:2201.5073423514814 
Step 225 | loss:4.923550605773926 lr:0.0001998372777726714 tokens_per_second_per_gpu:2228.4541776892074 
Step 226 | loss:4.8961286544799805 lr:0.00019983502620814792 tokens_per_second_per_gpu:2160.2332281882245 
Step 227 | loss:4.90262508392334 lr:0.0001998327591860403 tokens_per_second_per_gpu:2201.317278125633 
Step 228 | loss:4.853919982910156 lr:0.0001998304767066995 tokens_per_second_per_gpu:2209.5791491767973 
Step 229 | loss:4.902634620666504 lr:0.00019982817877047898 tokens_per_second_per_gpu:2203.0340281750405 
Step 230 | loss:4.895810127258301 lr:0.00019982586537773452 tokens_per_second_per_gpu:2169.64284298147 
Step 231 | loss:4.840427875518799 lr:0.00019982353652882426 tokens_per_second_per_gpu:2233.0674835934888 
Step 232 | loss:4.8485894203186035 lr:0.0001998211922241088 tokens_per_second_per_gpu:2193.5161248415457 
Step 233 | loss:4.824641227722168 lr:0.00019981883246395117 tokens_per_second_per_gpu:2212.3728541496744 
Step 234 | loss:4.846299648284912 lr:0.00019981645724871663 tokens_per_second_per_gpu:2131.6086586732763 
Step 235 | loss:4.836965560913086 lr:0.00019981406657877302 tokens_per_second_per_gpu:2238.066479030298 
Step 236 | loss:4.805380821228027 lr:0.00019981166045449046 tokens_per_second_per_gpu:2200.4748349654346 
Step 237 | loss:4.817169189453125 lr:0.0001998092388762415 tokens_per_second_per_gpu:2177.6573833565185 
Step 238 | loss:4.750138759613037 lr:0.0001998068018444011 tokens_per_second_per_gpu:2200.0630585242548 
Step 239 | loss:4.7478437423706055 lr:0.00019980434935934653 tokens_per_second_per_gpu:2187.467693289683 
Step 240 | loss:4.727957248687744 lr:0.00019980188142145754 tokens_per_second_per_gpu:2229.7745198772845 
Step 241 | loss:4.718325614929199 lr:0.00019979939803111627 tokens_per_second_per_gpu:2231.860754293867 
Step 242 | loss:4.693659782409668 lr:0.00019979689918870719 tokens_per_second_per_gpu:2128.5357076241567 
Step 243 | loss:4.698329925537109 lr:0.0001997943848946172 tokens_per_second_per_gpu:2231.1640247875725 
Step 244 | loss:4.6584153175354 lr:0.00019979185514923563 tokens_per_second_per_gpu:2201.1977719136603 
Step 245 | loss:4.741934299468994 lr:0.0001997893099529541 tokens_per_second_per_gpu:2233.2256510771685 
Step 246 | loss:4.655282974243164 lr:0.00019978674930616676 tokens_per_second_per_gpu:2231.942299991912 
Step 247 | loss:4.607871055603027 lr:0.00019978417320927003 tokens_per_second_per_gpu:2199.564308353304 
Step 248 | loss:4.689756393432617 lr:0.00019978158166266278 tokens_per_second_per_gpu:2228.991123866584 
Step 249 | loss:4.663753509521484 lr:0.00019977897466674628 tokens_per_second_per_gpu:2225.157832454061 
Step 250 | loss:4.594825744628906 lr:0.00019977635222192413 tokens_per_second_per_gpu:2180.997876318746 
Step 251 | loss:4.531325817108154 lr:0.00019977371432860244 tokens_per_second_per_gpu:2200.8470778055494 
Step 252 | loss:4.468146324157715 lr:0.00019977106098718956 tokens_per_second_per_gpu:2198.998166481729 
Step 253 | loss:4.540581703186035 lr:0.00019976839219809636 tokens_per_second_per_gpu:2089.3092632172334 
Step 254 | loss:4.533329010009766 lr:0.00019976570796173602 tokens_per_second_per_gpu:2214.552411093665 
Step 255 | loss:4.428043365478516 lr:0.00019976300827852418 tokens_per_second_per_gpu:2220.0532417421273 
Step 256 | loss:4.449463844299316 lr:0.00019976029314887881 tokens_per_second_per_gpu:2153.8015296282924 
Step 257 | loss:4.397178649902344 lr:0.0001997575625732203 tokens_per_second_per_gpu:2226.5781715647304 
Step 258 | loss:4.406618118286133 lr:0.00019975481655197142 tokens_per_second_per_gpu:2170.8547283483767 
Step 259 | loss:4.474860191345215 lr:0.00019975205508555735 tokens_per_second_per_gpu:2231.016936486725 
Step 260 | loss:4.30595588684082 lr:0.00019974927817440564 tokens_per_second_per_gpu:2218.7786257805255 
Step 261 | loss:4.242755889892578 lr:0.0001997464858189463 tokens_per_second_per_gpu:2226.4427110031297 
Step 262 | loss:4.348515510559082 lr:0.0001997436780196116 tokens_per_second_per_gpu:2220.0345572090273 
Step 263 | loss:4.34440803527832 lr:0.00019974085477683632 tokens_per_second_per_gpu:2188.119973675196 
Step 264 | loss:4.266152381896973 lr:0.00019973801609105755 tokens_per_second_per_gpu:2183.929427385562 
Step 265 | loss:4.315512657165527 lr:0.00019973516196271484 tokens_per_second_per_gpu:2234.577886975059 
Step 266 | loss:4.46778678894043 lr:0.00019973229239225008 tokens_per_second_per_gpu:2227.4159193339615 
Step 267 | loss:4.506097316741943 lr:0.0001997294073801076 tokens_per_second_per_gpu:2212.686607512716 
Step 268 | loss:4.267505645751953 lr:0.00019972650692673405 tokens_per_second_per_gpu:2222.9158608536673 
Step 269 | loss:4.369577407836914 lr:0.0001997235910325785 tokens_per_second_per_gpu:2222.973394658454 
Step 270 | loss:4.334829330444336 lr:0.00019972065969809245 tokens_per_second_per_gpu:2022.1091043639267 
Step 271 | loss:4.2990946769714355 lr:0.00019971771292372982 tokens_per_second_per_gpu:2167.06766384278 
Step 272 | loss:4.171797752380371 lr:0.00019971475070994674 tokens_per_second_per_gpu:2226.46123956038 
Step 273 | loss:4.111806869506836 lr:0.00019971177305720195 tokens_per_second_per_gpu:2227.8443950906403 
Step 274 | loss:4.194904327392578 lr:0.00019970877996595645 tokens_per_second_per_gpu:2235.0103464975746 
Step 275 | loss:4.031490325927734 lr:0.00019970577143667363 tokens_per_second_per_gpu:2217.0320665375666 
Step 276 | loss:4.058449745178223 lr:0.0001997027474698194 tokens_per_second_per_gpu:2179.3195217610396 
Step 277 | loss:4.11307430267334 lr:0.00019969970806586184 tokens_per_second_per_gpu:2129.851291509168 
Step 278 | loss:4.027682304382324 lr:0.0001996966532252716 tokens_per_second_per_gpu:2153.3370823964287 
Step 279 | loss:3.93192195892334 lr:0.00019969358294852173 tokens_per_second_per_gpu:2188.9998730373054 
Step 280 | loss:3.9831223487854004 lr:0.00019969049723608752 tokens_per_second_per_gpu:2228.12117553999 
Step 281 | loss:3.9903903007507324 lr:0.00019968739608844678 tokens_per_second_per_gpu:2225.109201997982 
Step 282 | loss:3.9409213066101074 lr:0.00019968427950607965 tokens_per_second_per_gpu:2201.829066606096 
Step 283 | loss:3.9094481468200684 lr:0.00019968114748946864 tokens_per_second_per_gpu:2213.177150883596 
Step 284 | loss:3.8267035484313965 lr:0.00019967800003909872 tokens_per_second_per_gpu:2214.4226333335096 
Step 285 | loss:3.9183883666992188 lr:0.00019967483715545723 tokens_per_second_per_gpu:2194.736137133 
Step 286 | loss:3.9147748947143555 lr:0.00019967165883903385 tokens_per_second_per_gpu:2209.6239191153127 
Step 287 | loss:3.8420987129211426 lr:0.0001996684650903207 tokens_per_second_per_gpu:2068.4542081014897 
Step 288 | loss:3.7490108013153076 lr:0.00019966525590981227 tokens_per_second_per_gpu:2193.7682807702986 
Step 289 | loss:3.6769237518310547 lr:0.00019966203129800545 tokens_per_second_per_gpu:2148.1826059268215 
Step 290 | loss:3.784381628036499 lr:0.00019965879125539946 tokens_per_second_per_gpu:2069.0883655594707 
Step 291 | loss:3.8275275230407715 lr:0.00019965553578249603 tokens_per_second_per_gpu:2146.2269074693395 
Step 292 | loss:3.7137084007263184 lr:0.00019965226487979917 tokens_per_second_per_gpu:2076.468263320268 
Step 293 | loss:3.789989948272705 lr:0.00019964897854781534 tokens_per_second_per_gpu:2155.6068150301185 
Step 294 | loss:3.6685447692871094 lr:0.00019964567678705335 tokens_per_second_per_gpu:2151.5034797832614 
Step 295 | loss:3.6673669815063477 lr:0.0001996423595980244 tokens_per_second_per_gpu:2103.251725672015 
Step 296 | loss:3.689614772796631 lr:0.00019963902698124213 tokens_per_second_per_gpu:2150.8808616032434 
Step 297 | loss:3.593173027038574 lr:0.00019963567893722253 tokens_per_second_per_gpu:2127.284638693354 
Step 298 | loss:3.6598572731018066 lr:0.00019963231546648395 tokens_per_second_per_gpu:2147.7542447167757 
Step 299 | loss:3.5707590579986572 lr:0.00019962893656954718 tokens_per_second_per_gpu:2168.6436436594795 
Step 300 | loss:3.5438461303710938 lr:0.00019962554224693538 tokens_per_second_per_gpu:2172.2919335534752 
Step 301 | loss:3.653660297393799 lr:0.00019962213249917412 tokens_per_second_per_gpu:2166.6860273007806 
Step 302 | loss:3.5566020011901855 lr:0.00019961870732679128 tokens_per_second_per_gpu:2178.3697864277556 
Step 303 | loss:3.5578651428222656 lr:0.00019961526673031724 tokens_per_second_per_gpu:2187.1714258547086 
Step 304 | loss:3.5859856605529785 lr:0.00019961181071028467 tokens_per_second_per_gpu:2188.8839193034814 
Step 305 | loss:3.489777088165283 lr:0.0001996083392672287 tokens_per_second_per_gpu:2193.6557871289256 
Step 306 | loss:3.4716548919677734 lr:0.00019960485240168681 tokens_per_second_per_gpu:2183.4096805904496 
Step 307 | loss:3.435822010040283 lr:0.00019960135011419885 tokens_per_second_per_gpu:2193.181704061348 
Step 308 | loss:3.496929883956909 lr:0.00019959783240530712 tokens_per_second_per_gpu:2142.051054788059 
Step 309 | loss:3.4469809532165527 lr:0.00019959429927555626 tokens_per_second_per_gpu:2194.0735086076875 
Step 310 | loss:3.4490859508514404 lr:0.0001995907507254933 tokens_per_second_per_gpu:2152.1903114109887 
Step 311 | loss:3.4269309043884277 lr:0.00019958718675566766 tokens_per_second_per_gpu:2117.991929666379 
Step 312 | loss:3.422572135925293 lr:0.00019958360736663117 tokens_per_second_per_gpu:2127.0651659699924 
Step 313 | loss:3.3558030128479004 lr:0.00019958001255893803 tokens_per_second_per_gpu:2169.778298372427 
Step 314 | loss:3.2927589416503906 lr:0.00019957640233314483 tokens_per_second_per_gpu:2133.709508516707 
Step 315 | loss:3.3291773796081543 lr:0.00019957277668981055 tokens_per_second_per_gpu:2172.179693570328 
Step 316 | loss:3.3908567428588867 lr:0.0001995691356294965 tokens_per_second_per_gpu:2146.44079253139 
Step 317 | loss:3.40425443649292 lr:0.00019956547915276653 tokens_per_second_per_gpu:2141.82903189135 
Step 318 | loss:3.341658115386963 lr:0.00019956180726018668 tokens_per_second_per_gpu:2166.9158112011996 
Step 319 | loss:3.4942336082458496 lr:0.00019955811995232554 tokens_per_second_per_gpu:2129.2719215448165 
Step 320 | loss:3.334463119506836 lr:0.000199554417229754 tokens_per_second_per_gpu:2152.7776756613757 
Step 321 | loss:3.319063901901245 lr:0.00019955069909304536 tokens_per_second_per_gpu:2169.63128787911 
Step 322 | loss:3.393798589706421 lr:0.00019954696554277525 tokens_per_second_per_gpu:2164.1091934145825 
Step 323 | loss:3.3048770427703857 lr:0.00019954321657952184 tokens_per_second_per_gpu:2158.8550247454414 
Step 324 | loss:3.3541433811187744 lr:0.00019953945220386551 tokens_per_second_per_gpu:2159.2567398255 
Step 325 | loss:3.328960418701172 lr:0.00019953567241638912 tokens_per_second_per_gpu:2152.417088850816 
Step 326 | loss:3.2895607948303223 lr:0.00019953187721767792 tokens_per_second_per_gpu:2155.792772669333 
Step 327 | loss:3.3246498107910156 lr:0.0001995280666083195 tokens_per_second_per_gpu:2108.1471792369207 
Step 328 | loss:3.26448392868042 lr:0.00019952424058890388 tokens_per_second_per_gpu:2146.3393264617553 
Step 329 | loss:3.320918083190918 lr:0.00019952039916002346 tokens_per_second_per_gpu:2149.96734926424 
Step 330 | loss:3.242614507675171 lr:0.00019951654232227298 tokens_per_second_per_gpu:2152.879623438853 
Step 331 | loss:3.2945756912231445 lr:0.0001995126700762496 tokens_per_second_per_gpu:2128.947531790813 
Step 332 | loss:3.2603678703308105 lr:0.0001995087824225529 tokens_per_second_per_gpu:2162.5997391438027 
Step 333 | loss:3.2420272827148438 lr:0.00019950487936178476 tokens_per_second_per_gpu:2157.1784873431866 
Step 334 | loss:3.28523850440979 lr:0.00019950096089454955 tokens_per_second_per_gpu:2086.8093332199132 
Step 335 | loss:3.249833106994629 lr:0.00019949702702145393 tokens_per_second_per_gpu:2089.60764268873 
Step 336 | loss:3.276090621948242 lr:0.000199493077743107 tokens_per_second_per_gpu:2177.55149560643 
Step 337 | loss:3.20125150680542 lr:0.00019948911306012023 tokens_per_second_per_gpu:2149.6990368926063 
Step 338 | loss:3.236536979675293 lr:0.00019948513297310752 tokens_per_second_per_gpu:2105.6776640367257 
Step 339 | loss:3.2195076942443848 lr:0.000199481137482685 tokens_per_second_per_gpu:2148.1990811619708 
Step 340 | loss:3.2987618446350098 lr:0.00019947712658947145 tokens_per_second_per_gpu:2179.8006055902165 
Step 341 | loss:3.3234877586364746 lr:0.00019947310029408777 tokens_per_second_per_gpu:2165.7193123150046 
Step 342 | loss:3.13442325592041 lr:0.00019946905859715737 tokens_per_second_per_gpu:2169.420834298347 
Step 343 | loss:3.1857402324676514 lr:0.00019946500149930607 tokens_per_second_per_gpu:2197.296356306644 
Step 344 | loss:3.1658692359924316 lr:0.000199460929001162 tokens_per_second_per_gpu:2186.018541101876 
Step 345 | loss:3.080233573913574 lr:0.00019945684110335573 tokens_per_second_per_gpu:2187.9164429361194 
Step 346 | loss:3.1532325744628906 lr:0.00019945273780652017 tokens_per_second_per_gpu:2179.3121671666604 
Step 347 | loss:3.160214424133301 lr:0.00019944861911129068 tokens_per_second_per_gpu:2150.0692363158496 
Step 348 | loss:3.2158946990966797 lr:0.00019944448501830496 tokens_per_second_per_gpu:2189.3107136384915 
Step 349 | loss:3.1496999263763428 lr:0.00019944033552820304 tokens_per_second_per_gpu:2171.4049055080986 
Step 350 | loss:3.1611804962158203 lr:0.00019943617064162745 tokens_per_second_per_gpu:2151.326015424515 
Step 351 | loss:3.1350655555725098 lr:0.000199431990359223 tokens_per_second_per_gpu:2156.222841979856 
Step 352 | loss:3.166644334793091 lr:0.00019942779468163697 tokens_per_second_per_gpu:2169.5525701046017 
Step 353 | loss:3.191810369491577 lr:0.00019942358360951898 tokens_per_second_per_gpu:2189.499393684463 
Step 354 | loss:3.131405830383301 lr:0.000199419357143521 tokens_per_second_per_gpu:2170.0155229850566 
Step 355 | loss:3.185222625732422 lr:0.00019941511528429745 tokens_per_second_per_gpu:2165.554740304602 
Step 356 | loss:3.184832811355591 lr:0.00019941085803250506 tokens_per_second_per_gpu:2154.608542892926 
Step 357 | loss:3.0611820220947266 lr:0.00019940658538880303 tokens_per_second_per_gpu:2187.064300480217 
Step 358 | loss:3.065476179122925 lr:0.00019940229735385288 tokens_per_second_per_gpu:2186.0510440278704 
Step 359 | loss:3.084512948989868 lr:0.00019939799392831856 tokens_per_second_per_gpu:2143.5725111045326 
Step 360 | loss:3.159107208251953 lr:0.00019939367511286635 tokens_per_second_per_gpu:2162.6193489093594 
Step 361 | loss:3.1208744049072266 lr:0.0001993893409081649 tokens_per_second_per_gpu:2042.081468224104 
Step 362 | loss:3.053225517272949 lr:0.00019938499131488534 tokens_per_second_per_gpu:2191.9327815879765 
Step 363 | loss:3.0521140098571777 lr:0.00019938062633370114 tokens_per_second_per_gpu:2150.020370534459 
Step 364 | loss:3.0754618644714355 lr:0.00019937624596528806 tokens_per_second_per_gpu:2167.9860624791413 
Step 365 | loss:3.0731258392333984 lr:0.0001993718502103244 tokens_per_second_per_gpu:2188.9381893086465 
Step 366 | loss:3.095822334289551 lr:0.00019936743906949066 tokens_per_second_per_gpu:2195.465419598719 
Step 367 | loss:3.0527725219726562 lr:0.0001993630125434699 tokens_per_second_per_gpu:2182.130526530191 
Step 368 | loss:3.0280749797821045 lr:0.00019935857063294748 tokens_per_second_per_gpu:2143.0250520740738 
Step 369 | loss:3.043200731277466 lr:0.00019935411333861112 tokens_per_second_per_gpu:2158.1807955675945 
Step 370 | loss:3.0398268699645996 lr:0.00019934964066115093 tokens_per_second_per_gpu:2093.9497221186643 
Step 371 | loss:3.0479021072387695 lr:0.0001993451526012595 tokens_per_second_per_gpu:2167.3380452074316 
Step 372 | loss:3.0900917053222656 lr:0.00019934064915963165 tokens_per_second_per_gpu:2044.7300456570088 
Step 373 | loss:3.0616722106933594 lr:0.00019933613033696465 tokens_per_second_per_gpu:2186.732996620653 
Step 374 | loss:3.0716400146484375 lr:0.00019933159613395822 tokens_per_second_per_gpu:2151.0781303712442 
Step 375 | loss:3.0570898056030273 lr:0.00019932704655131436 tokens_per_second_per_gpu:2195.550356859124 
Step 376 | loss:2.953754425048828 lr:0.00019932248158973745 tokens_per_second_per_gpu:2158.9866595338326 
Step 377 | loss:3.05592679977417 lr:0.00019931790124993434 tokens_per_second_per_gpu:2169.1387123875156 
Step 378 | loss:3.032891273498535 lr:0.0001993133055326142 tokens_per_second_per_gpu:2160.067277794613 
Step 379 | loss:3.064265727996826 lr:0.00019930869443848858 tokens_per_second_per_gpu:2130.025587484484 
Step 380 | loss:3.0350732803344727 lr:0.00019930406796827145 tokens_per_second_per_gpu:2177.6564017881155 
Step 381 | loss:3.013793468475342 lr:0.00019929942612267906 tokens_per_second_per_gpu:2061.987448995023 
Step 382 | loss:3.034844398498535 lr:0.00019929476890243018 tokens_per_second_per_gpu:2189.628846638251 
Step 383 | loss:3.0446653366088867 lr:0.00019929009630824585 tokens_per_second_per_gpu:2141.9755506008373 
Step 384 | loss:3.0498335361480713 lr:0.0001992854083408496 tokens_per_second_per_gpu:2193.702579756225 
Step 385 | loss:3.048707962036133 lr:0.0001992807050009672 tokens_per_second_per_gpu:2183.622335827478 
Step 386 | loss:2.998788833618164 lr:0.00019927598628932694 tokens_per_second_per_gpu:2134.405841110551 
Step 387 | loss:3.0346529483795166 lr:0.00019927125220665936 tokens_per_second_per_gpu:2147.730297217903 
Step 388 | loss:2.9827022552490234 lr:0.0001992665027536975 tokens_per_second_per_gpu:2167.143125434378 
Step 389 | loss:3.0409812927246094 lr:0.0001992617379311767 tokens_per_second_per_gpu:2088.9102749294466 
Step 390 | loss:3.0032687187194824 lr:0.00019925695773983466 tokens_per_second_per_gpu:2150.2275601248216 
Step 391 | loss:3.013046979904175 lr:0.0001992521621804116 tokens_per_second_per_gpu:2183.3823411902235 
Step 392 | loss:2.954874038696289 lr:0.00019924735125364992 tokens_per_second_per_gpu:2081.407862704647 
Step 393 | loss:2.9230432510375977 lr:0.00019924252496029453 tokens_per_second_per_gpu:2194.0051787474613 
Step 394 | loss:3.044637680053711 lr:0.00019923768330109277 tokens_per_second_per_gpu:2158.7222010211062 
Step 395 | loss:2.9922475814819336 lr:0.00019923282627679417 tokens_per_second_per_gpu:2180.8467314065947 
Step 396 | loss:3.020153760910034 lr:0.00019922795388815085 tokens_per_second_per_gpu:2188.6022054458977 
Step 397 | loss:2.989739179611206 lr:0.00019922306613591714 tokens_per_second_per_gpu:2183.651964097076 
Step 398 | loss:3.037649154663086 lr:0.00019921816302084983 tokens_per_second_per_gpu:2124.1735105505977 
Step 399 | loss:3.0449869632720947 lr:0.00019921324454370807 tokens_per_second_per_gpu:2122.846507306825 
Step 400 | loss:3.0068259239196777 lr:0.00019920831070525342 tokens_per_second_per_gpu:2050.1617568994134 
Step 401 | loss:2.9908928871154785 lr:0.00019920336150624975 tokens_per_second_per_gpu:2190.0998330296243 
Step 402 | loss:2.930513381958008 lr:0.0001991983969474634 tokens_per_second_per_gpu:2184.5769685800296 
Step 403 | loss:3.0272016525268555 lr:0.00019919341702966302 tokens_per_second_per_gpu:2181.445841071927 
Step 404 | loss:2.939542293548584 lr:0.00019918842175361965 tokens_per_second_per_gpu:2193.6901464325206 
Step 405 | loss:2.964829921722412 lr:0.0001991834111201067 tokens_per_second_per_gpu:2056.9728246844033 
Step 406 | loss:2.94781756401062 lr:0.00019917838512990003 tokens_per_second_per_gpu:2183.814756184995 
Step 407 | loss:3.027554750442505 lr:0.00019917334378377773 tokens_per_second_per_gpu:2175.6890051252626 
Step 408 | loss:2.9379167556762695 lr:0.00019916828708252044 tokens_per_second_per_gpu:2135.0226921911767 
Step 409 | loss:2.9834232330322266 lr:0.00019916321502691108 tokens_per_second_per_gpu:2183.459668675176 
Step 410 | loss:2.9680800437927246 lr:0.0001991581276177349 tokens_per_second_per_gpu:2139.863790610219 
Step 411 | loss:3.022174596786499 lr:0.00019915302485577966 tokens_per_second_per_gpu:2191.7704128673513 
Step 412 | loss:2.961738109588623 lr:0.00019914790674183542 tokens_per_second_per_gpu:2175.836001964516 
Step 413 | loss:2.9115891456604004 lr:0.00019914277327669463 tokens_per_second_per_gpu:2112.285258097761 
Step 414 | loss:2.9009015560150146 lr:0.00019913762446115206 tokens_per_second_per_gpu:2134.4542901562595 
Step 415 | loss:2.9275636672973633 lr:0.00019913246029600493 tokens_per_second_per_gpu:2194.635925663172 
Step 416 | loss:2.9639644622802734 lr:0.00019912728078205283 tokens_per_second_per_gpu:2189.6688485613286 
Step 417 | loss:3.0127291679382324 lr:0.0001991220859200977 tokens_per_second_per_gpu:2074.5757940372046 
Step 418 | loss:2.8366193771362305 lr:0.0001991168757109439 tokens_per_second_per_gpu:2189.7069885718756 
Step 419 | loss:2.9121551513671875 lr:0.00019911165015539805 tokens_per_second_per_gpu:2062.199216523399 
Step 420 | loss:2.93710994720459 lr:0.00019910640925426934 tokens_per_second_per_gpu:2163.048711127094 
Step 421 | loss:2.8675200939178467 lr:0.0001991011530083691 tokens_per_second_per_gpu:2140.3775521674424 
Step 422 | loss:2.9120287895202637 lr:0.00019909588141851128 tokens_per_second_per_gpu:2180.376464940133 
Step 423 | loss:2.9639759063720703 lr:0.00019909059448551203 tokens_per_second_per_gpu:2168.2224190370885 
Step 424 | loss:2.9142749309539795 lr:0.00019908529221018993 tokens_per_second_per_gpu:2152.1929381593354 
Step 425 | loss:2.8353500366210938 lr:0.00019907997459336595 tokens_per_second_per_gpu:2128.3459668437386 
Step 426 | loss:2.8451404571533203 lr:0.00019907464163586346 tokens_per_second_per_gpu:2131.558289985357 
Step 427 | loss:2.952981472015381 lr:0.00019906929333850807 tokens_per_second_per_gpu:2182.6464513489086 
Step 428 | loss:2.9196667671203613 lr:0.00019906392970212792 tokens_per_second_per_gpu:2185.878870296171 
Step 429 | loss:2.8932130336761475 lr:0.00019905855072755352 tokens_per_second_per_gpu:2121.7354830128374 
Step 430 | loss:2.9107513427734375 lr:0.0001990531564156176 tokens_per_second_per_gpu:2168.890541022265 
Step 431 | loss:2.8554139137268066 lr:0.00019904774676715548 tokens_per_second_per_gpu:2173.7771988526797 
Step 432 | loss:2.9410102367401123 lr:0.00019904232178300464 tokens_per_second_per_gpu:2172.297351262176 
Step 433 | loss:2.8966898918151855 lr:0.0001990368814640051 tokens_per_second_per_gpu:2169.6595837204704 
Step 434 | loss:2.910444736480713 lr:0.00019903142581099918 tokens_per_second_per_gpu:2156.748667250221 
Step 435 | loss:2.8313822746276855 lr:0.00019902595482483159 tokens_per_second_per_gpu:2133.4938833070023 
Step 436 | loss:2.8509111404418945 lr:0.00019902046850634933 tokens_per_second_per_gpu:2123.6171459491343 
Step 437 | loss:2.886253833770752 lr:0.000199014966856402 tokens_per_second_per_gpu:2157.1089638266694 
Step 438 | loss:2.826813220977783 lr:0.00019900944987584132 tokens_per_second_per_gpu:2191.2593806496043 
Step 439 | loss:2.8696441650390625 lr:0.00019900391756552153 tokens_per_second_per_gpu:2179.0034016898853 
Step 440 | loss:2.8060836791992188 lr:0.0001989983699262992 tokens_per_second_per_gpu:2169.780881291753 
Step 441 | loss:2.869678020477295 lr:0.00019899280695903325 tokens_per_second_per_gpu:2181.31639589074 
Step 442 | loss:2.8178553581237793 lr:0.00019898722866458507 tokens_per_second_per_gpu:2188.0696766667625 
Step 443 | loss:2.9392669200897217 lr:0.00019898163504381827 tokens_per_second_per_gpu:2185.7562935847964 
Step 444 | loss:2.8944668769836426 lr:0.000198976026097599 tokens_per_second_per_gpu:2146.4110585197686 
Step 445 | loss:2.809072494506836 lr:0.00019897040182679563 tokens_per_second_per_gpu:2185.663761083429 
Step 446 | loss:2.9307949542999268 lr:0.000198964762232279 tokens_per_second_per_gpu:2115.844032177901 
Step 447 | loss:2.8848352432250977 lr:0.00019895910731492232 tokens_per_second_per_gpu:2152.207736706182 
Step 448 | loss:2.8745980262756348 lr:0.00019895343707560108 tokens_per_second_per_gpu:2139.3619816097953 
Step 449 | loss:2.8212063312530518 lr:0.0001989477515151933 tokens_per_second_per_gpu:2153.0143858621477 
Step 450 | loss:2.868129253387451 lr:0.0001989420506345792 tokens_per_second_per_gpu:2129.5924174345773 
Step 451 | loss:2.8486781120300293 lr:0.00019893633443464153 tokens_per_second_per_gpu:2167.723663329197 
Step 452 | loss:2.8013274669647217 lr:0.00019893060291626527 tokens_per_second_per_gpu:2128.174616734983 
Step 453 | loss:2.884625196456909 lr:0.0001989248560803379 tokens_per_second_per_gpu:2133.0163681555587 
Step 454 | loss:2.838745594024658 lr:0.00019891909392774913 tokens_per_second_per_gpu:2159.833067130347 
Step 455 | loss:2.842242956161499 lr:0.0001989133164593912 tokens_per_second_per_gpu:2078.768413673306 
Step 456 | loss:2.830122470855713 lr:0.0001989075236761586 tokens_per_second_per_gpu:2155.0262700887224 
Step 457 | loss:2.8208508491516113 lr:0.00019890171557894823 tokens_per_second_per_gpu:2183.851325119143 
Step 458 | loss:2.8298730850219727 lr:0.0001988958921686594 tokens_per_second_per_gpu:2162.704769934351 
Step 459 | loss:2.787454605102539 lr:0.00019889005344619375 tokens_per_second_per_gpu:2136.022166747781 
Step 460 | loss:2.76130747795105 lr:0.00019888419941245527 tokens_per_second_per_gpu:2091.840811558752 
Step 461 | loss:2.8502705097198486 lr:0.00019887833006835038 tokens_per_second_per_gpu:2131.1387477715944 
Step 462 | loss:2.7923996448516846 lr:0.00019887244541478777 tokens_per_second_per_gpu:2124.9531981695986 
Step 463 | loss:2.785041332244873 lr:0.00019886654545267867 tokens_per_second_per_gpu:2126.532257125748 
Step 464 | loss:2.779367446899414 lr:0.0001988606301829365 tokens_per_second_per_gpu:2115.5276776588234 
Step 465 | loss:2.88679838180542 lr:0.00019885469960647712 tokens_per_second_per_gpu:2191.105386078682 
Step 466 | loss:2.8400344848632812 lr:0.00019884875372421884 tokens_per_second_per_gpu:2192.5395565966514 
Step 467 | loss:2.7641091346740723 lr:0.00019884279253708226 tokens_per_second_per_gpu:2188.8782979033435 
Step 468 | loss:2.794694423675537 lr:0.00019883681604599028 tokens_per_second_per_gpu:2106.5916608258844 
Step 469 | loss:2.8172502517700195 lr:0.00019883082425186833 tokens_per_second_per_gpu:2068.939124249617 
Step 470 | loss:2.7857179641723633 lr:0.00019882481715564407 tokens_per_second_per_gpu:2190.5521219688044 
Step 471 | loss:2.8288846015930176 lr:0.00019881879475824762 tokens_per_second_per_gpu:2152.9341131239835 
Step 472 | loss:2.837838649749756 lr:0.00019881275706061145 tokens_per_second_per_gpu:2178.5443404249686 
Step 473 | loss:2.8952255249023438 lr:0.00019880670406367031 tokens_per_second_per_gpu:2169.458636070964 
Step 474 | loss:2.774448871612549 lr:0.00019880063576836147 tokens_per_second_per_gpu:2093.021251660624 
Step 475 | loss:2.8253300189971924 lr:0.00019879455217562447 tokens_per_second_per_gpu:2172.1762034055737 
Step 476 | loss:2.7902021408081055 lr:0.00019878845328640126 tokens_per_second_per_gpu:2181.0493966911517 
Step 477 | loss:2.7269251346588135 lr:0.0001987823391016361 tokens_per_second_per_gpu:2171.1834610444917 
Step 478 | loss:2.832664966583252 lr:0.00019877620962227566 tokens_per_second_per_gpu:2141.5112401133074 
Step 479 | loss:2.768458366394043 lr:0.00019877006484926896 tokens_per_second_per_gpu:2038.8095446596435 
Step 480 | loss:2.843095302581787 lr:0.00019876390478356748 tokens_per_second_per_gpu:2191.708788580228 
Step 481 | loss:2.7141857147216797 lr:0.00019875772942612492 tokens_per_second_per_gpu:2124.334365733944 
Step 482 | loss:2.738227367401123 lr:0.00019875153877789745 tokens_per_second_per_gpu:2097.8781685286976 
Step 483 | loss:2.7620656490325928 lr:0.00019874533283984356 tokens_per_second_per_gpu:2125.6925099831233 
Step 484 | loss:2.799912929534912 lr:0.0001987391116129241 tokens_per_second_per_gpu:2191.1943747392147 
Step 485 | loss:2.8028130531311035 lr:0.0001987328750981024 tokens_per_second_per_gpu:2189.613289354498 
Step 486 | loss:2.8478808403015137 lr:0.00019872662329634396 tokens_per_second_per_gpu:2109.4939376909574 
Step 487 | loss:2.791975498199463 lr:0.00019872035620861682 tokens_per_second_per_gpu:2147.9002506065126 
Step 488 | loss:2.757051944732666 lr:0.0001987140738358913 tokens_per_second_per_gpu:2123.619620838448 
Step 489 | loss:2.783081293106079 lr:0.0001987077761791401 tokens_per_second_per_gpu:2144.9640466895175 
Step 490 | loss:2.7643399238586426 lr:0.0001987014632393383 tokens_per_second_per_gpu:2124.9878768836425 
Step 491 | loss:2.7411234378814697 lr:0.00019869513501746336 tokens_per_second_per_gpu:2196.9975219147086 
Step 492 | loss:2.76051664352417 lr:0.0001986887915144951 tokens_per_second_per_gpu:2125.378595779243 
Step 493 | loss:2.780240774154663 lr:0.0001986824327314156 tokens_per_second_per_gpu:2167.8943879877966 
Step 494 | loss:2.7751355171203613 lr:0.0001986760586692095 tokens_per_second_per_gpu:2179.103206565156 
Step 495 | loss:2.777805805206299 lr:0.00019866966932886366 tokens_per_second_per_gpu:2199.427341418572 
Step 496 | loss:2.7137417793273926 lr:0.00019866326471136735 tokens_per_second_per_gpu:2150.5213878973595 
Step 497 | loss:2.820430040359497 lr:0.00019865684481771222 tokens_per_second_per_gpu:2159.1451973967596 
Step 498 | loss:2.790492296218872 lr:0.00019865040964889229 tokens_per_second_per_gpu:2063.2259433314853 
Step 499 | loss:2.777337074279785 lr:0.00019864395920590384 tokens_per_second_per_gpu:2143.775693587205 
Step 500 | loss:2.745133399963379 lr:0.0001986374934897457 tokens_per_second_per_gpu:2147.449705449479 
Step 501 | loss:2.8000569343566895 lr:0.0001986310125014189 tokens_per_second_per_gpu:2132.0590681830313 
Step 502 | loss:2.811166286468506 lr:0.00019862451624192692 tokens_per_second_per_gpu:2130.442275037011 
Step 503 | loss:2.813275098800659 lr:0.00019861800471227562 tokens_per_second_per_gpu:2170.209909531882 
Step 504 | loss:2.790980339050293 lr:0.00019861147791347313 tokens_per_second_per_gpu:2189.534702183734 
Step 505 | loss:2.751056671142578 lr:0.00019860493584653003 tokens_per_second_per_gpu:2194.205933087407 
Step 506 | loss:2.7825775146484375 lr:0.00019859837851245922 tokens_per_second_per_gpu:2176.158708220209 
Step 507 | loss:2.753448486328125 lr:0.00019859180591227598 tokens_per_second_per_gpu:2188.8679726941127 
Step 508 | loss:2.8199334144592285 lr:0.000198585218046998 tokens_per_second_per_gpu:2155.9215043158238 
Step 509 | loss:2.75441837310791 lr:0.00019857861491764527 tokens_per_second_per_gpu:2173.5110844465657 
Step 510 | loss:2.7488319873809814 lr:0.00019857199652524013 tokens_per_second_per_gpu:2088.3961165714013 
Step 511 | loss:2.814514636993408 lr:0.00019856536287080734 tokens_per_second_per_gpu:2194.8266730540577 
Step 512 | loss:2.761625051498413 lr:0.00019855871395537395 tokens_per_second_per_gpu:2184.6801144793253 
Step 513 | loss:2.8372302055358887 lr:0.0001985520497799695 tokens_per_second_per_gpu:2162.811526113305 
Step 514 | loss:2.747462749481201 lr:0.00019854537034562575 tokens_per_second_per_gpu:2191.5365760054665 
Step 515 | loss:2.7848854064941406 lr:0.00019853867565337692 tokens_per_second_per_gpu:2187.9102097393634 
Step 516 | loss:2.728212356567383 lr:0.0001985319657042595 tokens_per_second_per_gpu:2189.0395618747552 
Step 517 | loss:2.737391710281372 lr:0.0001985252404993125 tokens_per_second_per_gpu:2191.2706700558106 
Step 518 | loss:2.745673656463623 lr:0.0001985185000395771 tokens_per_second_per_gpu:2127.8254562372595 
Step 519 | loss:2.807575225830078 lr:0.000198511744326097 tokens_per_second_per_gpu:2160.9543412019493 
Step 520 | loss:2.767336368560791 lr:0.00019850497335991815 tokens_per_second_per_gpu:2139.4295525829953 
Step 521 | loss:2.760385274887085 lr:0.00019849818714208893 tokens_per_second_per_gpu:2144.909607579707 
Step 522 | loss:2.7230710983276367 lr:0.00019849138567366005 tokens_per_second_per_gpu:2172.051246910017 
Step 523 | loss:2.723085880279541 lr:0.0001984845689556846 tokens_per_second_per_gpu:2146.093802869478 
Step 524 | loss:2.7994742393493652 lr:0.000198477736989218 tokens_per_second_per_gpu:2189.108485432809 
Step 525 | loss:2.7447142601013184 lr:0.00019847088977531806 tokens_per_second_per_gpu:2144.2604950875684 
Step 526 | loss:2.708967685699463 lr:0.00019846402731504498 tokens_per_second_per_gpu:2156.4322308601572 
Step 527 | loss:2.6419949531555176 lr:0.00019845714960946121 tokens_per_second_per_gpu:2185.7499846825726 
Step 528 | loss:2.75579833984375 lr:0.00019845025665963167 tokens_per_second_per_gpu:2191.207010197339 
Step 529 | loss:2.748640537261963 lr:0.00019844334846662364 tokens_per_second_per_gpu:2153.7589297211853 
Step 530 | loss:2.791985511779785 lr:0.00019843642503150668 tokens_per_second_per_gpu:2138.230488115867 
Step 531 | loss:2.6857476234436035 lr:0.00019842948635535277 tokens_per_second_per_gpu:2186.002009969228 
Step 532 | loss:2.781137228012085 lr:0.00019842253243923622 tokens_per_second_per_gpu:2174.292550810042 
Step 533 | loss:2.6849236488342285 lr:0.00019841556328423375 tokens_per_second_per_gpu:2170.5755514949724 
Step 534 | loss:2.6299562454223633 lr:0.00019840857889142437 tokens_per_second_per_gpu:2127.4799502332376 
Step 535 | loss:2.787003517150879 lr:0.0001984015792618895 tokens_per_second_per_gpu:2190.9153194825326 
Step 536 | loss:2.690023422241211 lr:0.00019839456439671286 tokens_per_second_per_gpu:2167.289254333228 
Step 537 | loss:2.6384124755859375 lr:0.00019838753429698064 tokens_per_second_per_gpu:2143.7840971692963 
Step 538 | loss:2.6747817993164062 lr:0.00019838048896378126 tokens_per_second_per_gpu:2160.3311045790215 
Step 539 | loss:2.7110629081726074 lr:0.0001983734283982056 tokens_per_second_per_gpu:2117.775189887929 
Step 540 | loss:2.692533016204834 lr:0.0001983663526013468 tokens_per_second_per_gpu:2192.218672793952 
Step 541 | loss:2.719618797302246 lr:0.0001983592615743005 tokens_per_second_per_gpu:2184.586400918738 
Step 542 | loss:2.7160446643829346 lr:0.0001983521553181645 tokens_per_second_per_gpu:2060.110393381463 
Step 543 | loss:2.727729320526123 lr:0.0001983450338340392 tokens_per_second_per_gpu:2159.2839010535363 
Step 544 | loss:2.6480307579040527 lr:0.00019833789712302713 tokens_per_second_per_gpu:2188.6756103230878 
Step 545 | loss:2.786926746368408 lr:0.0001983307451862333 tokens_per_second_per_gpu:2064.0633476863577 
Step 546 | loss:2.6914939880371094 lr:0.0001983235780247651 tokens_per_second_per_gpu:2179.3990183201945 
Step 547 | loss:2.669766902923584 lr:0.00019831639563973216 tokens_per_second_per_gpu:2194.3852723401446 
Step 548 | loss:2.672954559326172 lr:0.00019830919803224658 tokens_per_second_per_gpu:2166.5449147920385 
Step 549 | loss:2.6686999797821045 lr:0.0001983019852034228 tokens_per_second_per_gpu:2165.5415466460527 
Step 550 | loss:2.710784435272217 lr:0.0001982947571543775 tokens_per_second_per_gpu:2157.7986345265435 
Step 551 | loss:2.670161008834839 lr:0.0001982875138862299 tokens_per_second_per_gpu:2177.674804679691 
Step 552 | loss:2.708601951599121 lr:0.00019828025540010144 tokens_per_second_per_gpu:2125.146351031761 
Step 553 | loss:2.6746315956115723 lr:0.00019827298169711597 tokens_per_second_per_gpu:2097.956012539484 
Step 554 | loss:2.7045087814331055 lr:0.00019826569277839968 tokens_per_second_per_gpu:2162.469603106009 
Step 555 | loss:2.6608502864837646 lr:0.00019825838864508116 tokens_per_second_per_gpu:2131.4284231695356 
Step 556 | loss:2.7309889793395996 lr:0.00019825106929829126 tokens_per_second_per_gpu:2176.0793984431384 
Step 557 | loss:2.680605888366699 lr:0.0001982437347391633 tokens_per_second_per_gpu:2174.418179677581 
Step 558 | loss:2.7774181365966797 lr:0.00019823638496883284 tokens_per_second_per_gpu:2158.441533916757 
Step 559 | loss:2.711655616760254 lr:0.00019822901998843787 tokens_per_second_per_gpu:2043.5989572138483 
Step 560 | loss:2.678938388824463 lr:0.0001982216397991188 tokens_per_second_per_gpu:2187.4957879835924 
Step 561 | loss:2.618281841278076 lr:0.0001982142444020182 tokens_per_second_per_gpu:2171.9908192652792 
Step 562 | loss:2.711214542388916 lr:0.00019820683379828116 tokens_per_second_per_gpu:2179.7434889840542 
Step 563 | loss:2.6744003295898438 lr:0.0001981994079890551 tokens_per_second_per_gpu:2174.565381002749 
Step 564 | loss:2.681122064590454 lr:0.00019819196697548968 tokens_per_second_per_gpu:2145.4877068377045 
Step 565 | loss:2.7223665714263916 lr:0.00019818451075873713 tokens_per_second_per_gpu:2135.0942163425475 
Step 566 | loss:2.6931586265563965 lr:0.0001981770393399518 tokens_per_second_per_gpu:2193.0565173642967 
Step 567 | loss:2.632111072540283 lr:0.0001981695527202905 tokens_per_second_per_gpu:2135.760463662307 
Step 568 | loss:2.749635696411133 lr:0.0001981620509009125 tokens_per_second_per_gpu:2143.8875079572135 
Step 569 | loss:2.719658613204956 lr:0.0001981545338829792 tokens_per_second_per_gpu:2195.158537159582 
Step 570 | loss:2.6263155937194824 lr:0.0001981470016676545 tokens_per_second_per_gpu:2113.3348092556826 
Step 571 | loss:2.6878418922424316 lr:0.00019813945425610466 tokens_per_second_per_gpu:2145.305784990138 
Step 572 | loss:2.6424202919006348 lr:0.00019813189164949823 tokens_per_second_per_gpu:2158.7477331140335 
Step 573 | loss:2.677095890045166 lr:0.00019812431384900613 tokens_per_second_per_gpu:2176.2172102097234 
Step 574 | loss:2.710324764251709 lr:0.0001981167208558017 tokens_per_second_per_gpu:2190.8942535022684 
Step 575 | loss:2.622511863708496 lr:0.00019810911267106044 tokens_per_second_per_gpu:2193.018291184426 
Step 576 | loss:2.601996421813965 lr:0.00019810148929596047 tokens_per_second_per_gpu:2166.6152188377623 
Step 577 | loss:2.708735466003418 lr:0.00019809385073168206 tokens_per_second_per_gpu:2187.644179674041 
Step 578 | loss:2.697277307510376 lr:0.0001980861969794079 tokens_per_second_per_gpu:2179.207107367371 
Step 579 | loss:2.6821556091308594 lr:0.00019807852804032305 tokens_per_second_per_gpu:2166.526757980194 
Step 580 | loss:2.60663104057312 lr:0.0001980708439156149 tokens_per_second_per_gpu:2132.048452402548 
Step 581 | loss:2.672741651535034 lr:0.00019806314460647318 tokens_per_second_per_gpu:2091.97604214074 
Step 582 | loss:2.649885892868042 lr:0.00019805543011409 tokens_per_second_per_gpu:2184.2989555000495 
Step 583 | loss:2.7146997451782227 lr:0.0001980477004396598 tokens_per_second_per_gpu:2185.121831364935 
Step 584 | loss:2.663761615753174 lr:0.00019803995558437934 tokens_per_second_per_gpu:2163.122560181074 
Step 585 | loss:2.652297019958496 lr:0.00019803219554944784 tokens_per_second_per_gpu:2191.0466365870698 
Step 586 | loss:2.7045836448669434 lr:0.00019802442033606675 tokens_per_second_per_gpu:2067.7175506174385 
Step 587 | loss:2.6409316062927246 lr:0.00019801662994543988 tokens_per_second_per_gpu:2121.143948007343 
Step 588 | loss:2.699911117553711 lr:0.00019800882437877348 tokens_per_second_per_gpu:2196.9482650892865 
Step 589 | loss:2.648373603820801 lr:0.00019800100363727609 tokens_per_second_per_gpu:2143.7997344588525 
Step 590 | loss:2.6313321590423584 lr:0.0001979931677221586 tokens_per_second_per_gpu:2167.1356024099564 
Step 591 | loss:2.6466689109802246 lr:0.00019798531663463425 tokens_per_second_per_gpu:2169.199441038188 
Step 592 | loss:2.6892035007476807 lr:0.00019797745037591864 tokens_per_second_per_gpu:2188.0409725678433 
Step 593 | loss:2.726747512817383 lr:0.0001979695689472297 tokens_per_second_per_gpu:2193.144002588355 
Step 594 | loss:2.662473678588867 lr:0.00019796167234978774 tokens_per_second_per_gpu:2177.1568818981596 
Step 595 | loss:2.656136989593506 lr:0.00019795376058481535 tokens_per_second_per_gpu:2196.4326448607458 
Step 596 | loss:2.6795225143432617 lr:0.0001979458336535376 tokens_per_second_per_gpu:2182.6044776725716 
Step 597 | loss:2.6805617809295654 lr:0.00019793789155718176 tokens_per_second_per_gpu:2171.9739021583946 
Step 598 | loss:2.6489439010620117 lr:0.00019792993429697755 tokens_per_second_per_gpu:2142.4062752362934 
Step 599 | loss:2.5859720706939697 lr:0.000197921961874157 tokens_per_second_per_gpu:2137.3027626138237 
Step 600 | loss:2.660329818725586 lr:0.0001979139742899545 tokens_per_second_per_gpu:2110.9736795036247 
Step 601 | loss:2.7120361328125 lr:0.00019790597154560672 tokens_per_second_per_gpu:2180.9285462746006 
Step 602 | loss:2.6526899337768555 lr:0.0001978979536423528 tokens_per_second_per_gpu:2111.5531315767785 
Step 603 | loss:2.6000008583068848 lr:0.00019788992058143414 tokens_per_second_per_gpu:2176.1040279655526 
Step 604 | loss:2.6199469566345215 lr:0.0001978818723640945 tokens_per_second_per_gpu:2151.0404097047567 
Step 605 | loss:2.5784835815429688 lr:0.00019787380899158002 tokens_per_second_per_gpu:2165.0815530266163 
Step 606 | loss:2.5436739921569824 lr:0.0001978657304651391 tokens_per_second_per_gpu:2182.048275642302 
Step 607 | loss:2.593903064727783 lr:0.00019785763678602263 tokens_per_second_per_gpu:2171.4756687768686 
Step 608 | loss:2.5767321586608887 lr:0.00019784952795548372 tokens_per_second_per_gpu:2169.6382449953394 
Step 609 | loss:2.617802619934082 lr:0.0001978414039747779 tokens_per_second_per_gpu:2178.43008337988 
Step 610 | loss:2.5908291339874268 lr:0.00019783326484516296 tokens_per_second_per_gpu:2141.320843046906 
Step 611 | loss:2.580514430999756 lr:0.00019782511056789915 tokens_per_second_per_gpu:2190.881499640213 
Step 612 | loss:2.6251630783081055 lr:0.00019781694114424898 tokens_per_second_per_gpu:2190.6372148015707 
Step 613 | loss:2.6340718269348145 lr:0.00019780875657547732 tokens_per_second_per_gpu:2177.010797409966 
Step 614 | loss:2.6608495712280273 lr:0.00019780055686285141 tokens_per_second_per_gpu:2187.994064445641 
Step 615 | loss:2.67240047454834 lr:0.00019779234200764084 tokens_per_second_per_gpu:2147.1668902018373 
Step 616 | loss:2.6364736557006836 lr:0.00019778411201111753 tokens_per_second_per_gpu:2150.1765943186097 
Step 617 | loss:2.6652941703796387 lr:0.0001977758668745557 tokens_per_second_per_gpu:2176.4234644889434 
Step 618 | loss:2.702782154083252 lr:0.000197767606599232 tokens_per_second_per_gpu:2147.02596861546 
Step 619 | loss:2.574817180633545 lr:0.00019775933118642533 tokens_per_second_per_gpu:2169.450824874867 
Step 620 | loss:2.5897717475891113 lr:0.00019775104063741704 tokens_per_second_per_gpu:2174.457177308256 
Step 621 | loss:2.688227415084839 lr:0.0001977427349534907 tokens_per_second_per_gpu:2176.4274122312418 
Step 622 | loss:2.6236486434936523 lr:0.00019773441413593234 tokens_per_second_per_gpu:2178.9435107793056 
Step 623 | loss:2.6288156509399414 lr:0.00019772607818603025 tokens_per_second_per_gpu:2177.9106109599024 
Step 624 | loss:2.574270725250244 lr:0.00019771772710507516 tokens_per_second_per_gpu:2148.242607861085 
Step 625 | loss:2.6568846702575684 lr:0.00019770936089436 tokens_per_second_per_gpu:2182.180274563408 
Step 626 | loss:2.6703262329101562 lr:0.00019770097955518017 tokens_per_second_per_gpu:2190.7812225821212 
Step 627 | loss:2.6672863960266113 lr:0.00019769258308883334 tokens_per_second_per_gpu:2162.6878633953575 
Step 628 | loss:2.669607639312744 lr:0.00019768417149661956 tokens_per_second_per_gpu:2173.1428229753406 
Step 629 | loss:2.545098304748535 lr:0.0001976757447798412 tokens_per_second_per_gpu:2168.8097159239787 
Step 630 | loss:2.6263251304626465 lr:0.00019766730293980294 tokens_per_second_per_gpu:2076.7209383752083 
Step 631 | loss:2.62691593170166 lr:0.00019765884597781192 tokens_per_second_per_gpu:2194.4832095763422 
Step 632 | loss:2.6394832134246826 lr:0.0001976503738951775 tokens_per_second_per_gpu:2143.681861542864 
Step 633 | loss:2.6337497234344482 lr:0.0001976418866932114 tokens_per_second_per_gpu:2154.7640764988823 
Step 634 | loss:2.5575754642486572 lr:0.00019763338437322773 tokens_per_second_per_gpu:2123.9880413352726 
Step 635 | loss:2.657378673553467 lr:0.00019762486693654293 tokens_per_second_per_gpu:2195.2904598854357 
Step 636 | loss:2.648214340209961 lr:0.00019761633438447577 tokens_per_second_per_gpu:2058.714815416808 
Step 637 | loss:2.5961978435516357 lr:0.00019760778671834732 tokens_per_second_per_gpu:2188.2839261708596 
Step 638 | loss:2.5779972076416016 lr:0.00019759922393948104 tokens_per_second_per_gpu:2191.5783956993514 
Step 639 | loss:2.6285197734832764 lr:0.00019759064604920273 tokens_per_second_per_gpu:2116.2357916204346 
Step 640 | loss:2.632864475250244 lr:0.0001975820530488405 tokens_per_second_per_gpu:2180.126219042712 
Step 641 | loss:2.6647534370422363 lr:0.0001975734449397248 tokens_per_second_per_gpu:2159.298577782279 
Step 642 | loss:2.6552016735076904 lr:0.00019756482172318847 tokens_per_second_per_gpu:2179.6713994718284 
Step 643 | loss:2.5752081871032715 lr:0.00019755618340056664 tokens_per_second_per_gpu:2198.722387033939 
Step 644 | loss:2.5759871006011963 lr:0.00019754752997319677 tokens_per_second_per_gpu:2126.5427305834005 
Step 645 | loss:2.5968666076660156 lr:0.0001975388614424187 tokens_per_second_per_gpu:2165.1368644220806 
Step 646 | loss:2.5400543212890625 lr:0.00019753017780957461 tokens_per_second_per_gpu:2107.8830106102946 
Step 647 | loss:2.618497371673584 lr:0.000197521479076009 tokens_per_second_per_gpu:2161.884251388971 
Step 648 | loss:2.5450193881988525 lr:0.00019751276524306862 tokens_per_second_per_gpu:2177.4231464252425 
Step 649 | loss:2.570359468460083 lr:0.00019750403631210275 tokens_per_second_per_gpu:2185.1476220913214 
Step 650 | loss:2.609337091445923 lr:0.00019749529228446286 tokens_per_second_per_gpu:2115.7334498169216 
Step 651 | loss:2.5616657733917236 lr:0.0001974865331615028 tokens_per_second_per_gpu:2189.4062625039146 
Step 652 | loss:2.5972089767456055 lr:0.00019747775894457875 tokens_per_second_per_gpu:2191.460461680623 
Step 653 | loss:2.556431531906128 lr:0.00019746896963504921 tokens_per_second_per_gpu:2161.0489086867133 
Step 654 | loss:2.581465244293213 lr:0.00019746016523427513 tokens_per_second_per_gpu:2189.519190068221 
Step 655 | loss:2.5976624488830566 lr:0.0001974513457436196 tokens_per_second_per_gpu:2191.9687781818175 
Step 656 | loss:2.646482467651367 lr:0.00019744251116444818 tokens_per_second_per_gpu:2175.3492392844796 
Step 657 | loss:2.592209815979004 lr:0.00019743366149812882 tokens_per_second_per_gpu:2194.2899129816287 
Step 658 | loss:2.501765251159668 lr:0.00019742479674603162 tokens_per_second_per_gpu:2122.4015535405165 
Step 659 | loss:2.592940330505371 lr:0.00019741591690952914 tokens_per_second_per_gpu:2181.0969979448796 
Step 660 | loss:2.5342845916748047 lr:0.00019740702198999633 tokens_per_second_per_gpu:2143.8967660030144 
Step 661 | loss:2.583951473236084 lr:0.00019739811198881034 tokens_per_second_per_gpu:2160.1521269759523 
Step 662 | loss:2.586122989654541 lr:0.0001973891869073507 tokens_per_second_per_gpu:2173.2314695840073 
Step 663 | loss:2.572995662689209 lr:0.00019738024674699934 tokens_per_second_per_gpu:2149.227873298464 
Step 664 | loss:2.585667133331299 lr:0.00019737129150914045 tokens_per_second_per_gpu:2165.314610824972 
Step 665 | loss:2.546611785888672 lr:0.00019736232119516058 tokens_per_second_per_gpu:2194.0700454640214 
Step 666 | loss:2.6275858879089355 lr:0.00019735333580644864 tokens_per_second_per_gpu:2192.5052692293007 
Step 667 | loss:2.5388736724853516 lr:0.0001973443353443958 tokens_per_second_per_gpu:2178.0746972726047 
Step 668 | loss:2.60270619392395 lr:0.00019733531981039568 tokens_per_second_per_gpu:2191.99943507956 
Step 669 | loss:2.5352468490600586 lr:0.00019732628920584412 tokens_per_second_per_gpu:2170.56907353008 
Step 670 | loss:2.507418155670166 lr:0.00019731724353213933 tokens_per_second_per_gpu:2155.51884154567 
Step 671 | loss:2.523854970932007 lr:0.00019730818279068188 tokens_per_second_per_gpu:2176.9894531076698 
Step 672 | loss:2.504410743713379 lr:0.0001972991069828747 tokens_per_second_per_gpu:2141.8460761078386 
Step 673 | loss:2.4939422607421875 lr:0.00019729001611012295 tokens_per_second_per_gpu:2107.5072970018696 
Step 674 | loss:2.5866212844848633 lr:0.00019728091017383418 tokens_per_second_per_gpu:2161.983663807984 
Step 675 | loss:2.57228946685791 lr:0.00019727178917541832 tokens_per_second_per_gpu:2147.8364598783705 
Step 676 | loss:2.5633957386016846 lr:0.00019726265311628756 tokens_per_second_per_gpu:2179.1954282694965 
Step 677 | loss:2.6071386337280273 lr:0.00019725350199785641 tokens_per_second_per_gpu:2185.351180197273 
Step 678 | loss:2.5832276344299316 lr:0.0001972443358215418 tokens_per_second_per_gpu:2183.5470504928758 
Step 679 | loss:2.5085620880126953 lr:0.00019723515458876297 tokens_per_second_per_gpu:2152.4615060517826 
Step 680 | loss:2.500436782836914 lr:0.00019722595830094138 tokens_per_second_per_gpu:2175.4003032738215 
Step 681 | loss:2.6131632328033447 lr:0.00019721674695950093 tokens_per_second_per_gpu:2141.762940028003 
Step 682 | loss:2.5070302486419678 lr:0.0001972075205658679 tokens_per_second_per_gpu:2164.472668641659 
Step 683 | loss:2.5573015213012695 lr:0.0001971982791214707 tokens_per_second_per_gpu:2149.752634238848 
Step 684 | loss:2.5717263221740723 lr:0.00019718902262774027 tokens_per_second_per_gpu:2134.8365777191675 
Step 685 | loss:2.558342695236206 lr:0.0001971797510861098 tokens_per_second_per_gpu:2199.777932459444 
Step 686 | loss:2.5348682403564453 lr:0.00019717046449801477 tokens_per_second_per_gpu:2150.1527052313863 
Step 687 | loss:2.52809739112854 lr:0.0001971611628648931 tokens_per_second_per_gpu:2157.650343667774 
Step 688 | loss:2.6335935592651367 lr:0.00019715184618818493 tokens_per_second_per_gpu:2195.0218019768035 
Step 689 | loss:2.5090246200561523 lr:0.0001971425144693328 tokens_per_second_per_gpu:2168.1135893718406 
Step 690 | loss:2.5928452014923096 lr:0.00019713316770978155 tokens_per_second_per_gpu:2163.687217786822 
Step 691 | loss:2.5499019622802734 lr:0.0001971238059109783 tokens_per_second_per_gpu:2161.0373898593693 
Step 692 | loss:2.557058095932007 lr:0.00019711442907437257 tokens_per_second_per_gpu:2166.1070705212082 
Step 693 | loss:2.5065460205078125 lr:0.00019710503720141625 tokens_per_second_per_gpu:2194.1547308319036 
Step 694 | loss:2.5298726558685303 lr:0.00019709563029356343 tokens_per_second_per_gpu:2186.8844642872905 
Step 695 | loss:2.489626407623291 lr:0.00019708620835227062 tokens_per_second_per_gpu:2190.0377564719597 
Step 696 | loss:2.503054618835449 lr:0.00019707677137899662 tokens_per_second_per_gpu:2156.961984098099 
Step 697 | loss:2.5553054809570312 lr:0.00019706731937520257 tokens_per_second_per_gpu:2179.1921275851046 
Step 698 | loss:2.5802958011627197 lr:0.00019705785234235197 tokens_per_second_per_gpu:2120.3414018357585 
Step 699 | loss:2.4892282485961914 lr:0.00019704837028191054 tokens_per_second_per_gpu:2154.2960358898245 
Step 700 | loss:2.5125815868377686 lr:0.00019703887319534645 tokens_per_second_per_gpu:2167.6150964292774 
Step 701 | loss:2.5004401206970215 lr:0.00019702936108413014 tokens_per_second_per_gpu:2187.6705346627587 
Step 702 | loss:2.5261623859405518 lr:0.0001970198339497344 tokens_per_second_per_gpu:2140.0071548200044 
Step 703 | loss:2.551722526550293 lr:0.00019701029179363427 tokens_per_second_per_gpu:2186.0305199425484 
Step 704 | loss:2.550705909729004 lr:0.00019700073461730727 tokens_per_second_per_gpu:2165.237995882496 
Step 705 | loss:2.62253475189209 lr:0.00019699116242223306 tokens_per_second_per_gpu:2152.025865104067 
Step 706 | loss:2.548370361328125 lr:0.00019698157520989373 tokens_per_second_per_gpu:2164.8558122559175 
Step 707 | loss:2.5669350624084473 lr:0.0001969719729817737 tokens_per_second_per_gpu:2188.8691600215093 
Step 708 | loss:2.5742459297180176 lr:0.0001969623557393597 tokens_per_second_per_gpu:2128.2285151372325 
Step 709 | loss:2.5599164962768555 lr:0.00019695272348414078 tokens_per_second_per_gpu:2184.437098869199 
Step 710 | loss:2.5152993202209473 lr:0.0001969430762176083 tokens_per_second_per_gpu:2143.59795441736 
Step 711 | loss:2.488705635070801 lr:0.00019693341394125597 tokens_per_second_per_gpu:2193.9541588835523 
Step 712 | loss:2.576104164123535 lr:0.00019692373665657978 tokens_per_second_per_gpu:2178.6212582416665 
Step 713 | loss:2.589257001876831 lr:0.00019691404436507815 tokens_per_second_per_gpu:2096.47066124676 
Step 714 | loss:2.505171775817871 lr:0.0001969043370682517 tokens_per_second_per_gpu:2137.235115065457 
Step 715 | loss:2.5107479095458984 lr:0.0001968946147676034 tokens_per_second_per_gpu:2116.2550710152723 
Step 716 | loss:2.4998583793640137 lr:0.00019688487746463858 tokens_per_second_per_gpu:2124.8119863417983 
Step 717 | loss:2.5351428985595703 lr:0.00019687512516086494 tokens_per_second_per_gpu:2187.9147515426253 
Step 718 | loss:2.5137622356414795 lr:0.00019686535785779234 tokens_per_second_per_gpu:2089.9440832785244 
Step 719 | loss:2.50872540473938 lr:0.00019685557555693315 tokens_per_second_per_gpu:2192.134772779553 
Step 720 | loss:2.540919303894043 lr:0.00019684577825980192 tokens_per_second_per_gpu:2186.3908864575574 
Step 721 | loss:2.5276310443878174 lr:0.00019683596596791562 tokens_per_second_per_gpu:2193.0394360242485 
Step 722 | loss:2.554811954498291 lr:0.00019682613868279348 tokens_per_second_per_gpu:2123.3596102381744 
Step 723 | loss:2.4938840866088867 lr:0.0001968162964059571 tokens_per_second_per_gpu:2172.4538098268963 
Step 724 | loss:2.489712715148926 lr:0.0001968064391389303 tokens_per_second_per_gpu:2146.0147266111026 
Step 725 | loss:2.5574474334716797 lr:0.00019679656688323936 tokens_per_second_per_gpu:2175.2796540895965 
Step 726 | loss:2.623664617538452 lr:0.0001967866796404128 tokens_per_second_per_gpu:2191.7248359608657 
Step 727 | loss:2.534414768218994 lr:0.00019677677741198143 tokens_per_second_per_gpu:2080.695051730179 
Step 728 | loss:2.5625526905059814 lr:0.0001967668601994785 tokens_per_second_per_gpu:2180.570419553155 
Step 729 | loss:2.479236364364624 lr:0.00019675692800443943 tokens_per_second_per_gpu:2189.258127071757 
Step 730 | loss:2.5106430053710938 lr:0.00019674698082840212 tokens_per_second_per_gpu:2164.3928075572553 
Step 731 | loss:2.4967145919799805 lr:0.0001967370186729066 tokens_per_second_per_gpu:2183.133309599351 
Step 732 | loss:2.6131184101104736 lr:0.0001967270415394954 tokens_per_second_per_gpu:2199.5969731020036 
Step 733 | loss:2.5462517738342285 lr:0.00019671704942971326 tokens_per_second_per_gpu:2196.2072835000376 
Step 734 | loss:2.5215845108032227 lr:0.0001967070423451073 tokens_per_second_per_gpu:2173.369450645459 
Step 735 | loss:2.535830020904541 lr:0.00019669702028722689 tokens_per_second_per_gpu:2195.515165514862 
Step 736 | loss:2.551238536834717 lr:0.0001966869832576238 tokens_per_second_per_gpu:2165.475026286916 
Step 737 | loss:2.5036330223083496 lr:0.000196676931257852 tokens_per_second_per_gpu:2155.501527802484 
Step 738 | loss:2.4937963485717773 lr:0.00019666686428946797 tokens_per_second_per_gpu:2177.676426511618 
Step 739 | loss:2.5239367485046387 lr:0.00019665678235403032 tokens_per_second_per_gpu:2194.942957705148 
Step 740 | loss:2.5246410369873047 lr:0.00019664668545310004 tokens_per_second_per_gpu:2178.7374096443477 
Step 741 | loss:2.463460683822632 lr:0.00019663657358824047 tokens_per_second_per_gpu:2137.642605665711 
Step 742 | loss:2.475243091583252 lr:0.00019662644676101724 tokens_per_second_per_gpu:2195.5179305817455 
Step 743 | loss:2.503587245941162 lr:0.0001966163049729983 tokens_per_second_per_gpu:2189.6959362779744 
Step 744 | loss:2.551048755645752 lr:0.0001966061482257539 tokens_per_second_per_gpu:2133.2851006611686 
Step 745 | loss:2.482998847961426 lr:0.00019659597652085665 tokens_per_second_per_gpu:2178.550143974732 
Step 746 | loss:2.5187299251556396 lr:0.00019658578985988143 tokens_per_second_per_gpu:2195.589751971248 
Step 747 | loss:2.48514986038208 lr:0.00019657558824440546 tokens_per_second_per_gpu:2196.0194789519483 
Step 748 | loss:2.5089335441589355 lr:0.00019656537167600825 tokens_per_second_per_gpu:2187.1446963768135 
Step 749 | loss:2.52497935295105 lr:0.00019655514015627166 tokens_per_second_per_gpu:2121.124829834254 
Step 750 | loss:2.4937427043914795 lr:0.00019654489368677985 tokens_per_second_per_gpu:2195.8853456027637 
Step 751 | loss:2.4711763858795166 lr:0.0001965346322691193 tokens_per_second_per_gpu:2190.3383551717397 
Step 752 | loss:2.484457015991211 lr:0.0001965243559048788 tokens_per_second_per_gpu:2196.3449282186875 
Step 753 | loss:2.4579248428344727 lr:0.00019651406459564942 tokens_per_second_per_gpu:2188.020359832383 
Step 754 | loss:2.468555450439453 lr:0.0001965037583430246 tokens_per_second_per_gpu:2116.838874217808 
Step 755 | loss:2.57804536819458 lr:0.00019649343714860012 tokens_per_second_per_gpu:2168.576358875591 
Step 756 | loss:2.4629716873168945 lr:0.00019648310101397391 tokens_per_second_per_gpu:2105.453836668915 
Step 757 | loss:2.48858642578125 lr:0.00019647274994074644 tokens_per_second_per_gpu:2156.2811075802415 
Step 758 | loss:2.4605517387390137 lr:0.0001964623839305203 tokens_per_second_per_gpu:2182.3883696622315 
Step 759 | loss:2.444230556488037 lr:0.00019645200298490053 tokens_per_second_per_gpu:2190.1708937426793 
Step 760 | loss:2.555870771408081 lr:0.00019644160710549437 tokens_per_second_per_gpu:2181.7119348927536 
Step 761 | loss:2.4995570182800293 lr:0.00019643119629391147 tokens_per_second_per_gpu:2186.6789183728365 
Step 762 | loss:2.5039196014404297 lr:0.00019642077055176375 tokens_per_second_per_gpu:2193.7790854202935 
Step 763 | loss:2.534787654876709 lr:0.0001964103298806654 tokens_per_second_per_gpu:2179.5709191964092 
Step 764 | loss:2.504903793334961 lr:0.000196399874282233 tokens_per_second_per_gpu:2157.639522838347 
Step 765 | loss:2.5047953128814697 lr:0.0001963894037580854 tokens_per_second_per_gpu:2182.087868039712 
Step 766 | loss:2.479081869125366 lr:0.00019637891830984373 tokens_per_second_per_gpu:2197.0789037269483 
Step 767 | loss:2.4539639949798584 lr:0.0001963684179391315 tokens_per_second_per_gpu:2040.6753584328344 
Step 768 | loss:2.447678327560425 lr:0.0001963579026475745 tokens_per_second_per_gpu:2159.709056613154 
Step 769 | loss:2.5457077026367188 lr:0.00019634737243680084 tokens_per_second_per_gpu:2167.9043137433237 
Step 770 | loss:2.424098014831543 lr:0.00019633682730844086 tokens_per_second_per_gpu:2154.9199856408245 
Step 771 | loss:2.513559341430664 lr:0.00019632626726412734 tokens_per_second_per_gpu:2199.793875237687 
Step 772 | loss:2.461334228515625 lr:0.00019631569230549523 tokens_per_second_per_gpu:2169.918824207891 
Step 773 | loss:2.4543964862823486 lr:0.00019630510243418196 tokens_per_second_per_gpu:2161.900302573656 
Step 774 | loss:2.41628360748291 lr:0.0001962944976518271 tokens_per_second_per_gpu:2189.481578932819 
Step 775 | loss:2.489475965499878 lr:0.00019628387796007265 tokens_per_second_per_gpu:2138.2428015104956 
Step 776 | loss:2.481313705444336 lr:0.00019627324336056289 tokens_per_second_per_gpu:2178.124468338345 
Step 777 | loss:2.4827804565429688 lr:0.00019626259385494428 tokens_per_second_per_gpu:2187.3458190674087 
Step 778 | loss:2.4713292121887207 lr:0.00019625192944486579 tokens_per_second_per_gpu:2169.6559577381 
Step 779 | loss:2.5045697689056396 lr:0.00019624125013197857 tokens_per_second_per_gpu:2155.8559023590374 
Step 780 | loss:2.4522194862365723 lr:0.00019623055591793613 tokens_per_second_per_gpu:2187.85309013858 
Step 781 | loss:2.4929428100585938 lr:0.00019621984680439426 tokens_per_second_per_gpu:2197.589838999602 
Step 782 | loss:2.521237850189209 lr:0.0001962091227930111 tokens_per_second_per_gpu:2191.3853489756284 
Step 783 | loss:2.537674903869629 lr:0.00019619838388544697 tokens_per_second_per_gpu:2165.2136904374315 
Step 784 | loss:2.4659574031829834 lr:0.00019618763008336467 tokens_per_second_per_gpu:2167.253175288812 
Step 785 | loss:2.540367603302002 lr:0.0001961768613884292 tokens_per_second_per_gpu:2183.8762095856623 
Step 786 | loss:2.421727180480957 lr:0.00019616607780230792 tokens_per_second_per_gpu:2076.0843609101994 
Step 787 | loss:2.407494306564331 lr:0.0001961552793266704 tokens_per_second_per_gpu:2199.851074083736 
Step 788 | loss:2.453367233276367 lr:0.00019614446596318862 tokens_per_second_per_gpu:2182.2305125748317 
Step 789 | loss:2.5309810638427734 lr:0.00019613363771353684 tokens_per_second_per_gpu:2149.738908818673 
Step 790 | loss:2.496943950653076 lr:0.0001961227945793916 tokens_per_second_per_gpu:2194.79607098008 
Step 791 | loss:2.4182848930358887 lr:0.00019611193656243175 tokens_per_second_per_gpu:2158.426955513163 
Step 792 | loss:2.5198044776916504 lr:0.00019610106366433846 tokens_per_second_per_gpu:2194.3779587715003 
Step 793 | loss:2.476348400115967 lr:0.0001960901758867952 tokens_per_second_per_gpu:2192.0818943284708 
Step 794 | loss:2.4773850440979004 lr:0.00019607927323148772 tokens_per_second_per_gpu:2168.7239928142 
Step 795 | loss:2.463615894317627 lr:0.0001960683557001041 tokens_per_second_per_gpu:2123.9943963430014 
Step 796 | loss:2.3844590187072754 lr:0.00019605742329433472 tokens_per_second_per_gpu:2147.890830270788 
Step 797 | loss:2.4885261058807373 lr:0.0001960464760158722 tokens_per_second_per_gpu:2174.0482668572045 
Step 798 | loss:2.4857892990112305 lr:0.00019603551386641166 tokens_per_second_per_gpu:2180.1083776452024 
Step 799 | loss:2.4784281253814697 lr:0.00019602453684765028 tokens_per_second_per_gpu:2179.64886258421 
Step 800 | loss:2.4363932609558105 lr:0.00019601354496128764 tokens_per_second_per_gpu:2164.113018621828 
Step 801 | loss:2.51161527633667 lr:0.00019600253820902566 tokens_per_second_per_gpu:2161.1307503683283 
Step 802 | loss:2.493678092956543 lr:0.00019599151659256854 tokens_per_second_per_gpu:2150.148360953689 
Step 803 | loss:2.4358038902282715 lr:0.00019598048011362272 tokens_per_second_per_gpu:2158.716584314646 
Step 804 | loss:2.49387788772583 lr:0.00019596942877389702 tokens_per_second_per_gpu:2153.082022841506 
Step 805 | loss:2.4646201133728027 lr:0.00019595836257510257 tokens_per_second_per_gpu:2079.5954317148594 
Step 806 | loss:2.478379249572754 lr:0.0001959472815189527 tokens_per_second_per_gpu:2194.724126355116 
Step 807 | loss:2.458087682723999 lr:0.00019593618560716317 tokens_per_second_per_gpu:2118.5826367419268 
Step 808 | loss:2.456179618835449 lr:0.00019592507484145192 tokens_per_second_per_gpu:2137.334230803468 
Step 809 | loss:2.521397829055786 lr:0.00019591394922353927 tokens_per_second_per_gpu:2184.6353010927483 
Step 810 | loss:2.507659435272217 lr:0.0001959028087551478 tokens_per_second_per_gpu:2153.878017428997 
Step 811 | loss:2.431830406188965 lr:0.00019589165343800242 tokens_per_second_per_gpu:2189.7213690699823 
Step 812 | loss:2.4635658264160156 lr:0.0001958804832738303 tokens_per_second_per_gpu:2109.5794789555953 
Step 813 | loss:2.434638023376465 lr:0.00019586929826436095 tokens_per_second_per_gpu:2161.257990213075 
Step 814 | loss:2.4669322967529297 lr:0.00019585809841132616 tokens_per_second_per_gpu:2164.5288983889736 
Step 815 | loss:2.5231261253356934 lr:0.00019584688371646 tokens_per_second_per_gpu:2154.8765166677645 
Step 816 | loss:2.540534496307373 lr:0.00019583565418149887 tokens_per_second_per_gpu:2180.7402168120066 
Step 817 | loss:2.404752731323242 lr:0.00019582440980818144 tokens_per_second_per_gpu:2158.3408966138686 
Step 818 | loss:2.4512314796447754 lr:0.0001958131505982487 tokens_per_second_per_gpu:2033.4584118937753 
Step 819 | loss:2.4759321212768555 lr:0.00019580187655344393 tokens_per_second_per_gpu:2180.487940033844 
Step 820 | loss:2.4645638465881348 lr:0.0001957905876755127 tokens_per_second_per_gpu:2191.5098510132657 
Step 821 | loss:2.484894037246704 lr:0.00019577928396620288 tokens_per_second_per_gpu:2176.4726019605446 
Step 822 | loss:2.4128055572509766 lr:0.00019576796542726465 tokens_per_second_per_gpu:2156.6773933729914 
Step 823 | loss:2.4718856811523438 lr:0.00019575663206045045 tokens_per_second_per_gpu:2178.772135574013 
Step 824 | loss:2.407388687133789 lr:0.00019574528386751507 tokens_per_second_per_gpu:2164.057712999191 
Step 825 | loss:2.4345059394836426 lr:0.00019573392085021554 tokens_per_second_per_gpu:2179.897540919828 
Step 826 | loss:2.431455135345459 lr:0.0001957225430103112 tokens_per_second_per_gpu:2164.096342048882 
Step 827 | loss:2.4227285385131836 lr:0.00019571115034956374 tokens_per_second_per_gpu:2152.956923870815 
Step 828 | loss:2.4409546852111816 lr:0.0001956997428697371 tokens_per_second_per_gpu:2179.294521952962 
Step 829 | loss:2.4267220497131348 lr:0.00019568832057259743 tokens_per_second_per_gpu:2179.6082397820414 
Step 830 | loss:2.451066493988037 lr:0.00019567688345991334 tokens_per_second_per_gpu:2148.058374043126 
Step 831 | loss:2.4116296768188477 lr:0.00019566543153345565 tokens_per_second_per_gpu:2189.577601728805 
Step 832 | loss:2.492938995361328 lr:0.00019565396479499745 tokens_per_second_per_gpu:2183.037932788698 
Step 833 | loss:2.5017693042755127 lr:0.00019564248324631413 tokens_per_second_per_gpu:2175.73396490754 
Step 834 | loss:2.5049262046813965 lr:0.00019563098688918346 tokens_per_second_per_gpu:2182.341351555422 
Step 835 | loss:2.466973066329956 lr:0.00019561947572538537 tokens_per_second_per_gpu:2174.3810060913734 
Step 836 | loss:2.4656195640563965 lr:0.00019560794975670217 tokens_per_second_per_gpu:2136.604551087573 
Step 837 | loss:2.4384841918945312 lr:0.00019559640898491847 tokens_per_second_per_gpu:2190.555596853427 
Step 838 | loss:2.4219131469726562 lr:0.0001955848534118211 tokens_per_second_per_gpu:2132.736222524926 
Step 839 | loss:2.441516399383545 lr:0.00019557328303919925 tokens_per_second_per_gpu:2068.9282036929203 
Step 840 | loss:2.480923652648926 lr:0.00019556169786884436 tokens_per_second_per_gpu:2151.7985382831307 
Step 841 | loss:2.4753851890563965 lr:0.00019555009790255017 tokens_per_second_per_gpu:2146.1398984396055 
Step 842 | loss:2.505016326904297 lr:0.00019553848314211273 tokens_per_second_per_gpu:2132.9353645857645 
Step 843 | loss:2.449643611907959 lr:0.0001955268535893304 tokens_per_second_per_gpu:2162.9124745265804 
Step 844 | loss:2.4469172954559326 lr:0.00019551520924600374 tokens_per_second_per_gpu:2190.003689055467 
Step 845 | loss:2.3827691078186035 lr:0.0001955035501139357 tokens_per_second_per_gpu:2192.9582081019016 
Step 846 | loss:2.4743757247924805 lr:0.00019549187619493144 tokens_per_second_per_gpu:2183.116724440725 
Step 847 | loss:2.413212299346924 lr:0.00019548018749079849 tokens_per_second_per_gpu:2176.722170948286 
Step 848 | loss:2.3998024463653564 lr:0.0001954684840033466 tokens_per_second_per_gpu:2186.2631583413718 
Step 849 | loss:2.4423646926879883 lr:0.00019545676573438784 tokens_per_second_per_gpu:2169.910343205205 
Step 850 | loss:2.429377555847168 lr:0.00019544503268573656 tokens_per_second_per_gpu:2158.6949956131034 
Step 851 | loss:2.467055320739746 lr:0.00019543328485920945 tokens_per_second_per_gpu:2193.9561027093787 
Step 852 | loss:2.496171712875366 lr:0.0001954215222566254 tokens_per_second_per_gpu:2093.179207084011 
Step 853 | loss:2.4794065952301025 lr:0.0001954097448798056 tokens_per_second_per_gpu:2130.8971017469908 
Step 854 | loss:2.503868818283081 lr:0.0001953979527305736 tokens_per_second_per_gpu:2082.758032745747 
Step 855 | loss:2.4665045738220215 lr:0.00019538614581075518 tokens_per_second_per_gpu:2186.1927475231278 
Step 856 | loss:2.4885170459747314 lr:0.00019537432412217843 tokens_per_second_per_gpu:2130.6024538254014 
Step 857 | loss:2.4065959453582764 lr:0.00019536248766667368 tokens_per_second_per_gpu:2184.7143948851335 
Step 858 | loss:2.4428892135620117 lr:0.00019535063644607364 tokens_per_second_per_gpu:2122.772005250348 
Step 859 | loss:2.4091835021972656 lr:0.0001953387704622132 tokens_per_second_per_gpu:2153.2178699161796 
Step 860 | loss:2.451939582824707 lr:0.00019532688971692964 tokens_per_second_per_gpu:2192.5129034573156 
Step 861 | loss:2.4396793842315674 lr:0.0001953149942120624 tokens_per_second_per_gpu:2185.720381669769 
Step 862 | loss:2.4230971336364746 lr:0.00019530308394945334 tokens_per_second_per_gpu:2172.8626526355124 
Step 863 | loss:2.4475178718566895 lr:0.00019529115893094653 tokens_per_second_per_gpu:2190.9969170526597 
Step 864 | loss:2.5109081268310547 lr:0.00019527921915838827 tokens_per_second_per_gpu:2186.67774871297 
Step 865 | loss:2.397376537322998 lr:0.00019526726463362727 tokens_per_second_per_gpu:2139.1997710394517 
Step 866 | loss:2.390381336212158 lr:0.0001952552953585145 tokens_per_second_per_gpu:2172.061634552186 
Step 867 | loss:2.4814157485961914 lr:0.0001952433113349031 tokens_per_second_per_gpu:2166.466768625308 
Step 868 | loss:2.5074710845947266 lr:0.0001952313125646486 tokens_per_second_per_gpu:2190.2826152025773 
Step 869 | loss:2.4122767448425293 lr:0.0001952192990496088 tokens_per_second_per_gpu:2196.8432037623484 
Step 870 | loss:2.3854408264160156 lr:0.00019520727079164375 tokens_per_second_per_gpu:2166.4903046071367 
Step 871 | loss:2.4208359718322754 lr:0.0001951952277926158 tokens_per_second_per_gpu:2196.3722615649235 
Step 872 | loss:2.4225077629089355 lr:0.00019518317005438963 tokens_per_second_per_gpu:2179.9280202633927 
Step 873 | loss:2.44681978225708 lr:0.0001951710975788321 tokens_per_second_per_gpu:2197.0460851891835 
Step 874 | loss:2.482365131378174 lr:0.0001951590103678124 tokens_per_second_per_gpu:2115.975426627717 
Step 875 | loss:2.4675979614257812 lr:0.00019514690842320205 tokens_per_second_per_gpu:2193.0420574213235 
Step 876 | loss:2.4110817909240723 lr:0.0001951347917468748 tokens_per_second_per_gpu:2143.7049521292997 
Step 877 | loss:2.3892784118652344 lr:0.00019512266034070664 tokens_per_second_per_gpu:2091.7319130351893 
Step 878 | loss:2.4562253952026367 lr:0.00019511051420657597 tokens_per_second_per_gpu:2133.791796445557 
Step 879 | loss:2.455791473388672 lr:0.00019509835334636334 tokens_per_second_per_gpu:2180.971480018114 
Step 880 | loss:2.4556689262390137 lr:0.00019508617776195167 tokens_per_second_per_gpu:2100.5549792674533 
Step 881 | loss:2.4867072105407715 lr:0.00019507398745522605 tokens_per_second_per_gpu:2131.445359774411 
Step 882 | loss:2.4254038333892822 lr:0.000195061782428074 tokens_per_second_per_gpu:2119.901293085975 
Step 883 | loss:2.4088258743286133 lr:0.00019504956268238518 tokens_per_second_per_gpu:2195.4262892121565 
Step 884 | loss:2.4687657356262207 lr:0.00019503732822005162 tokens_per_second_per_gpu:2186.2833330252247 
Step 885 | loss:2.454954147338867 lr:0.00019502507904296763 tokens_per_second_per_gpu:2123.060698729882 
Step 886 | loss:2.3818159103393555 lr:0.00019501281515302968 tokens_per_second_per_gpu:2141.913238639444 
Step 887 | loss:2.4723968505859375 lr:0.0001950005365521367 tokens_per_second_per_gpu:2143.708793607298 
Step 888 | loss:2.43727445602417 lr:0.0001949882432421897 tokens_per_second_per_gpu:2171.959624542614 
Step 889 | loss:2.3909084796905518 lr:0.00019497593522509218 tokens_per_second_per_gpu:2171.584618686491 
Step 890 | loss:2.404398202896118 lr:0.0001949636125027497 tokens_per_second_per_gpu:2128.3540421786342 
Step 891 | loss:2.3920278549194336 lr:0.00019495127507707026 tokens_per_second_per_gpu:2194.2873603472126 
Step 892 | loss:2.343437671661377 lr:0.0001949389229499641 tokens_per_second_per_gpu:2181.2752675270817 
Step 893 | loss:2.428288459777832 lr:0.00019492655612334366 tokens_per_second_per_gpu:2193.1728598632853 
Step 894 | loss:2.4165661334991455 lr:0.00019491417459912373 tokens_per_second_per_gpu:2188.2893228098333 
Step 895 | loss:2.462430000305176 lr:0.00019490177837922138 tokens_per_second_per_gpu:2175.493453191102 
Step 896 | loss:2.4556336402893066 lr:0.00019488936746555593 tokens_per_second_per_gpu:2139.7742224375047 
Step 897 | loss:2.42987060546875 lr:0.00019487694186004893 tokens_per_second_per_gpu:2177.104660445358 
Step 898 | loss:2.455872058868408 lr:0.0001948645015646243 tokens_per_second_per_gpu:2152.2481732387864 
Step 899 | loss:2.324936866760254 lr:0.00019485204658120818 tokens_per_second_per_gpu:2169.3497416087544 
Step 900 | loss:2.4488067626953125 lr:0.000194839576911729 tokens_per_second_per_gpu:2179.557871986277 
Step 901 | loss:2.5097622871398926 lr:0.00019482709255811743 tokens_per_second_per_gpu:2165.853751056559 
Step 902 | loss:2.408949851989746 lr:0.0001948145935223064 tokens_per_second_per_gpu:2091.6941080619918 
Step 903 | loss:2.4464211463928223 lr:0.00019480207980623128 tokens_per_second_per_gpu:2197.3828005151536 
Step 904 | loss:2.3910202980041504 lr:0.00019478955141182945 tokens_per_second_per_gpu:2176.470919455121 
Step 905 | loss:2.4673585891723633 lr:0.00019477700834104078 tokens_per_second_per_gpu:2187.2954185973176 
Step 906 | loss:2.4771833419799805 lr:0.00019476445059580727 tokens_per_second_per_gpu:2194.3124717290257 
Step 907 | loss:2.4297027587890625 lr:0.00019475187817807332 tokens_per_second_per_gpu:2153.290676765768 
Step 908 | loss:2.3505160808563232 lr:0.00019473929108978545 tokens_per_second_per_gpu:2181.899004803918 
Step 909 | loss:2.386273145675659 lr:0.00019472668933289263 tokens_per_second_per_gpu:2097.5968298834177 
Step 910 | loss:2.445267677307129 lr:0.00019471407290934593 tokens_per_second_per_gpu:2174.314244909928 
Step 911 | loss:2.425942897796631 lr:0.0001947014418210988 tokens_per_second_per_gpu:2180.9912326246395 
Step 912 | loss:2.327883720397949 lr:0.0001946887960701069 tokens_per_second_per_gpu:2156.3346120540955 
Step 913 | loss:2.4580750465393066 lr:0.00019467613565832823 tokens_per_second_per_gpu:2186.6211781242114 
Step 914 | loss:2.337125778198242 lr:0.00019466346058772297 tokens_per_second_per_gpu:2138.203319259019 
Step 915 | loss:2.4929544925689697 lr:0.00019465077086025368 tokens_per_second_per_gpu:2179.356903961421 
Step 916 | loss:2.3503127098083496 lr:0.00019463806647788506 tokens_per_second_per_gpu:2083.889390189703 
Step 917 | loss:2.452073574066162 lr:0.00019462534744258423 tokens_per_second_per_gpu:2190.3425714822715 
Step 918 | loss:2.4451308250427246 lr:0.0001946126137563204 tokens_per_second_per_gpu:2108.4069312671554 
Step 919 | loss:2.3753855228424072 lr:0.00019459986542106519 tokens_per_second_per_gpu:2082.222053250591 
Step 920 | loss:2.3376150131225586 lr:0.00019458710243879242 tokens_per_second_per_gpu:2190.179583327512 
Step 921 | loss:2.3641035556793213 lr:0.00019457432481147823 tokens_per_second_per_gpu:2168.1286155397943 
Step 922 | loss:2.420177459716797 lr:0.00019456153254110098 tokens_per_second_per_gpu:2133.1086734536207 
Step 923 | loss:2.3626320362091064 lr:0.00019454872562964132 tokens_per_second_per_gpu:2122.7373316876915 
Step 924 | loss:2.4169812202453613 lr:0.00019453590407908213 tokens_per_second_per_gpu:2190.083004894204 
Step 925 | loss:2.4005484580993652 lr:0.0001945230678914086 tokens_per_second_per_gpu:2170.323664741696 
Step 926 | loss:2.3830149173736572 lr:0.0001945102170686082 tokens_per_second_per_gpu:2197.3783129567682 
Step 927 | loss:2.34253191947937 lr:0.00019449735161267064 tokens_per_second_per_gpu:2178.781401245726 
Step 928 | loss:2.4981887340545654 lr:0.0001944844715255879 tokens_per_second_per_gpu:2194.645157465342 
Step 929 | loss:2.392474412918091 lr:0.00019447157680935412 tokens_per_second_per_gpu:2174.2738266057822 
Step 930 | loss:2.4129180908203125 lr:0.00019445866746596596 tokens_per_second_per_gpu:2130.61575244591 
Step 931 | loss:2.421542167663574 lr:0.00019444574349742206 tokens_per_second_per_gpu:2181.088396101243 
Step 932 | loss:2.3685264587402344 lr:0.00019443280490572353 tokens_per_second_per_gpu:2189.3290420562003 
Step 933 | loss:2.4516849517822266 lr:0.00019441985169287368 tokens_per_second_per_gpu:2163.906964664522 
Step 934 | loss:2.3629584312438965 lr:0.000194406883860878 tokens_per_second_per_gpu:2170.763499028624 
Step 935 | loss:2.3935294151306152 lr:0.00019439390141174435 tokens_per_second_per_gpu:2186.7146487999858 
Step 936 | loss:2.3669209480285645 lr:0.00019438090434748285 tokens_per_second_per_gpu:2173.4196752307694 
Step 937 | loss:2.448638916015625 lr:0.0001943678926701058 tokens_per_second_per_gpu:2179.0776256457943 
Step 938 | loss:2.361943244934082 lr:0.00019435486638162786 tokens_per_second_per_gpu:2189.2525086159294 
Step 939 | loss:2.425229549407959 lr:0.00019434182548406587 tokens_per_second_per_gpu:2145.4825639837904 
Step 940 | loss:2.363084077835083 lr:0.00019432876997943897 tokens_per_second_per_gpu:2180.5540971596342 
Step 941 | loss:2.5033693313598633 lr:0.00019431569986976864 tokens_per_second_per_gpu:2142.1143300703907 
Step 942 | loss:2.372757911682129 lr:0.00019430261515707842 tokens_per_second_per_gpu:2157.7247300341223 
Step 943 | loss:2.3237154483795166 lr:0.0001942895158433943 tokens_per_second_per_gpu:2160.6297797597895 
Step 944 | loss:2.3793797492980957 lr:0.0001942764019307445 tokens_per_second_per_gpu:2183.811009996849 
Step 945 | loss:2.423680305480957 lr:0.00019426327342115938 tokens_per_second_per_gpu:2150.2976835453255 
Step 946 | loss:2.4619216918945312 lr:0.00019425013031667168 tokens_per_second_per_gpu:2175.2454287821847 
Step 947 | loss:2.3568644523620605 lr:0.00019423697261931636 tokens_per_second_per_gpu:2101.540495340228 
Step 948 | loss:2.4092860221862793 lr:0.00019422380033113067 tokens_per_second_per_gpu:2137.5458181262748 
Step 949 | loss:2.414386510848999 lr:0.00019421061345415406 tokens_per_second_per_gpu:2164.1327826317256 
Step 950 | loss:2.345411777496338 lr:0.0001941974119904283 tokens_per_second_per_gpu:2188.91718119626 
Step 951 | loss:2.345384120941162 lr:0.00019418419594199735 tokens_per_second_per_gpu:2126.9326856448606 
Step 952 | loss:2.397413969039917 lr:0.0001941709653109075 tokens_per_second_per_gpu:2107.075559285502 
Step 953 | loss:2.4609713554382324 lr:0.00019415772009920726 tokens_per_second_per_gpu:2177.446674228814 
Step 954 | loss:2.304600715637207 lr:0.00019414446030894736 tokens_per_second_per_gpu:2198.545657452395 
Step 955 | loss:2.49410343170166 lr:0.00019413118594218093 tokens_per_second_per_gpu:2178.5589586331857 
Step 956 | loss:2.4201855659484863 lr:0.00019411789700096314 tokens_per_second_per_gpu:2186.5389161630424 
Step 957 | loss:2.368734359741211 lr:0.00019410459348735159 tokens_per_second_per_gpu:2189.3344492245487 
Step 958 | loss:2.4134669303894043 lr:0.0001940912754034061 tokens_per_second_per_gpu:2186.5999620812804 
Step 959 | loss:2.4284932613372803 lr:0.0001940779427511887 tokens_per_second_per_gpu:2177.3128737712204 
Step 960 | loss:2.457386016845703 lr:0.0001940645955327637 tokens_per_second_per_gpu:2148.386898301247 
Step 961 | loss:2.411348342895508 lr:0.0001940512337501977 tokens_per_second_per_gpu:2189.9401478702475 
Step 962 | loss:2.4211063385009766 lr:0.00019403785740555946 tokens_per_second_per_gpu:2178.5084979539765 
Step 963 | loss:2.4469423294067383 lr:0.0001940244665009201 tokens_per_second_per_gpu:2196.2826890179 
Step 964 | loss:2.378143548965454 lr:0.00019401106103835296 tokens_per_second_per_gpu:2121.993209118952 
Step 965 | loss:2.393057346343994 lr:0.0001939976410199336 tokens_per_second_per_gpu:2139.3097320811653 
Step 966 | loss:2.459089756011963 lr:0.00019398420644773984 tokens_per_second_per_gpu:2195.5761102123624 
Step 967 | loss:2.4156317710876465 lr:0.0001939707573238518 tokens_per_second_per_gpu:2173.809865722765 
Step 968 | loss:2.450129747390747 lr:0.00019395729365035184 tokens_per_second_per_gpu:2189.655679326851 
Step 969 | loss:2.384287118911743 lr:0.00019394381542932454 tokens_per_second_per_gpu:2132.8348448266283 
Step 970 | loss:2.3523340225219727 lr:0.00019393032266285676 tokens_per_second_per_gpu:2073.933303752869 
Step 971 | loss:2.373900890350342 lr:0.00019391681535303756 tokens_per_second_per_gpu:2165.760460808511 
Step 972 | loss:2.366698741912842 lr:0.00019390329350195835 tokens_per_second_per_gpu:2108.87517350071 
Step 973 | loss:2.4629273414611816 lr:0.0001938897571117127 tokens_per_second_per_gpu:2195.773156332155 
Step 974 | loss:2.3708176612854004 lr:0.00019387620618439649 tokens_per_second_per_gpu:2182.684758938453 
Step 975 | loss:2.384523868560791 lr:0.0001938626407221078 tokens_per_second_per_gpu:2155.4920208195113 
Step 976 | loss:2.351266384124756 lr:0.00019384906072694702 tokens_per_second_per_gpu:2171.7061141993377 
Step 977 | loss:2.4003164768218994 lr:0.0001938354662010167 tokens_per_second_per_gpu:2192.3222965678124 
Step 978 | loss:2.417304515838623 lr:0.0001938218571464218 tokens_per_second_per_gpu:2106.9140614252688 
Step 979 | loss:2.4167890548706055 lr:0.00019380823356526932 tokens_per_second_per_gpu:2144.753491207166 
Step 980 | loss:2.385308265686035 lr:0.00019379459545966867 tokens_per_second_per_gpu:2174.9637773469644 
Step 981 | loss:2.401050329208374 lr:0.00019378094283173145 tokens_per_second_per_gpu:2139.5862772616088 
Step 982 | loss:2.3701109886169434 lr:0.0001937672756835715 tokens_per_second_per_gpu:2060.03054367744 
Step 983 | loss:2.300848960876465 lr:0.00019375359401730498 tokens_per_second_per_gpu:2159.6579657634775 
Step 984 | loss:2.442880630493164 lr:0.00019373989783505016 tokens_per_second_per_gpu:2170.4167626234403 
Step 985 | loss:2.4510295391082764 lr:0.00019372618713892764 tokens_per_second_per_gpu:2181.935338459931 
Step 986 | loss:2.43648624420166 lr:0.00019371246193106032 tokens_per_second_per_gpu:2181.412682489391 
Step 987 | loss:2.3478329181671143 lr:0.00019369872221357328 tokens_per_second_per_gpu:2192.8089441769093 
Step 988 | loss:2.3952829837799072 lr:0.00019368496798859383 tokens_per_second_per_gpu:2146.8032306427326 
Step 989 | loss:2.3973703384399414 lr:0.00019367119925825158 tokens_per_second_per_gpu:2068.0904812211547 
Step 990 | loss:2.382812023162842 lr:0.00019365741602467835 tokens_per_second_per_gpu:2193.616232779347 
Step 991 | loss:2.3867101669311523 lr:0.00019364361829000818 tokens_per_second_per_gpu:2154.5763051212602 
Step 992 | loss:2.402456283569336 lr:0.00019362980605637747 tokens_per_second_per_gpu:2157.847709849969 
Step 993 | loss:2.4179940223693848 lr:0.00019361597932592473 tokens_per_second_per_gpu:2198.0451704239676 
Step 994 | loss:2.3707194328308105 lr:0.00019360213810079078 tokens_per_second_per_gpu:2193.298885540882 
Step 995 | loss:2.2911229133605957 lr:0.00019358828238311864 tokens_per_second_per_gpu:2164.940654600467 
Step 996 | loss:2.409494161605835 lr:0.00019357441217505368 tokens_per_second_per_gpu:2163.1617860135198 
Step 997 | loss:2.318722724914551 lr:0.0001935605274787434 tokens_per_second_per_gpu:2189.4100722020744 
Step 998 | loss:2.3542654514312744 lr:0.00019354662829633757 tokens_per_second_per_gpu:2085.2814346784803 
Step 999 | loss:2.339630126953125 lr:0.00019353271462998825 tokens_per_second_per_gpu:2157.938229597321 
Step 1000 | loss:2.4501733779907227 lr:0.00019351878648184972 tokens_per_second_per_gpu:2191.4392635443883 
Step 1001 | loss:2.463144302368164 lr:0.00019350484385407846 tokens_per_second_per_gpu:2188.907687222131 
Step 1002 | loss:2.355958938598633 lr:0.00019349088674883324 tokens_per_second_per_gpu:2203.4642251231444 
Step 1003 | loss:2.3366851806640625 lr:0.00019347691516827505 tokens_per_second_per_gpu:2160.9137393853593 
Step 1004 | loss:2.412870407104492 lr:0.00019346292911456711 tokens_per_second_per_gpu:2201.2190642327705 
Step 1005 | loss:2.3492941856384277 lr:0.00019344892858987492 tokens_per_second_per_gpu:2185.014826370511 
Step 1006 | loss:2.4238290786743164 lr:0.00019343491359636623 tokens_per_second_per_gpu:2195.259882031769 
Step 1007 | loss:2.3581480979919434 lr:0.00019342088413621097 tokens_per_second_per_gpu:2150.946903850014 
Step 1008 | loss:2.3739185333251953 lr:0.0001934068402115813 tokens_per_second_per_gpu:2168.5463963068073 
Step 1009 | loss:2.348562717437744 lr:0.00019339278182465175 tokens_per_second_per_gpu:2170.8703802986884 
Step 1010 | loss:2.358938455581665 lr:0.00019337870897759892 tokens_per_second_per_gpu:2192.2983335057465 
Step 1011 | loss:2.2792916297912598 lr:0.00019336462167260173 tokens_per_second_per_gpu:2161.174229183629 
Step 1012 | loss:2.4124112129211426 lr:0.00019335051991184137 tokens_per_second_per_gpu:2175.4888503507364 
Step 1013 | loss:2.4183249473571777 lr:0.00019333640369750122 tokens_per_second_per_gpu:2176.6131812456615 
Step 1014 | loss:2.389315605163574 lr:0.00019332227303176688 tokens_per_second_per_gpu:2118.648100055596 
Step 1015 | loss:2.367327928543091 lr:0.00019330812791682627 tokens_per_second_per_gpu:2035.2551174190808 
Step 1016 | loss:2.366377353668213 lr:0.0001932939683548695 tokens_per_second_per_gpu:2179.6462798205334 
Step 1017 | loss:2.40553617477417 lr:0.00019327979434808888 tokens_per_second_per_gpu:2127.250646729527 
Step 1018 | loss:2.411799669265747 lr:0.000193265605898679 tokens_per_second_per_gpu:2165.370279300217 
Step 1019 | loss:2.4192769527435303 lr:0.00019325140300883667 tokens_per_second_per_gpu:2150.502257695927 
Step 1020 | loss:2.39193058013916 lr:0.00019323718568076093 tokens_per_second_per_gpu:2179.11356546675 
Step 1021 | loss:2.3672657012939453 lr:0.0001932229539166531 tokens_per_second_per_gpu:2107.7494763931395 
Step 1022 | loss:2.417052745819092 lr:0.0001932087077187167 tokens_per_second_per_gpu:2184.6300500236357 
Step 1023 | loss:2.3475730419158936 lr:0.00019319444708915744 tokens_per_second_per_gpu:2144.932375822662 
Step 1024 | loss:2.384521007537842 lr:0.00019318017203018336 tokens_per_second_per_gpu:2051.039633850424 
Step 1025 | loss:2.3323569297790527 lr:0.00019316588254400464 tokens_per_second_per_gpu:2111.2061524185656 
Step 1026 | loss:2.305835247039795 lr:0.0001931515786328338 tokens_per_second_per_gpu:2117.3620873667705 
Step 1027 | loss:2.306460380554199 lr:0.0001931372602988855 tokens_per_second_per_gpu:2142.609967756684 
Step 1028 | loss:2.4091076850891113 lr:0.00019312292754437667 tokens_per_second_per_gpu:2174.5855868957196 
Step 1029 | loss:2.3882265090942383 lr:0.00019310858037152647 tokens_per_second_per_gpu:2192.612712789124 
Step 1030 | loss:2.3498363494873047 lr:0.00019309421878255624 tokens_per_second_per_gpu:2150.3132949434635 
Step 1031 | loss:2.350238800048828 lr:0.0001930798427796897 tokens_per_second_per_gpu:2176.735122425377 
Step 1032 | loss:2.333524227142334 lr:0.00019306545236515263 tokens_per_second_per_gpu:2099.0732752184467 
Step 1033 | loss:2.3209080696105957 lr:0.00019305104754117314 tokens_per_second_per_gpu:2162.4936359493922 
Step 1034 | loss:2.3137872219085693 lr:0.00019303662830998154 tokens_per_second_per_gpu:2169.4774429967224 
Step 1035 | loss:2.3735239505767822 lr:0.0001930221946738104 tokens_per_second_per_gpu:2163.5144034410246 
Step 1036 | loss:2.3818211555480957 lr:0.0001930077466348945 tokens_per_second_per_gpu:2153.913642092374 
Step 1037 | loss:2.364652633666992 lr:0.0001929932841954708 tokens_per_second_per_gpu:2148.733900201304 
Step 1038 | loss:2.46480131149292 lr:0.0001929788073577786 tokens_per_second_per_gpu:2040.1231405931528 
Step 1039 | loss:2.410484790802002 lr:0.00019296431612405933 tokens_per_second_per_gpu:2106.9069372545437 
Step 1040 | loss:2.311727523803711 lr:0.00019294981049655668 tokens_per_second_per_gpu:2167.5570407716696 
Step 1041 | loss:2.3678107261657715 lr:0.00019293529047751661 tokens_per_second_per_gpu:2147.7682990375597 
Step 1042 | loss:2.369706153869629 lr:0.00019292075606918725 tokens_per_second_per_gpu:2172.2196764404007 
Step 1043 | loss:2.4148709774017334 lr:0.00019290620727381894 tokens_per_second_per_gpu:2135.41390600825 
Step 1044 | loss:2.375621795654297 lr:0.00019289164409366438 tokens_per_second_per_gpu:2168.108136179097 
Step 1045 | loss:2.336634635925293 lr:0.00019287706653097833 tokens_per_second_per_gpu:2088.863307002803 
Step 1046 | loss:2.373138427734375 lr:0.00019286247458801786 tokens_per_second_per_gpu:2178.089007766669 
Step 1047 | loss:2.320262908935547 lr:0.0001928478682670423 tokens_per_second_per_gpu:2132.176329407195 
Step 1048 | loss:2.4015448093414307 lr:0.00019283324757031318 tokens_per_second_per_gpu:2188.506794934953 
Step 1049 | loss:2.3564648628234863 lr:0.00019281861250009416 tokens_per_second_per_gpu:2065.2946757159216 
Step 1050 | loss:2.32912015914917 lr:0.00019280396305865126 tokens_per_second_per_gpu:2104.930161322982 
Step 1051 | loss:2.432793617248535 lr:0.00019278929924825268 tokens_per_second_per_gpu:2128.7009576709847 
Step 1052 | loss:2.3447351455688477 lr:0.0001927746210711688 tokens_per_second_per_gpu:2057.7061194156977 
Step 1053 | loss:2.3975932598114014 lr:0.00019275992852967226 tokens_per_second_per_gpu:2188.577455905188 
Step 1054 | loss:2.394284248352051 lr:0.000192745221626038 tokens_per_second_per_gpu:2186.456228604154 
Step 1055 | loss:2.3361053466796875 lr:0.00019273050036254302 tokens_per_second_per_gpu:2166.906736209286 
Step 1056 | loss:2.373741865158081 lr:0.00019271576474146667 tokens_per_second_per_gpu:2154.559281865887 
Step 1057 | loss:2.361999273300171 lr:0.00019270101476509045 tokens_per_second_per_gpu:2121.2692072795026 
Step 1058 | loss:2.409196376800537 lr:0.00019268625043569818 tokens_per_second_per_gpu:2168.019456056062 
Step 1059 | loss:2.289010524749756 lr:0.0001926714717555758 tokens_per_second_per_gpu:2190.2324431287593 
Step 1060 | loss:2.3845033645629883 lr:0.00019265667872701153 tokens_per_second_per_gpu:2180.1809503440986 
Step 1061 | loss:2.4154915809631348 lr:0.00019264187135229578 tokens_per_second_per_gpu:2138.208872592368 
Step 1062 | loss:2.4091076850891113 lr:0.0001926270496337212 tokens_per_second_per_gpu:2183.418200879317 
Step 1063 | loss:2.3804521560668945 lr:0.00019261221357358267 tokens_per_second_per_gpu:2114.8198836611105 
Step 1064 | loss:2.331984043121338 lr:0.00019259736317417723 tokens_per_second_per_gpu:2187.3981111319345 
Step 1065 | loss:2.3631317615509033 lr:0.0001925824984378042 tokens_per_second_per_gpu:2162.87518817903 
Step 1066 | loss:2.392873764038086 lr:0.00019256761936676514 tokens_per_second_per_gpu:2161.1008293793248 
Step 1067 | loss:2.2993946075439453 lr:0.0001925527259633638 tokens_per_second_per_gpu:2181.6734958609827 
Step 1068 | loss:2.356358528137207 lr:0.00019253781822990612 tokens_per_second_per_gpu:2176.679599941706 
Step 1069 | loss:2.4432616233825684 lr:0.00019252289616870024 tokens_per_second_per_gpu:2147.6257858137506 
Step 1070 | loss:2.333987236022949 lr:0.00019250795978205664 tokens_per_second_per_gpu:2126.458899307327 
Step 1071 | loss:2.333195686340332 lr:0.00019249300907228789 tokens_per_second_per_gpu:2157.7024015649376 
Step 1072 | loss:2.366626739501953 lr:0.0001924780440417089 tokens_per_second_per_gpu:2158.0617166631328 
Step 1073 | loss:2.3169307708740234 lr:0.0001924630646926366 tokens_per_second_per_gpu:2164.3041318378896 
Step 1074 | loss:2.371829032897949 lr:0.00019244807102739036 tokens_per_second_per_gpu:2180.095140343681 
Step 1075 | loss:2.330280065536499 lr:0.00019243306304829162 tokens_per_second_per_gpu:2190.421877433279 
Step 1076 | loss:2.3477635383605957 lr:0.00019241804075766412 tokens_per_second_per_gpu:2152.8494996860195 
Step 1077 | loss:2.3476338386535645 lr:0.00019240300415783375 tokens_per_second_per_gpu:2190.4333917793 
Step 1078 | loss:2.3991613388061523 lr:0.0001923879532511287 tokens_per_second_per_gpu:2144.080489777938 
Step 1079 | loss:2.3572874069213867 lr:0.00019237288803987922 tokens_per_second_per_gpu:2164.546505077303 
Step 1080 | loss:2.3737916946411133 lr:0.00019235780852641798 tokens_per_second_per_gpu:2170.6746990926986 
Step 1081 | loss:2.3540310859680176 lr:0.00019234271471307973 tokens_per_second_per_gpu:2146.670499520554 
Step 1082 | loss:2.310771942138672 lr:0.00019232760660220142 tokens_per_second_per_gpu:2169.1922596555014 
Step 1083 | loss:2.34306001663208 lr:0.00019231248419612225 tokens_per_second_per_gpu:2179.5548278139727 
Step 1084 | loss:2.348684310913086 lr:0.00019229734749718374 tokens_per_second_per_gpu:2183.4245529482596 
Step 1085 | loss:2.338388204574585 lr:0.00019228219650772944 tokens_per_second_per_gpu:2186.64531625875 
Step 1086 | loss:2.3890480995178223 lr:0.00019226703123010526 tokens_per_second_per_gpu:2088.24521686708 
Step 1087 | loss:2.3759255409240723 lr:0.0001922518516666592 tokens_per_second_per_gpu:2192.807933179468 
Step 1088 | loss:2.438872814178467 lr:0.00019223665781974153 tokens_per_second_per_gpu:2128.4580971974074 
Step 1089 | loss:2.394169569015503 lr:0.00019222144969170476 tokens_per_second_per_gpu:2181.1271114971914 
Step 1090 | loss:2.3259029388427734 lr:0.0001922062272849036 tokens_per_second_per_gpu:2178.3231969710337 
Step 1091 | loss:2.3597564697265625 lr:0.00019219099060169493 tokens_per_second_per_gpu:2184.916200490765 
Step 1092 | loss:2.292922019958496 lr:0.00019217573964443784 tokens_per_second_per_gpu:2124.504120598298 
Step 1093 | loss:2.3325228691101074 lr:0.0001921604744154937 tokens_per_second_per_gpu:2163.499591921636 
Step 1094 | loss:2.3856101036071777 lr:0.00019214519491722603 tokens_per_second_per_gpu:2181.6674108276557 
Step 1095 | loss:2.4282052516937256 lr:0.00019212990115200057 tokens_per_second_per_gpu:2123.503508744917 
Step 1096 | loss:2.350351333618164 lr:0.0001921145931221853 tokens_per_second_per_gpu:2189.0567555271346 
Step 1097 | loss:2.381725311279297 lr:0.00019209927083015034 tokens_per_second_per_gpu:2187.1385687142033 
Step 1098 | loss:2.330857276916504 lr:0.00019208393427826804 tokens_per_second_per_gpu:2153.612097612734 
Step 1099 | loss:2.265227794647217 lr:0.00019206858346891304 tokens_per_second_per_gpu:2164.7839314800003 
Step 1100 | loss:2.261932611465454 lr:0.00019205321840446213 tokens_per_second_per_gpu:2167.1966109374093 
Step 1101 | loss:2.3734726905822754 lr:0.00019203783908729424 tokens_per_second_per_gpu:2109.42776870155 
Step 1102 | loss:2.2823359966278076 lr:0.00019202244551979063 tokens_per_second_per_gpu:2100.936677076975 
Step 1103 | loss:2.3863940238952637 lr:0.00019200703770433464 tokens_per_second_per_gpu:2166.6245610357164 
Step 1104 | loss:2.4079713821411133 lr:0.00019199161564331196 tokens_per_second_per_gpu:2162.4410648307753 
Step 1105 | loss:2.4377799034118652 lr:0.00019197617933911033 tokens_per_second_per_gpu:2178.3716610121 
Step 1106 | loss:2.2956061363220215 lr:0.00019196072879411983 tokens_per_second_per_gpu:2112.2706030289482 
Step 1107 | loss:2.3833861351013184 lr:0.00019194526401073266 tokens_per_second_per_gpu:2052.696701602069 
Step 1108 | loss:2.347111225128174 lr:0.00019192978499134327 tokens_per_second_per_gpu:2185.2063934665 
Step 1109 | loss:2.2969517707824707 lr:0.00019191429173834827 tokens_per_second_per_gpu:2161.9634859917255 
Step 1110 | loss:2.394926071166992 lr:0.0001918987842541465 tokens_per_second_per_gpu:2147.2075862130923 
Step 1111 | loss:2.305391311645508 lr:0.00019188326254113906 tokens_per_second_per_gpu:2165.605513814456 
Step 1112 | loss:2.3697509765625 lr:0.00019186772660172917 tokens_per_second_per_gpu:2154.8008253145917 
Step 1113 | loss:2.33203387260437 lr:0.0001918521764383222 tokens_per_second_per_gpu:2143.0912694386425 
Step 1114 | loss:2.3320956230163574 lr:0.0001918366120533259 tokens_per_second_per_gpu:2178.936286080663 
Step 1115 | loss:2.3838753700256348 lr:0.0001918210334491501 tokens_per_second_per_gpu:2167.1123848847656 
Step 1116 | loss:2.2620668411254883 lr:0.00019180544062820682 tokens_per_second_per_gpu:2168.3263117405677 
Step 1117 | loss:2.2865524291992188 lr:0.00019178983359291035 tokens_per_second_per_gpu:2185.2598237979532 
Step 1118 | loss:2.382599353790283 lr:0.00019177421234567714 tokens_per_second_per_gpu:2182.9256164368007 
Step 1119 | loss:2.364582061767578 lr:0.00019175857688892583 tokens_per_second_per_gpu:2139.436377112805 
Step 1120 | loss:2.295135736465454 lr:0.00019174292722507735 tokens_per_second_per_gpu:2132.4017113442537 
Step 1121 | loss:2.387995958328247 lr:0.00019172726335655465 tokens_per_second_per_gpu:2167.508996146836 
Step 1122 | loss:2.347795009613037 lr:0.00019171158528578306 tokens_per_second_per_gpu:2113.272583031842 
Step 1123 | loss:2.3159804344177246 lr:0.00019169589301518998 tokens_per_second_per_gpu:2176.294934179052 
Step 1124 | loss:2.3213658332824707 lr:0.00019168018654720515 tokens_per_second_per_gpu:2136.0886369388213 
Step 1125 | loss:2.3399343490600586 lr:0.00019166446588426031 tokens_per_second_per_gpu:2185.160337623657 
Step 1126 | loss:2.340193748474121 lr:0.0001916487310287896 tokens_per_second_per_gpu:2190.5265979614214 
Step 1127 | loss:2.378814458847046 lr:0.00019163298198322925 tokens_per_second_per_gpu:2140.7703177052877 
Step 1128 | loss:2.338366985321045 lr:0.00019161721875001768 tokens_per_second_per_gpu:2123.506089833664 
Step 1129 | loss:2.354379415512085 lr:0.00019160144133159555 tokens_per_second_per_gpu:2187.894693320633 
Step 1130 | loss:2.293640613555908 lr:0.00019158564973040568 tokens_per_second_per_gpu:2148.0890944092375 
Step 1131 | loss:2.340625762939453 lr:0.00019156984394889313 tokens_per_second_per_gpu:2124.4198037553283 
Step 1132 | loss:2.346158504486084 lr:0.0001915540239895051 tokens_per_second_per_gpu:2171.768935460899 
Step 1133 | loss:2.214214563369751 lr:0.00019153818985469102 tokens_per_second_per_gpu:2056.9347546399767 
Step 1134 | loss:2.388829231262207 lr:0.00019152234154690256 tokens_per_second_per_gpu:2170.291544822043 
Step 1135 | loss:2.3785881996154785 lr:0.00019150647906859348 tokens_per_second_per_gpu:2139.936833155189 
Step 1136 | loss:2.3337507247924805 lr:0.0001914906024222198 tokens_per_second_per_gpu:2123.2135001108454 
Step 1137 | loss:2.3280086517333984 lr:0.0001914747116102397 tokens_per_second_per_gpu:2184.266614312762 
Step 1138 | loss:2.3517017364501953 lr:0.00019145880663511358 tokens_per_second_per_gpu:2139.195931827662 
Step 1139 | loss:2.319049835205078 lr:0.00019144288749930408 tokens_per_second_per_gpu:2195.7927385415474 
Step 1140 | loss:2.3695614337921143 lr:0.00019142695420527593 tokens_per_second_per_gpu:2176.541113143263 
Step 1141 | loss:2.4029808044433594 lr:0.00019141100675549612 tokens_per_second_per_gpu:2122.0667034230405 
Step 1142 | loss:2.2992472648620605 lr:0.00019139504515243381 tokens_per_second_per_gpu:2185.0087189616333 
Step 1143 | loss:2.361351251602173 lr:0.00019137906939856034 tokens_per_second_per_gpu:2116.367205190407 
Step 1144 | loss:2.3692755699157715 lr:0.00019136307949634929 tokens_per_second_per_gpu:2156.0290001754497 
Step 1145 | loss:2.2861499786376953 lr:0.00019134707544827637 tokens_per_second_per_gpu:2164.587680436581 
Step 1146 | loss:2.315708875656128 lr:0.00019133105725681953 tokens_per_second_per_gpu:2122.556593431798 
Step 1147 | loss:2.3301613330841064 lr:0.00019131502492445885 tokens_per_second_per_gpu:2180.153833995992 
Step 1148 | loss:2.329780101776123 lr:0.00019129897845367668 tokens_per_second_per_gpu:2192.596443910194 
Step 1149 | loss:2.3268213272094727 lr:0.00019128291784695746 tokens_per_second_per_gpu:2181.6648720509456 
Step 1150 | loss:2.3149547576904297 lr:0.00019126684310678794 tokens_per_second_per_gpu:2137.09749841361 
Step 1151 | loss:2.338533401489258 lr:0.00019125075423565696 tokens_per_second_per_gpu:2176.4965846770133 
Step 1152 | loss:2.3289034366607666 lr:0.00019123465123605557 tokens_per_second_per_gpu:2176.911622128794 
Step 1153 | loss:2.3341221809387207 lr:0.00019121853411047704 tokens_per_second_per_gpu:2063.528930429693 
Step 1154 | loss:2.348439931869507 lr:0.00019120240286141677 tokens_per_second_per_gpu:2135.9222207181106 
Step 1155 | loss:2.3346080780029297 lr:0.00019118625749137244 tokens_per_second_per_gpu:2188.059201901932 
Step 1156 | loss:2.3615245819091797 lr:0.0001911700980028438 tokens_per_second_per_gpu:2127.7970159337747 
Step 1157 | loss:2.345768690109253 lr:0.00019115392439833287 tokens_per_second_per_gpu:2134.679177342102 
Step 1158 | loss:2.4192886352539062 lr:0.00019113773668034384 tokens_per_second_per_gpu:2129.23292181678 
Step 1159 | loss:2.3513383865356445 lr:0.00019112153485138306 tokens_per_second_per_gpu:2179.4224909356476 
Step 1160 | loss:2.306414842605591 lr:0.00019110531891395905 tokens_per_second_per_gpu:2187.168086299915 
Step 1161 | loss:2.309190273284912 lr:0.00019108908887058263 tokens_per_second_per_gpu:2185.0739208153177 
Step 1162 | loss:2.310023069381714 lr:0.00019107284472376663 tokens_per_second_per_gpu:2149.777786523123 
Step 1163 | loss:2.3055596351623535 lr:0.0001910565864760262 tokens_per_second_per_gpu:2191.833125346172 
Step 1164 | loss:2.283623695373535 lr:0.00019104031412987862 tokens_per_second_per_gpu:2182.041054152492 
Step 1165 | loss:2.4004664421081543 lr:0.00019102402768784334 tokens_per_second_per_gpu:2087.67637354031 
Step 1166 | loss:2.312465190887451 lr:0.00019100772715244203 tokens_per_second_per_gpu:2129.7253741149507 
Step 1167 | loss:2.3339569568634033 lr:0.0001909914125261985 tokens_per_second_per_gpu:2170.385120348622 
Step 1168 | loss:2.3165104389190674 lr:0.00019097508381163877 tokens_per_second_per_gpu:2156.0666932269964 
Step 1169 | loss:2.346623420715332 lr:0.0001909587410112911 tokens_per_second_per_gpu:2153.3527005082647 
Step 1170 | loss:2.3510067462921143 lr:0.00019094238412768576 tokens_per_second_per_gpu:2171.5899303703363 
Step 1171 | loss:2.345850944519043 lr:0.00019092601316335537 tokens_per_second_per_gpu:2130.436696113235 
Step 1172 | loss:2.354989767074585 lr:0.00019090962812083463 tokens_per_second_per_gpu:2156.1229163636144 
Step 1173 | loss:2.350562572479248 lr:0.0001908932290026605 tokens_per_second_per_gpu:2151.1382765961175 
Step 1174 | loss:2.3297359943389893 lr:0.00019087681581137208 tokens_per_second_per_gpu:2169.7094763937075 
Step 1175 | loss:2.2837882041931152 lr:0.0001908603885495106 tokens_per_second_per_gpu:2120.2615619904277 
Step 1176 | loss:2.3083157539367676 lr:0.00019084394721961956 tokens_per_second_per_gpu:2177.6168413894234 
Step 1177 | loss:2.314244270324707 lr:0.00019082749182424452 tokens_per_second_per_gpu:2173.2818448146622 
Step 1178 | loss:2.3702268600463867 lr:0.0001908110223659334 tokens_per_second_per_gpu:2192.302771136354 
Step 1179 | loss:2.3666605949401855 lr:0.00019079453884723608 tokens_per_second_per_gpu:2140.461066793592 
Step 1180 | loss:2.282879114151001 lr:0.0001907780412707048 tokens_per_second_per_gpu:2190.0668058074793 
Step 1181 | loss:2.4401676654815674 lr:0.00019076152963889384 tokens_per_second_per_gpu:2133.5441731767696 
Step 1182 | loss:2.3890414237976074 lr:0.00019074500395435977 tokens_per_second_per_gpu:2127.9096306730416 
Step 1183 | loss:2.4070749282836914 lr:0.00019072846421966125 tokens_per_second_per_gpu:2169.0909737475395 
Step 1184 | loss:2.3495843410491943 lr:0.0001907119104373592 tokens_per_second_per_gpu:2181.0402311012267 
Step 1185 | loss:2.3601789474487305 lr:0.00019069534261001656 tokens_per_second_per_gpu:2189.393726709984 
Step 1186 | loss:2.2521872520446777 lr:0.00019067876074019865 tokens_per_second_per_gpu:2118.4758312967233 
Step 1187 | loss:2.309757709503174 lr:0.0001906621648304728 tokens_per_second_per_gpu:2166.502996116695 
Step 1188 | loss:2.351081371307373 lr:0.00019064555488340862 tokens_per_second_per_gpu:2193.0069223028217 
Step 1189 | loss:2.285216808319092 lr:0.0001906289309015778 tokens_per_second_per_gpu:2135.811422412636 
Step 1190 | loss:2.3520092964172363 lr:0.00019061229288755432 tokens_per_second_per_gpu:2170.424129331498 
Step 1191 | loss:2.3018105030059814 lr:0.0001905956408439142 tokens_per_second_per_gpu:2152.690947787481 
Step 1192 | loss:2.3413782119750977 lr:0.00019057897477323568 tokens_per_second_per_gpu:2110.540210261665 
Step 1193 | loss:2.3881044387817383 lr:0.0001905622946780993 tokens_per_second_per_gpu:2188.1956996884337 
Step 1194 | loss:2.328707695007324 lr:0.00019054560056108754 tokens_per_second_per_gpu:2180.9386546011074 
Step 1195 | loss:2.3801283836364746 lr:0.00019052889242478528 tokens_per_second_per_gpu:2181.1343555118538 
Step 1196 | loss:2.3217716217041016 lr:0.00019051217027177934 tokens_per_second_per_gpu:2172.8676963798393 
Step 1197 | loss:2.2806506156921387 lr:0.00019049543410465893 tokens_per_second_per_gpu:2151.4492031129585 
Step 1198 | loss:2.406355857849121 lr:0.00019047868392601532 tokens_per_second_per_gpu:2168.058373930983 
Step 1199 | loss:2.342116355895996 lr:0.0001904619197384419 tokens_per_second_per_gpu:2150.1469040273832 
Step 1200 | loss:2.3251051902770996 lr:0.00019044514154453434 tokens_per_second_per_gpu:2097.4902561495846 
Step 1201 | loss:2.3026793003082275 lr:0.0001904283493468904 tokens_per_second_per_gpu:2124.4336245952086 
Step 1202 | loss:2.3771376609802246 lr:0.0001904115431481101 tokens_per_second_per_gpu:2173.7085299791565 
Step 1203 | loss:2.290872573852539 lr:0.0001903947229507955 tokens_per_second_per_gpu:2155.4002482823457 
Step 1204 | loss:2.279785394668579 lr:0.0001903778887575509 tokens_per_second_per_gpu:2108.1192787565824 
Step 1205 | loss:2.372576951980591 lr:0.0001903610405709828 tokens_per_second_per_gpu:2159.0505327843994 
Step 1206 | loss:2.367631435394287 lr:0.00019034417839369977 tokens_per_second_per_gpu:2112.1021322609245 
Step 1207 | loss:2.326287269592285 lr:0.00019032730222831264 tokens_per_second_per_gpu:2177.8054677705823 
Step 1208 | loss:2.3585174083709717 lr:0.0001903104120774344 tokens_per_second_per_gpu:2099.261494130554 
Step 1209 | loss:2.319444417953491 lr:0.0001902935079436801 tokens_per_second_per_gpu:2169.1237391429413 
Step 1210 | loss:2.3120667934417725 lr:0.00019027658982966706 tokens_per_second_per_gpu:2186.1478669699536 
Step 1211 | loss:2.266756057739258 lr:0.00019025965773801476 tokens_per_second_per_gpu:2118.266594918956 
Step 1212 | loss:2.3367815017700195 lr:0.00019024271167134477 tokens_per_second_per_gpu:2179.0061915890237 
Step 1213 | loss:2.395134449005127 lr:0.0001902257516322809 tokens_per_second_per_gpu:2157.612476822523 
Step 1214 | loss:2.2903525829315186 lr:0.0001902087776234491 tokens_per_second_per_gpu:2192.170970704536 
Step 1215 | loss:2.3814210891723633 lr:0.00019019178964747746 tokens_per_second_per_gpu:2170.1889663523234 
Step 1216 | loss:2.236056327819824 lr:0.00019017478770699624 tokens_per_second_per_gpu:2178.675439031603 
Step 1217 | loss:2.3000240325927734 lr:0.0001901577718046379 tokens_per_second_per_gpu:2043.710457491407 
Step 1218 | loss:2.241187572479248 lr:0.00019014074194303703 tokens_per_second_per_gpu:2189.9145080801113 
Step 1219 | loss:2.328148365020752 lr:0.00019012369812483035 tokens_per_second_per_gpu:2141.1277768756 
Step 1220 | loss:2.337496757507324 lr:0.00019010664035265683 tokens_per_second_per_gpu:2168.6620560939837 
Step 1221 | loss:2.297544479370117 lr:0.00019008956862915752 tokens_per_second_per_gpu:2171.6998616524734 
Step 1222 | loss:2.369750499725342 lr:0.00019007248295697563 tokens_per_second_per_gpu:2152.2928336235964 
Step 1223 | loss:2.272160053253174 lr:0.0001900553833387566 tokens_per_second_per_gpu:2156.159591831284 
Step 1224 | loss:2.2831010818481445 lr:0.00019003826977714798 tokens_per_second_per_gpu:2154.9739730058513 
Step 1225 | loss:2.2877554893493652 lr:0.0001900211422747995 tokens_per_second_per_gpu:2158.0907707543297 
Step 1226 | loss:2.2316012382507324 lr:0.00019000400083436295 tokens_per_second_per_gpu:2181.401665242995 
Step 1227 | loss:2.339142322540283 lr:0.00018998684545849245 tokens_per_second_per_gpu:2186.8580970784774 
Step 1228 | loss:2.3552122116088867 lr:0.00018996967614984413 tokens_per_second_per_gpu:2175.9354487848414 
Step 1229 | loss:2.318556785583496 lr:0.00018995249291107636 tokens_per_second_per_gpu:2177.3465439559523 
Step 1230 | loss:2.2997193336486816 lr:0.00018993529574484966 tokens_per_second_per_gpu:2029.8670088312554 
Step 1231 | loss:2.2629599571228027 lr:0.00018991808465382667 tokens_per_second_per_gpu:2124.469840368363 
Step 1232 | loss:2.3137102127075195 lr:0.0001899008596406722 tokens_per_second_per_gpu:2188.1352922988103 
Step 1233 | loss:2.334181308746338 lr:0.00018988362070805325 tokens_per_second_per_gpu:2196.4791839323443 
Step 1234 | loss:2.3212103843688965 lr:0.0001898663678586389 tokens_per_second_per_gpu:2174.8907629134847 
Step 1235 | loss:2.3037326335906982 lr:0.0001898491010951005 tokens_per_second_per_gpu:2176.0578746401666 
Step 1236 | loss:2.332841396331787 lr:0.0001898318204201114 tokens_per_second_per_gpu:2129.414415706935 
Step 1237 | loss:2.2597556114196777 lr:0.00018981452583634724 tokens_per_second_per_gpu:2192.720427745536 
Step 1238 | loss:2.33093523979187 lr:0.00018979721734648574 tokens_per_second_per_gpu:2130.1217912702773 
Step 1239 | loss:2.2724051475524902 lr:0.00018977989495320684 tokens_per_second_per_gpu:2084.612433954628 
Step 1240 | loss:2.314676284790039 lr:0.0001897625586591925 tokens_per_second_per_gpu:2164.8862182182534 
Step 1241 | loss:2.317472457885742 lr:0.00018974520846712703 tokens_per_second_per_gpu:2181.6685786548856 
Step 1242 | loss:2.2866601943969727 lr:0.00018972784437969672 tokens_per_second_per_gpu:2188.410509795676 
Step 1243 | loss:2.2406773567199707 lr:0.00018971046639959006 tokens_per_second_per_gpu:2174.8766921629026 
Step 1244 | loss:2.2981724739074707 lr:0.00018969307452949773 tokens_per_second_per_gpu:2183.5814314559248 
Step 1245 | loss:2.3025951385498047 lr:0.00018967566877211255 tokens_per_second_per_gpu:2147.0292124706934 
Step 1246 | loss:2.348621129989624 lr:0.00018965824913012944 tokens_per_second_per_gpu:2142.279016597972 
Step 1247 | loss:2.330263137817383 lr:0.00018964081560624553 tokens_per_second_per_gpu:2193.7571740023423 
Step 1248 | loss:2.2847583293914795 lr:0.00018962336820316006 tokens_per_second_per_gpu:2093.859382765229 
Step 1249 | loss:2.286536931991577 lr:0.00018960590692357446 tokens_per_second_per_gpu:2161.8434047884475 
Step 1250 | loss:2.279231548309326 lr:0.00018958843177019227 tokens_per_second_per_gpu:2118.7051656592166 
Step 1251 | loss:2.270181655883789 lr:0.00018957094274571915 tokens_per_second_per_gpu:2185.3823734640464 
Step 1252 | loss:2.344398260116577 lr:0.00018955343985286303 tokens_per_second_per_gpu:2183.8901718552925 
Step 1253 | loss:2.4061219692230225 lr:0.0001895359230943338 tokens_per_second_per_gpu:2145.337911513017 
Step 1254 | loss:2.2921199798583984 lr:0.00018951839247284368 tokens_per_second_per_gpu:2179.055506105602 
Step 1255 | loss:2.2942042350769043 lr:0.00018950084799110694 tokens_per_second_per_gpu:2128.2694686607906 
Step 1256 | loss:2.3667209148406982 lr:0.00018948328965184003 tokens_per_second_per_gpu:2162.3076523669606 
Step 1257 | loss:2.244567394256592 lr:0.0001894657174577615 tokens_per_second_per_gpu:2168.5402567112897 
Step 1258 | loss:2.2917864322662354 lr:0.00018944813141159208 tokens_per_second_per_gpu:2182.8992783919502 
Step 1259 | loss:2.334568500518799 lr:0.00018943053151605467 tokens_per_second_per_gpu:2165.188049467775 
Step 1260 | loss:2.2896385192871094 lr:0.00018941291777387425 tokens_per_second_per_gpu:2136.0937369740163 
Step 1261 | loss:2.323037624359131 lr:0.00018939529018777797 tokens_per_second_per_gpu:2185.265134840781 
Step 1262 | loss:2.2875289916992188 lr:0.00018937764876049515 tokens_per_second_per_gpu:2163.5040095917375 
Step 1263 | loss:2.3398330211639404 lr:0.00018935999349475725 tokens_per_second_per_gpu:2184.561118842412 
Step 1264 | loss:2.274369716644287 lr:0.00018934232439329787 tokens_per_second_per_gpu:2142.3561282565474 
Step 1265 | loss:2.2998428344726562 lr:0.00018932464145885266 tokens_per_second_per_gpu:2152.244313275701 
Step 1266 | loss:2.324429988861084 lr:0.00018930694469415958 tokens_per_second_per_gpu:2160.3184246068577 
Step 1267 | loss:2.327686309814453 lr:0.00018928923410195859 tokens_per_second_per_gpu:2140.0727011829003 
Step 1268 | loss:2.416177749633789 lr:0.00018927150968499188 tokens_per_second_per_gpu:2151.3304703161625 
Step 1269 | loss:2.3334903717041016 lr:0.0001892537714460037 tokens_per_second_per_gpu:2154.7821844474524 
Step 1270 | loss:2.3267853260040283 lr:0.0001892360193877405 tokens_per_second_per_gpu:2155.1486519108234 
Step 1271 | loss:2.270273208618164 lr:0.00018921825351295087 tokens_per_second_per_gpu:2133.323755155083 
Step 1272 | loss:2.274730920791626 lr:0.00018920047382438553 tokens_per_second_per_gpu:2078.5755776224314 
Step 1273 | loss:2.359243869781494 lr:0.00018918268032479732 tokens_per_second_per_gpu:2172.2506776022337 
Step 1274 | loss:2.3478283882141113 lr:0.0001891648730169412 tokens_per_second_per_gpu:2174.815863462374 
Step 1275 | loss:2.3581838607788086 lr:0.00018914705190357434 tokens_per_second_per_gpu:2189.8360949807043 
Step 1276 | loss:2.350937843322754 lr:0.00018912921698745598 tokens_per_second_per_gpu:2144.4417191798943 
Step 1277 | loss:2.2870092391967773 lr:0.00018911136827134755 tokens_per_second_per_gpu:2086.1045227627023 
Step 1278 | loss:2.3528265953063965 lr:0.00018909350575801258 tokens_per_second_per_gpu:2194.921279914274 
Step 1279 | loss:2.2886404991149902 lr:0.00018907562945021672 tokens_per_second_per_gpu:2177.8012861293655 
Step 1280 | loss:2.261845111846924 lr:0.0001890577393507278 tokens_per_second_per_gpu:2149.2191571513536 
Step 1281 | loss:2.3355045318603516 lr:0.0001890398354623158 tokens_per_second_per_gpu:2156.2213069988384 
Step 1282 | loss:2.271334648132324 lr:0.00018902191778775272 tokens_per_second_per_gpu:2140.9580844943316 
Step 1283 | loss:2.3278932571411133 lr:0.00018900398632981283 tokens_per_second_per_gpu:2171.0084226160657 
Step 1284 | loss:2.3437633514404297 lr:0.00018898604109127248 tokens_per_second_per_gpu:2146.9979896875825 
Step 1285 | loss:2.340860366821289 lr:0.00018896808207491018 tokens_per_second_per_gpu:2184.9304430063708 
Step 1286 | loss:2.30135440826416 lr:0.00018895010928350646 tokens_per_second_per_gpu:2161.03542659462 
Step 1287 | loss:2.3320364952087402 lr:0.00018893212271984416 tokens_per_second_per_gpu:2109.8693363918524 
Step 1288 | loss:2.2683091163635254 lr:0.00018891412238670815 tokens_per_second_per_gpu:2089.6963397596137 
Step 1289 | loss:2.3156139850616455 lr:0.00018889610828688543 tokens_per_second_per_gpu:2157.980315546425 
Step 1290 | loss:2.3388094902038574 lr:0.00018887808042316508 tokens_per_second_per_gpu:2134.946404752138 
Step 1291 | loss:2.363661766052246 lr:0.0001888600387983385 tokens_per_second_per_gpu:2191.2146183348605 
Step 1292 | loss:2.265009880065918 lr:0.000188841983415199 tokens_per_second_per_gpu:2188.6146457191194 
Step 1293 | loss:2.298201084136963 lr:0.00018882391427654213 tokens_per_second_per_gpu:2178.509707022719 
Step 1294 | loss:2.314014434814453 lr:0.00018880583138516563 tokens_per_second_per_gpu:2188.383328600918 
Step 1295 | loss:2.292781352996826 lr:0.00018878773474386923 tokens_per_second_per_gpu:2155.6259277311815 
Step 1296 | loss:2.320279836654663 lr:0.00018876962435545488 tokens_per_second_per_gpu:2161.0046233048665 
Step 1297 | loss:2.21466064453125 lr:0.0001887515002227266 tokens_per_second_per_gpu:2172.2853302206813 
Step 1298 | loss:2.334244966506958 lr:0.0001887333623484906 tokens_per_second_per_gpu:2173.4408688169287 
Step 1299 | loss:2.3148183822631836 lr:0.0001887152107355552 tokens_per_second_per_gpu:2193.907574211364 
Step 1300 | loss:2.3333821296691895 lr:0.00018869704538673084 tokens_per_second_per_gpu:2165.000645030299 
Step 1301 | loss:2.2424702644348145 lr:0.0001886788663048301 tokens_per_second_per_gpu:2137.5391944949683 
Step 1302 | loss:2.230755567550659 lr:0.00018866067349266761 tokens_per_second_per_gpu:2180.8703792101373 
Step 1303 | loss:2.2860302925109863 lr:0.00018864246695306022 tokens_per_second_per_gpu:2076.306711241424 
Step 1304 | loss:2.271125555038452 lr:0.00018862424668882687 tokens_per_second_per_gpu:2187.6805673515328 
Step 1305 | loss:2.2700889110565186 lr:0.00018860601270278863 tokens_per_second_per_gpu:2186.3864525889635 
Step 1306 | loss:2.294473648071289 lr:0.00018858776499776868 tokens_per_second_per_gpu:2159.5461061173423 
Step 1307 | loss:2.2562499046325684 lr:0.00018856950357659232 tokens_per_second_per_gpu:2183.5628068385763 
Step 1308 | loss:2.2687668800354004 lr:0.00018855122844208707 tokens_per_second_per_gpu:2080.2335908679433 
Step 1309 | loss:2.3469204902648926 lr:0.0001885329395970824 tokens_per_second_per_gpu:2183.6889065693363 
Step 1310 | loss:2.2836897373199463 lr:0.00018851463704441004 tokens_per_second_per_gpu:2172.5864367023087 
Step 1311 | loss:2.2151379585266113 lr:0.0001884963207869038 tokens_per_second_per_gpu:2171.47520001393 
Step 1312 | loss:2.31703519821167 lr:0.00018847799082739956 tokens_per_second_per_gpu:2155.979828053261 
Step 1313 | loss:2.3122949600219727 lr:0.00018845964716873544 tokens_per_second_per_gpu:2151.0757086032586 
Step 1314 | loss:2.2967143058776855 lr:0.00018844128981375158 tokens_per_second_per_gpu:2151.7195013808146 
Step 1315 | loss:2.2415003776550293 lr:0.00018842291876529027 tokens_per_second_per_gpu:2184.1903137919835 
Step 1316 | loss:2.2830018997192383 lr:0.0001884045340261959 tokens_per_second_per_gpu:2187.880861274804 
Step 1317 | loss:2.255833148956299 lr:0.00018838613559931506 tokens_per_second_per_gpu:2188.2400819283525 
Step 1318 | loss:2.352630615234375 lr:0.00018836772348749633 tokens_per_second_per_gpu:2117.6377940127604 
Step 1319 | loss:2.2420997619628906 lr:0.00018834929769359054 tokens_per_second_per_gpu:2165.9750995079444 
Step 1320 | loss:2.302093505859375 lr:0.0001883308582204506 tokens_per_second_per_gpu:2158.9194982828008 
Step 1321 | loss:2.3252172470092773 lr:0.0001883124050709314 tokens_per_second_per_gpu:2178.2250860552826 
Step 1322 | loss:2.331840753555298 lr:0.00018829393824789024 tokens_per_second_per_gpu:2190.1017869744983 
Step 1323 | loss:2.306910991668701 lr:0.00018827545775418618 tokens_per_second_per_gpu:2139.1129117942355 
Step 1324 | loss:2.2562196254730225 lr:0.0001882569635926807 tokens_per_second_per_gpu:2188.0831322396302 
Step 1325 | loss:2.3542466163635254 lr:0.00018823845576623725 tokens_per_second_per_gpu:2167.0090167512953 
Step 1326 | loss:2.310772180557251 lr:0.00018821993427772137 tokens_per_second_per_gpu:2131.283436351934 
Step 1327 | loss:2.29258394241333 lr:0.00018820139913000082 tokens_per_second_per_gpu:2172.685162094495 
Step 1328 | loss:2.271780014038086 lr:0.00018818285032594538 tokens_per_second_per_gpu:2154.804187028883 
Step 1329 | loss:2.355557918548584 lr:0.00018816428786842704 tokens_per_second_per_gpu:2165.625997681128 
Step 1330 | loss:2.3392815589904785 lr:0.0001881457117603198 tokens_per_second_per_gpu:2183.377018921797 
Step 1331 | loss:2.267685890197754 lr:0.00018812712200449986 tokens_per_second_per_gpu:2186.7313154550716 
Step 1332 | loss:2.3454461097717285 lr:0.00018810851860384545 tokens_per_second_per_gpu:2133.2865900969623 
Step 1333 | loss:2.245549201965332 lr:0.00018808990156123697 tokens_per_second_per_gpu:2189.2180025148627 
Step 1334 | loss:2.2590887546539307 lr:0.00018807127087955695 tokens_per_second_per_gpu:2104.480005090606 
Step 1335 | loss:2.2238264083862305 lr:0.00018805262656169 tokens_per_second_per_gpu:2185.061479825079 
Step 1336 | loss:2.296459674835205 lr:0.00018803396861052284 tokens_per_second_per_gpu:2189.499053046391 
Step 1337 | loss:2.377279043197632 lr:0.00018801529702894425 tokens_per_second_per_gpu:2144.9907900669727 
Step 1338 | loss:2.3088700771331787 lr:0.00018799661181984525 tokens_per_second_per_gpu:2182.931634216367 
Step 1339 | loss:2.283628225326538 lr:0.00018797791298611881 tokens_per_second_per_gpu:2127.067066067727 
Step 1340 | loss:2.2423758506774902 lr:0.0001879592005306602 tokens_per_second_per_gpu:2136.225076413553 
Step 1341 | loss:2.348066806793213 lr:0.00018794047445636666 tokens_per_second_per_gpu:2187.4839864591254 
Step 1342 | loss:2.3247251510620117 lr:0.0001879217347661375 tokens_per_second_per_gpu:2165.9810402882367 
Step 1343 | loss:2.3500022888183594 lr:0.0001879029814628743 tokens_per_second_per_gpu:2189.4150206007157 
Step 1344 | loss:2.341066598892212 lr:0.00018788421454948056 tokens_per_second_per_gpu:2190.8355288576668 
Step 1345 | loss:2.294977903366089 lr:0.0001878654340288621 tokens_per_second_per_gpu:2184.484161397372 
Step 1346 | loss:2.3083977699279785 lr:0.00018784663990392667 tokens_per_second_per_gpu:2119.507418462219 
Step 1347 | loss:2.245540142059326 lr:0.0001878278321775842 tokens_per_second_per_gpu:2148.259995824272 
Step 1348 | loss:2.323643445968628 lr:0.0001878090108527467 tokens_per_second_per_gpu:2189.3654390713023 
Step 1349 | loss:2.280677318572998 lr:0.0001877901759323283 tokens_per_second_per_gpu:2133.3998327674 
Step 1350 | loss:2.2298173904418945 lr:0.00018777132741924524 tokens_per_second_per_gpu:2145.240958051463 
Step 1351 | loss:2.3010430335998535 lr:0.00018775246531641587 tokens_per_second_per_gpu:2189.213901620276 
Step 1352 | loss:2.26882004737854 lr:0.00018773358962676065 tokens_per_second_per_gpu:2165.426398295242 
Step 1353 | loss:2.317261219024658 lr:0.00018771470035320207 tokens_per_second_per_gpu:2138.975557638396 
Step 1354 | loss:2.2918410301208496 lr:0.00018769579749866483 tokens_per_second_per_gpu:2179.6223308123062 
Step 1355 | loss:2.296430826187134 lr:0.00018767688106607566 tokens_per_second_per_gpu:2180.6309632443676 
Step 1356 | loss:2.288435459136963 lr:0.00018765795105836342 tokens_per_second_per_gpu:2112.1498926902555 
Step 1357 | loss:2.2787725925445557 lr:0.0001876390074784591 tokens_per_second_per_gpu:2123.879172693361 
Step 1358 | loss:2.2318806648254395 lr:0.00018762005032929566 tokens_per_second_per_gpu:2104.7072140041723 
Step 1359 | loss:2.306105136871338 lr:0.0001876010796138084 tokens_per_second_per_gpu:2191.3566778523345 
Step 1360 | loss:2.3184962272644043 lr:0.00018758209533493444 tokens_per_second_per_gpu:2177.754940883089 
Step 1361 | loss:2.310356855392456 lr:0.00018756309749561327 tokens_per_second_per_gpu:2141.111227283166 
Step 1362 | loss:2.2639565467834473 lr:0.00018754408609878627 tokens_per_second_per_gpu:2180.014386942344 
Step 1363 | loss:2.275104522705078 lr:0.000187525061147397 tokens_per_second_per_gpu:2142.4871174126542 
Step 1364 | loss:2.3201630115509033 lr:0.00018750602264439113 tokens_per_second_per_gpu:2164.549576607462 
Step 1365 | loss:2.3073172569274902 lr:0.00018748697059271641 tokens_per_second_per_gpu:2192.9836539790144 
Step 1366 | loss:2.249579429626465 lr:0.00018746790499532274 tokens_per_second_per_gpu:2152.093207291756 
Step 1367 | loss:2.228381633758545 lr:0.000187448825855162 tokens_per_second_per_gpu:2125.7608213861467 
Step 1368 | loss:2.244264602661133 lr:0.0001874297331751883 tokens_per_second_per_gpu:2165.1239320511395 
Step 1369 | loss:2.3109095096588135 lr:0.00018741062695835773 tokens_per_second_per_gpu:2189.0582561827705 
Step 1370 | loss:2.3187966346740723 lr:0.00018739150720762857 tokens_per_second_per_gpu:2136.566642468281 
Step 1371 | loss:2.248108386993408 lr:0.00018737237392596115 tokens_per_second_per_gpu:2177.0721893539007 
Step 1372 | loss:2.320854663848877 lr:0.00018735322711631785 tokens_per_second_per_gpu:2181.859490516478 
Step 1373 | loss:2.263753890991211 lr:0.00018733406678166325 tokens_per_second_per_gpu:2187.583121672542 
Step 1374 | loss:2.284998893737793 lr:0.00018731489292496395 tokens_per_second_per_gpu:2167.6731255536056 
Step 1375 | loss:2.262514591217041 lr:0.0001872957055491887 tokens_per_second_per_gpu:2111.280221817234 
Step 1376 | loss:2.303128480911255 lr:0.00018727650465730827 tokens_per_second_per_gpu:2124.976862826473 
Step 1377 | loss:2.3128840923309326 lr:0.00018725729025229553 tokens_per_second_per_gpu:2153.2256114456754 
Step 1378 | loss:2.2884602546691895 lr:0.00018723806233712548 tokens_per_second_per_gpu:2156.676974006798 
Step 1379 | loss:2.3212947845458984 lr:0.0001872188209147753 tokens_per_second_per_gpu:2143.3608548152674 
Step 1380 | loss:2.287071704864502 lr:0.00018719956598822402 tokens_per_second_per_gpu:2125.0325183507207 
Step 1381 | loss:2.2854371070861816 lr:0.00018718029756045298 tokens_per_second_per_gpu:2059.3819761750838 
Step 1382 | loss:2.2610058784484863 lr:0.00018716101563444557 tokens_per_second_per_gpu:2152.5743365546864 
Step 1383 | loss:2.2897884845733643 lr:0.0001871417202131872 tokens_per_second_per_gpu:2100.008359439211 
Step 1384 | loss:2.3050403594970703 lr:0.00018712241129966532 tokens_per_second_per_gpu:2130.0542690913667 
Step 1385 | loss:2.314079523086548 lr:0.0001871030888968697 tokens_per_second_per_gpu:2099.8045052805724 
Step 1386 | loss:2.3167953491210938 lr:0.00018708375300779197 tokens_per_second_per_gpu:2146.2230824074545 
Step 1387 | loss:2.300175189971924 lr:0.00018706440363542591 tokens_per_second_per_gpu:2144.3927232706797 
Step 1388 | loss:2.2719054222106934 lr:0.00018704504078276749 tokens_per_second_per_gpu:2161.8091869898067 
Step 1389 | loss:2.319889545440674 lr:0.0001870256644528146 tokens_per_second_per_gpu:2104.5268089913097 
Step 1390 | loss:2.27384090423584 lr:0.00018700627464856738 tokens_per_second_per_gpu:2162.705558640033 
Step 1391 | loss:2.32096004486084 lr:0.0001869868713730279 tokens_per_second_per_gpu:2121.189723773784 
Step 1392 | loss:2.327531337738037 lr:0.00018696745462920046 tokens_per_second_per_gpu:2134.024648306885 
Step 1393 | loss:2.2969894409179688 lr:0.00018694802442009132 tokens_per_second_per_gpu:2160.0674097623423 
Step 1394 | loss:2.318420886993408 lr:0.0001869285807487089 tokens_per_second_per_gpu:2186.4321550823993 
Step 1395 | loss:2.2919511795043945 lr:0.00018690912361806375 tokens_per_second_per_gpu:2152.9037423624186 
Step 1396 | loss:2.2976489067077637 lr:0.00018688965303116837 tokens_per_second_per_gpu:2180.127173855544 
Step 1397 | loss:2.3347554206848145 lr:0.00018687016899103745 tokens_per_second_per_gpu:2170.490006962319 
Step 1398 | loss:2.269958972930908 lr:0.0001868506715006877 tokens_per_second_per_gpu:2117.5535189277507 
Step 1399 | loss:2.3362112045288086 lr:0.00018683116056313797 tokens_per_second_per_gpu:2158.588608873911 
Step 1400 | loss:2.2818069458007812 lr:0.00018681163618140917 tokens_per_second_per_gpu:2184.521005387137 
Step 1401 | loss:2.3270623683929443 lr:0.00018679209835852426 tokens_per_second_per_gpu:2146.7563566894696 
Step 1402 | loss:2.3072946071624756 lr:0.0001867725470975083 tokens_per_second_per_gpu:2182.146061494634 
Step 1403 | loss:2.333322763442993 lr:0.00018675298240138845 tokens_per_second_per_gpu:2187.3491377570663 
Step 1404 | loss:2.2932302951812744 lr:0.00018673340427319396 tokens_per_second_per_gpu:2149.961083623705 
Step 1405 | loss:2.228485584259033 lr:0.00018671381271595608 tokens_per_second_per_gpu:2138.439639697761 
Step 1406 | loss:2.267277479171753 lr:0.00018669420773270828 tokens_per_second_per_gpu:2190.0348470807016 
Step 1407 | loss:2.295076370239258 lr:0.00018667458932648595 tokens_per_second_per_gpu:2165.613971796551 
Step 1408 | loss:2.3251423835754395 lr:0.00018665495750032663 tokens_per_second_per_gpu:2030.7542452990065 
Step 1409 | loss:2.307497501373291 lr:0.00018663531225727003 tokens_per_second_per_gpu:2181.2291702996436 
Step 1410 | loss:2.249936103820801 lr:0.00018661565360035773 tokens_per_second_per_gpu:2132.0595502130477 
Step 1411 | loss:2.268211841583252 lr:0.0001865959815326336 tokens_per_second_per_gpu:2175.646591258779 
Step 1412 | loss:2.302328109741211 lr:0.0001865762960571434 tokens_per_second_per_gpu:2172.750309531115 
Step 1413 | loss:2.2744264602661133 lr:0.00018655659717693517 tokens_per_second_per_gpu:2170.2032717646657 
Step 1414 | loss:2.2674527168273926 lr:0.00018653688489505882 tokens_per_second_per_gpu:2193.802374737502 
Step 1415 | loss:2.217341423034668 lr:0.00018651715921456647 tokens_per_second_per_gpu:2188.1316732051664 
Step 1416 | loss:2.326134204864502 lr:0.00018649742013851226 tokens_per_second_per_gpu:2191.0964523234124 
Step 1417 | loss:2.2651195526123047 lr:0.00018647766766995242 tokens_per_second_per_gpu:2178.665028985668 
Step 1418 | loss:2.3049707412719727 lr:0.00018645790181194522 tokens_per_second_per_gpu:2182.310239639318 
Step 1419 | loss:2.301699161529541 lr:0.0001864381225675511 tokens_per_second_per_gpu:2178.9653471514184 
Step 1420 | loss:2.232600212097168 lr:0.00018641832993983247 tokens_per_second_per_gpu:2096.585937960054 
Step 1421 | loss:2.3087666034698486 lr:0.0001863985239318538 tokens_per_second_per_gpu:2168.536946753324 
Step 1422 | loss:2.2700793743133545 lr:0.00018637870454668175 tokens_per_second_per_gpu:2162.674077219803 
Step 1423 | loss:2.30104398727417 lr:0.00018635887178738495 tokens_per_second_per_gpu:2199.9500322190033 
Step 1424 | loss:2.3125381469726562 lr:0.00018633902565703413 tokens_per_second_per_gpu:2191.5714075864853 
Step 1425 | loss:2.2909107208251953 lr:0.00018631916615870214 tokens_per_second_per_gpu:2111.0615637368546 
Step 1426 | loss:2.302581548690796 lr:0.00018629929329546375 tokens_per_second_per_gpu:2176.8483077363403 
Step 1427 | loss:2.267535448074341 lr:0.000186279407070396 tokens_per_second_per_gpu:2176.4835729258066 
Step 1428 | loss:2.2224833965301514 lr:0.00018625950748657783 tokens_per_second_per_gpu:2145.8698275655297 
Step 1429 | loss:2.271977424621582 lr:0.00018623959454709037 tokens_per_second_per_gpu:2184.892666119355 
Step 1430 | loss:2.250114679336548 lr:0.00018621966825501675 tokens_per_second_per_gpu:2157.8624989735404 
Step 1431 | loss:2.3302578926086426 lr:0.00018619972861344216 tokens_per_second_per_gpu:2160.4402136353383 
Step 1432 | loss:2.263380527496338 lr:0.00018617977562545389 tokens_per_second_per_gpu:2172.809587261096 
Step 1433 | loss:2.2908847332000732 lr:0.0001861598092941413 tokens_per_second_per_gpu:2177.1988439417296 
Step 1434 | loss:2.2421607971191406 lr:0.0001861398296225958 tokens_per_second_per_gpu:2188.436683134573 
Step 1435 | loss:2.2922420501708984 lr:0.00018611983661391082 tokens_per_second_per_gpu:2161.4131373088217 
Step 1436 | loss:2.225038766860962 lr:0.000186099830271182 tokens_per_second_per_gpu:2195.793733496246 
Step 1437 | loss:2.3361198902130127 lr:0.0001860798105975069 tokens_per_second_per_gpu:2182.9857076698686 
Step 1438 | loss:2.25828218460083 lr:0.00018605977759598514 tokens_per_second_per_gpu:2184.141925971191 
Step 1439 | loss:2.2467763423919678 lr:0.00018603973126971854 tokens_per_second_per_gpu:2184.970460698629 
Step 1440 | loss:2.301107406616211 lr:0.00018601967162181081 tokens_per_second_per_gpu:2137.8466901797374 
Step 1441 | loss:2.3087048530578613 lr:0.00018599959865536788 tokens_per_second_per_gpu:2167.7247089085845 
Step 1442 | loss:2.2283384799957275 lr:0.00018597951237349768 tokens_per_second_per_gpu:2153.867785560362 
Step 1443 | loss:2.248988151550293 lr:0.00018595941277931016 tokens_per_second_per_gpu:2198.7565224205478 
Step 1444 | loss:2.3048014640808105 lr:0.00018593929987591735 tokens_per_second_per_gpu:2160.9232153575163 
Step 1445 | loss:2.3253636360168457 lr:0.00018591917366643339 tokens_per_second_per_gpu:2161.125751291286 
Step 1446 | loss:2.3065648078918457 lr:0.00018589903415397444 tokens_per_second_per_gpu:2173.6756527965867 
Step 1447 | loss:2.256298542022705 lr:0.00018587888134165872 tokens_per_second_per_gpu:2160.6631172571706 
Step 1448 | loss:2.262765884399414 lr:0.00018585871523260652 tokens_per_second_per_gpu:2101.8561448800565 
Step 1449 | loss:2.2755532264709473 lr:0.00018583853582994014 tokens_per_second_per_gpu:2156.6105316551166 
Step 1450 | loss:2.301656484603882 lr:0.00018581834313678407 tokens_per_second_per_gpu:2187.00604462113 
Step 1451 | loss:2.2709407806396484 lr:0.0001857981371562647 tokens_per_second_per_gpu:2190.0026133587053 
Step 1452 | loss:2.3078646659851074 lr:0.0001857779178915106 tokens_per_second_per_gpu:2130.6097480787407 
Step 1453 | loss:2.3257932662963867 lr:0.00018575768534565232 tokens_per_second_per_gpu:2189.3665027780053 
Step 1454 | loss:2.2507009506225586 lr:0.00018573743952182245 tokens_per_second_per_gpu:2194.3026434978324 
Step 1455 | loss:2.2436113357543945 lr:0.00018571718042315576 tokens_per_second_per_gpu:2151.274151614273 
Step 1456 | loss:2.3276913166046143 lr:0.00018569690805278892 tokens_per_second_per_gpu:2169.863865274751 
Step 1457 | loss:2.344428539276123 lr:0.00018567662241386073 tokens_per_second_per_gpu:2194.5501421062295 
Step 1458 | loss:2.2501559257507324 lr:0.0001856563235095121 tokens_per_second_per_gpu:2169.0773694990667 
Step 1459 | loss:2.3320212364196777 lr:0.0001856360113428859 tokens_per_second_per_gpu:2167.4243534366124 
Step 1460 | loss:2.265493392944336 lr:0.00018561568591712706 tokens_per_second_per_gpu:2177.1139104327485 
Step 1461 | loss:2.311140298843384 lr:0.00018559534723538263 tokens_per_second_per_gpu:2104.5009498543227 
Step 1462 | loss:2.2481772899627686 lr:0.0001855749953008017 tokens_per_second_per_gpu:2157.679731534752 
Step 1463 | loss:2.201580762863159 lr:0.0001855546301165353 tokens_per_second_per_gpu:2160.6212513756323 
Step 1464 | loss:2.2876462936401367 lr:0.00018553425168573665 tokens_per_second_per_gpu:2179.387133198149 
Step 1465 | loss:2.2760064601898193 lr:0.000185513860011561 tokens_per_second_per_gpu:2180.424257567026 
Step 1466 | loss:2.267073154449463 lr:0.00018549345509716558 tokens_per_second_per_gpu:2146.0133168708467 
Step 1467 | loss:2.323315382003784 lr:0.0001854730369457097 tokens_per_second_per_gpu:2148.0027058734154 
Step 1468 | loss:2.276040554046631 lr:0.00018545260556035475 tokens_per_second_per_gpu:2164.4755678904307 
Step 1469 | loss:2.323767900466919 lr:0.00018543216094426412 tokens_per_second_per_gpu:2144.283378931462 
Step 1470 | loss:2.281369686126709 lr:0.00018541170310060328 tokens_per_second_per_gpu:2158.3829796430027 
Step 1471 | loss:2.2561028003692627 lr:0.0001853912320325398 tokens_per_second_per_gpu:2169.9363928660264 
Step 1472 | loss:2.249035358428955 lr:0.0001853707477432432 tokens_per_second_per_gpu:2190.7059788687648 
Step 1473 | loss:2.2229249477386475 lr:0.00018535025023588508 tokens_per_second_per_gpu:2190.082293343577 
Step 1474 | loss:2.2223434448242188 lr:0.00018532973951363907 tokens_per_second_per_gpu:2178.4061785638437 
Step 1475 | loss:2.1618435382843018 lr:0.00018530921557968096 tokens_per_second_per_gpu:2100.198723564836 
Step 1476 | loss:2.28485107421875 lr:0.00018528867843718843 tokens_per_second_per_gpu:2182.6691434770582 
Step 1477 | loss:2.198310136795044 lr:0.00018526812808934126 tokens_per_second_per_gpu:2165.4864352627196 
Step 1478 | loss:2.2477879524230957 lr:0.00018524756453932133 tokens_per_second_per_gpu:2190.075956028139 
Step 1479 | loss:2.27498722076416 lr:0.00018522698779031247 tokens_per_second_per_gpu:2176.6828329658197 
Step 1480 | loss:2.293515920639038 lr:0.00018520639784550067 tokens_per_second_per_gpu:2169.778973059917 
Step 1481 | loss:2.211063861846924 lr:0.00018518579470807385 tokens_per_second_per_gpu:2187.9924152543463 
Step 1482 | loss:2.2337818145751953 lr:0.00018516517838122203 tokens_per_second_per_gpu:2178.7101453742457 
Step 1483 | loss:2.1964712142944336 lr:0.0001851445488681373 tokens_per_second_per_gpu:2146.771315754605 
Step 1484 | loss:2.3022537231445312 lr:0.00018512390617201366 tokens_per_second_per_gpu:2120.2486679947924 
Step 1485 | loss:2.271087169647217 lr:0.00018510325029604734 tokens_per_second_per_gpu:2189.80803231257 
Step 1486 | loss:2.3147623538970947 lr:0.00018508258124343648 tokens_per_second_per_gpu:2128.3326816889225 
Step 1487 | loss:2.2997641563415527 lr:0.00018506189901738127 tokens_per_second_per_gpu:2106.358104128657 
Step 1488 | loss:2.26713228225708 lr:0.000185041203621084 tokens_per_second_per_gpu:2143.8207958227986 
Step 1489 | loss:2.230224370956421 lr:0.00018502049505774893 tokens_per_second_per_gpu:2164.0573641261108 
Step 1490 | loss:2.2920889854431152 lr:0.00018499977333058247 tokens_per_second_per_gpu:2149.9759169939293 
Step 1491 | loss:2.299694538116455 lr:0.0001849790384427929 tokens_per_second_per_gpu:2134.1905690900203 
Step 1492 | loss:2.2770509719848633 lr:0.0001849582903975907 tokens_per_second_per_gpu:2116.2966590104356 
Step 1493 | loss:2.2887654304504395 lr:0.0001849375291981883 tokens_per_second_per_gpu:2160.6988207163436 
Step 1494 | loss:2.3055737018585205 lr:0.00018491675484780013 tokens_per_second_per_gpu:2178.895562743742 
Step 1495 | loss:2.3157687187194824 lr:0.00018489596734964274 tokens_per_second_per_gpu:2179.886781927143 
Step 1496 | loss:2.2776355743408203 lr:0.0001848751667069347 tokens_per_second_per_gpu:2172.710343813585 
Step 1497 | loss:2.3164329528808594 lr:0.0001848543529228966 tokens_per_second_per_gpu:2186.7438688544885 
Step 1498 | loss:2.24466872215271 lr:0.0001848335260007511 tokens_per_second_per_gpu:2141.5546683188627 
Step 1499 | loss:2.1966917514801025 lr:0.00018481268594372274 tokens_per_second_per_gpu:2189.6318403996534 
Step 1500 | loss:2.208371639251709 lr:0.0001847918327550383 tokens_per_second_per_gpu:2165.123816591435 
Step 1501 | loss:2.2666399478912354 lr:0.00018477096643792652 tokens_per_second_per_gpu:2153.6346444888145 
Step 1502 | loss:2.2891526222229004 lr:0.0001847500869956181 tokens_per_second_per_gpu:2166.6645019069965 
Step 1503 | loss:2.2817893028259277 lr:0.0001847291944313459 tokens_per_second_per_gpu:2146.0932551856617 
Step 1504 | loss:2.2103638648986816 lr:0.0001847082887483447 tokens_per_second_per_gpu:2182.59929255722 
Step 1505 | loss:2.3216981887817383 lr:0.00018468736994985135 tokens_per_second_per_gpu:2191.3204576662984 
Step 1506 | loss:2.2744216918945312 lr:0.00018466643803910471 tokens_per_second_per_gpu:2167.2109397073787 
Step 1507 | loss:2.2403945922851562 lr:0.0001846454930193458 tokens_per_second_per_gpu:2183.6292011154305 
Step 1508 | loss:2.2754414081573486 lr:0.0001846245348938174 tokens_per_second_per_gpu:2180.3362954711447 
Step 1509 | loss:2.25447416305542 lr:0.00018460356366576462 tokens_per_second_per_gpu:2150.2776084243233 
Step 1510 | loss:2.2213473320007324 lr:0.00018458257933843446 tokens_per_second_per_gpu:2076.9887533885553 
Step 1511 | loss:2.219465732574463 lr:0.00018456158191507586 tokens_per_second_per_gpu:2102.431930997463 
Step 1512 | loss:2.238743782043457 lr:0.00018454057139893993 tokens_per_second_per_gpu:2142.8359130432063 
Step 1513 | loss:2.282350540161133 lr:0.00018451954779327974 tokens_per_second_per_gpu:2116.203511015133 
Step 1514 | loss:2.2356982231140137 lr:0.0001844985111013504 tokens_per_second_per_gpu:2152.7153410171245 
Step 1515 | loss:2.243595838546753 lr:0.0001844774613264091 tokens_per_second_per_gpu:2140.1266822490334 
Step 1516 | loss:2.3216676712036133 lr:0.00018445639847171493 tokens_per_second_per_gpu:2178.6010272052463 
Step 1517 | loss:2.2310233116149902 lr:0.0001844353225405291 tokens_per_second_per_gpu:2181.3679285301932 
Step 1518 | loss:2.2012863159179688 lr:0.00018441423353611486 tokens_per_second_per_gpu:2180.6426593745027 
Step 1519 | loss:2.29301118850708 lr:0.0001843931314617374 tokens_per_second_per_gpu:2190.6335155733796 
Step 1520 | loss:2.2347869873046875 lr:0.000184372016320664 tokens_per_second_per_gpu:2117.3784758339293 
Step 1521 | loss:2.2365362644195557 lr:0.00018435088811616398 tokens_per_second_per_gpu:2179.7080855840463 
Step 1522 | loss:2.2611050605773926 lr:0.00018432974685150862 tokens_per_second_per_gpu:2167.3074286641227 
Step 1523 | loss:2.2971677780151367 lr:0.00018430859252997119 tokens_per_second_per_gpu:2148.9078912299856 
Step 1524 | loss:2.183281183242798 lr:0.00018428742515482713 tokens_per_second_per_gpu:2172.3101764165567 
Step 1525 | loss:2.1830263137817383 lr:0.00018426624472935377 tokens_per_second_per_gpu:2099.3709851478034 
Step 1526 | loss:2.2730937004089355 lr:0.00018424505125683047 tokens_per_second_per_gpu:2163.8018468386676 
Step 1527 | loss:2.2618765830993652 lr:0.0001842238447405387 tokens_per_second_per_gpu:2170.7768865688454 
Step 1528 | loss:2.254526138305664 lr:0.0001842026251837619 tokens_per_second_per_gpu:2080.6489772378955 
Step 1529 | loss:2.2660422325134277 lr:0.00018418139258978547 tokens_per_second_per_gpu:2189.214500415557 
Step 1530 | loss:2.293600082397461 lr:0.0001841601469618969 tokens_per_second_per_gpu:2173.290302619126 
Step 1531 | loss:2.211970567703247 lr:0.00018413888830338566 tokens_per_second_per_gpu:2143.115886685275 
Step 1532 | loss:2.3283700942993164 lr:0.0001841176166175433 tokens_per_second_per_gpu:2148.1790217989756 
Step 1533 | loss:2.2738242149353027 lr:0.00018409633190766332 tokens_per_second_per_gpu:2180.39439923035 
Step 1534 | loss:2.2615630626678467 lr:0.0001840750341770412 tokens_per_second_per_gpu:2154.9798538810305 
Step 1535 | loss:2.206298351287842 lr:0.00018405372342897462 tokens_per_second_per_gpu:2163.5315089776445 
Step 1536 | loss:2.2571797370910645 lr:0.00018403239966676305 tokens_per_second_per_gpu:2119.77909925614 
Step 1537 | loss:2.307765483856201 lr:0.00018401106289370807 tokens_per_second_per_gpu:2181.0521259174657 
Step 1538 | loss:2.2553277015686035 lr:0.00018398971311311336 tokens_per_second_per_gpu:2200.3045344670118 
Step 1539 | loss:2.2568321228027344 lr:0.0001839683503282845 tokens_per_second_per_gpu:2176.1073559728957 
Step 1540 | loss:2.251248836517334 lr:0.00018394697454252908 tokens_per_second_per_gpu:2146.1440838872804 
Step 1541 | loss:2.2813472747802734 lr:0.00018392558575915677 tokens_per_second_per_gpu:2133.909053753758 
Step 1542 | loss:2.2665421962738037 lr:0.0001839041839814792 tokens_per_second_per_gpu:2116.1505630345323 
Step 1543 | loss:2.303330898284912 lr:0.00018388276921281008 tokens_per_second_per_gpu:2187.6200991840774 
Step 1544 | loss:2.3017942905426025 lr:0.00018386134145646503 tokens_per_second_per_gpu:2158.9838366950758 
Step 1545 | loss:2.24843168258667 lr:0.0001838399007157618 tokens_per_second_per_gpu:2102.494618296523 
Step 1546 | loss:2.2622153759002686 lr:0.00018381844699402 tokens_per_second_per_gpu:2181.6958373453854 
Step 1547 | loss:2.246370792388916 lr:0.00018379698029456144 tokens_per_second_per_gpu:2140.4990214100717 
Step 1548 | loss:2.270596504211426 lr:0.00018377550062070977 tokens_per_second_per_gpu:2145.593974312454 
Step 1549 | loss:2.2252817153930664 lr:0.00018375400797579074 tokens_per_second_per_gpu:2158.64190533914 
Step 1550 | loss:2.2261252403259277 lr:0.00018373250236313206 tokens_per_second_per_gpu:2155.103736543814 
Step 1551 | loss:2.2691187858581543 lr:0.0001837109837860635 tokens_per_second_per_gpu:2126.203543473414 
Step 1552 | loss:2.233729600906372 lr:0.0001836894522479168 tokens_per_second_per_gpu:2151.755399471787 
Step 1553 | loss:2.263519048690796 lr:0.00018366790775202566 tokens_per_second_per_gpu:2171.958125373899 
Step 1554 | loss:2.2317209243774414 lr:0.00018364635030172595 tokens_per_second_per_gpu:2125.301583111654 
Step 1555 | loss:2.258697509765625 lr:0.00018362477990035536 tokens_per_second_per_gpu:2146.5918961814873 
Step 1556 | loss:2.233167886734009 lr:0.0001836031965512537 tokens_per_second_per_gpu:2168.026300059389 
Step 1557 | loss:2.3201611042022705 lr:0.0001835816002577627 tokens_per_second_per_gpu:2173.1727634197164 
Step 1558 | loss:2.372541904449463 lr:0.00018355999102322615 tokens_per_second_per_gpu:2145.047590860082 
Step 1559 | loss:2.272909164428711 lr:0.0001835383688509899 tokens_per_second_per_gpu:2188.0012068689903 
Step 1560 | loss:2.23386549949646 lr:0.00018351673374440169 tokens_per_second_per_gpu:2115.7192509367414 
Step 1561 | loss:2.2411811351776123 lr:0.00018349508570681132 tokens_per_second_per_gpu:2193.1182795251216 
Step 1562 | loss:2.2419581413269043 lr:0.00018347342474157055 tokens_per_second_per_gpu:2132.26849577182 
Step 1563 | loss:2.2641382217407227 lr:0.00018345175085203322 tokens_per_second_per_gpu:2142.2049267458938 
Step 1564 | loss:2.2259373664855957 lr:0.00018343006404155512 tokens_per_second_per_gpu:2049.108951688028 
Step 1565 | loss:2.2706832885742188 lr:0.000183408364313494 tokens_per_second_per_gpu:2091.0996419969047 
Step 1566 | loss:2.2070693969726562 lr:0.0001833866516712097 tokens_per_second_per_gpu:2184.568893907751 
Step 1567 | loss:2.185462474822998 lr:0.00018336492611806406 tokens_per_second_per_gpu:2119.565849392878 
Step 1568 | loss:2.201503276824951 lr:0.00018334318765742078 tokens_per_second_per_gpu:2114.0276104353457 
Step 1569 | loss:2.26334810256958 lr:0.0001833214362926457 tokens_per_second_per_gpu:2199.733985366147 
Step 1570 | loss:2.2994585037231445 lr:0.00018329967202710662 tokens_per_second_per_gpu:2180.715000116167 
Step 1571 | loss:2.2722201347351074 lr:0.0001832778948641733 tokens_per_second_per_gpu:2193.272373068548 
Step 1572 | loss:2.250760555267334 lr:0.0001832561048072176 tokens_per_second_per_gpu:2166.1072467125496 
Step 1573 | loss:2.2678394317626953 lr:0.00018323430185961318 tokens_per_second_per_gpu:2175.013322957533 
Step 1574 | loss:2.314579963684082 lr:0.0001832124860247359 tokens_per_second_per_gpu:2145.8262700875807 
Step 1575 | loss:2.321124792098999 lr:0.00018319065730596352 tokens_per_second_per_gpu:2192.03395828631 
Step 1576 | loss:2.1988887786865234 lr:0.0001831688157066758 tokens_per_second_per_gpu:2194.7977923543713 
Step 1577 | loss:2.257768154144287 lr:0.00018314696123025454 tokens_per_second_per_gpu:2120.9719678083297 
Step 1578 | loss:2.1827492713928223 lr:0.00018312509388008344 tokens_per_second_per_gpu:2166.5370369470315 
Step 1579 | loss:2.255362033843994 lr:0.00018310321365954828 tokens_per_second_per_gpu:2155.289059669893 
Step 1580 | loss:2.2398276329040527 lr:0.0001830813205720368 tokens_per_second_per_gpu:2185.9288192044355 
Step 1581 | loss:2.181422472000122 lr:0.0001830594146209387 tokens_per_second_per_gpu:2168.0183436960097 
Step 1582 | loss:2.2816367149353027 lr:0.00018303749580964577 tokens_per_second_per_gpu:2171.3219614248155 
Step 1583 | loss:2.260958671569824 lr:0.0001830155641415517 tokens_per_second_per_gpu:2188.795139433196 
Step 1584 | loss:2.2706265449523926 lr:0.00018299361962005218 tokens_per_second_per_gpu:2089.600874219187 
Step 1585 | loss:2.256533622741699 lr:0.0001829716622485449 tokens_per_second_per_gpu:2175.994152851201 
Step 1586 | loss:2.2313082218170166 lr:0.0001829496920304296 tokens_per_second_per_gpu:2195.6351807094943 
Step 1587 | loss:2.2492706775665283 lr:0.00018292770896910794 tokens_per_second_per_gpu:2080.620466699633 
Step 1588 | loss:2.315124034881592 lr:0.00018290571306798354 tokens_per_second_per_gpu:2178.5715465813128 
Step 1589 | loss:2.1880578994750977 lr:0.0001828837043304621 tokens_per_second_per_gpu:2165.773296193035 
Step 1590 | loss:2.2626302242279053 lr:0.00018286168275995123 tokens_per_second_per_gpu:2159.130299373508 
Step 1591 | loss:2.2070093154907227 lr:0.00018283964835986058 tokens_per_second_per_gpu:2184.362926071647 
Step 1592 | loss:2.271073579788208 lr:0.00018281760113360177 tokens_per_second_per_gpu:2147.024110610053 
Step 1593 | loss:2.19734787940979 lr:0.00018279554108458835 tokens_per_second_per_gpu:2163.4701331739097 
Step 1594 | loss:2.2206013202667236 lr:0.000182773468216236 tokens_per_second_per_gpu:2195.532034986082 
Step 1595 | loss:2.196336269378662 lr:0.00018275138253196217 tokens_per_second_per_gpu:2195.8753786213288 
Step 1596 | loss:2.244948387145996 lr:0.00018272928403518653 tokens_per_second_per_gpu:2140.6911617087667 
Step 1597 | loss:2.28456449508667 lr:0.00018270717272933056 tokens_per_second_per_gpu:2143.0911503916295 
Step 1598 | loss:2.199192523956299 lr:0.00018268504861781776 tokens_per_second_per_gpu:2192.557779225409 
Step 1599 | loss:2.2519898414611816 lr:0.0001826629117040737 tokens_per_second_per_gpu:2117.38705551334 
Step 1600 | loss:2.193864107131958 lr:0.0001826407619915258 tokens_per_second_per_gpu:2158.7165184345863 
Step 1601 | loss:2.256524085998535 lr:0.00018261859948360355 tokens_per_second_per_gpu:2154.7528861515575 
Step 1602 | loss:2.2685494422912598 lr:0.00018259642418373844 tokens_per_second_per_gpu:2133.6167823908363 
Step 1603 | loss:2.2665019035339355 lr:0.00018257423609536384 tokens_per_second_per_gpu:2153.0050955621755 
Step 1604 | loss:2.230116128921509 lr:0.00018255203522191517 tokens_per_second_per_gpu:2144.419667704203 
Step 1605 | loss:2.2092602252960205 lr:0.00018252982156682988 tokens_per_second_per_gpu:2199.6342945929455 
Step 1606 | loss:2.2292892932891846 lr:0.00018250759513354728 tokens_per_second_per_gpu:2195.767417615869 
Step 1607 | loss:2.2666826248168945 lr:0.0001824853559255087 tokens_per_second_per_gpu:2196.8844835682353 
Step 1608 | loss:2.2815771102905273 lr:0.0001824631039461575 tokens_per_second_per_gpu:2165.373703394359 
Step 1609 | loss:2.247037887573242 lr:0.00018244083919893904 tokens_per_second_per_gpu:2194.346258505034 
Step 1610 | loss:2.2213401794433594 lr:0.00018241856168730046 tokens_per_second_per_gpu:2146.4829044450407 
Step 1611 | loss:2.1971497535705566 lr:0.00018239627141469113 tokens_per_second_per_gpu:2159.293488995715 
Step 1612 | loss:2.2080516815185547 lr:0.00018237396838456226 tokens_per_second_per_gpu:2165.9327485685144 
Step 1613 | loss:2.1815690994262695 lr:0.000182351652600367 tokens_per_second_per_gpu:2173.372510861207 
Step 1614 | loss:2.2140238285064697 lr:0.00018232932406556064 tokens_per_second_per_gpu:2120.452354282856 
Step 1615 | loss:2.169394016265869 lr:0.0001823069827836002 tokens_per_second_per_gpu:2111.959513928717 
Step 1616 | loss:2.250769853591919 lr:0.00018228462875794488 tokens_per_second_per_gpu:2184.8993878350043 
Step 1617 | loss:2.2985928058624268 lr:0.0001822622619920558 tokens_per_second_per_gpu:2135.704301119621 
Step 1618 | loss:2.307218074798584 lr:0.000182239882489396 tokens_per_second_per_gpu:2109.649579251271 
Step 1619 | loss:2.265042543411255 lr:0.00018221749025343058 tokens_per_second_per_gpu:2174.954159102763 
Step 1620 | loss:2.260749578475952 lr:0.00018219508528762648 tokens_per_second_per_gpu:2175.7583934832387 
Step 1621 | loss:2.215982675552368 lr:0.00018217266759545275 tokens_per_second_per_gpu:2165.3570595675583 
Step 1622 | loss:2.250833749771118 lr:0.0001821502371803803 tokens_per_second_per_gpu:2116.3581682311824 
Step 1623 | loss:2.218402624130249 lr:0.0001821277940458821 tokens_per_second_per_gpu:2195.937325695414 
Step 1624 | loss:2.2059059143066406 lr:0.00018210533819543306 tokens_per_second_per_gpu:2175.7736915010464 
Step 1625 | loss:2.2618417739868164 lr:0.00018208286963251 tokens_per_second_per_gpu:2133.4683497826086 
Step 1626 | loss:2.273646354675293 lr:0.00018206038836059176 tokens_per_second_per_gpu:2172.4485727046595 
Step 1627 | loss:2.230293035507202 lr:0.00018203789438315921 tokens_per_second_per_gpu:2196.021882446154 
Step 1628 | loss:2.2192883491516113 lr:0.00018201538770369507 tokens_per_second_per_gpu:2101.707027532392 
Step 1629 | loss:2.1934540271759033 lr:0.00018199286832568405 tokens_per_second_per_gpu:2150.4914833989174 
Step 1630 | loss:2.194410562515259 lr:0.00018197033625261293 tokens_per_second_per_gpu:2196.992410514752 
Step 1631 | loss:2.2520651817321777 lr:0.0001819477914879703 tokens_per_second_per_gpu:2164.7890658577057 
Step 1632 | loss:2.283390760421753 lr:0.00018192523403524685 tokens_per_second_per_gpu:2187.181723053399 
Step 1633 | loss:2.2556352615356445 lr:0.00018190266389793514 tokens_per_second_per_gpu:2115.6398142163116 
Step 1634 | loss:2.2848167419433594 lr:0.0001818800810795298 tokens_per_second_per_gpu:2166.350041224324 
Step 1635 | loss:2.2312309741973877 lr:0.00018185748558352728 tokens_per_second_per_gpu:2121.3932782455067 
Step 1636 | loss:2.2205119132995605 lr:0.00018183487741342612 tokens_per_second_per_gpu:2176.8447788429935 
Step 1637 | loss:2.227552652359009 lr:0.00018181225657272671 tokens_per_second_per_gpu:2171.2849349229527 
Step 1638 | loss:2.264622688293457 lr:0.00018178962306493153 tokens_per_second_per_gpu:2197.5471558211907 
Step 1639 | loss:2.2582454681396484 lr:0.00018176697689354493 tokens_per_second_per_gpu:2194.9128250198296 
Step 1640 | loss:2.2453174591064453 lr:0.00018174431806207325 tokens_per_second_per_gpu:2195.704954605395 
Step 1641 | loss:2.199954032897949 lr:0.00018172164657402477 tokens_per_second_per_gpu:2146.3023606532047 
Step 1642 | loss:2.190030574798584 lr:0.00018169896243290978 tokens_per_second_per_gpu:2115.7733003131693 
Step 1643 | loss:2.3248744010925293 lr:0.00018167626564224044 tokens_per_second_per_gpu:2185.4727689133224 
Step 1644 | loss:2.2441892623901367 lr:0.00018165355620553098 tokens_per_second_per_gpu:2131.636157454362 
Step 1645 | loss:2.2181572914123535 lr:0.0001816308341262975 tokens_per_second_per_gpu:2187.0589426072934 
Step 1646 | loss:2.268692970275879 lr:0.00018160809940805808 tokens_per_second_per_gpu:2158.4688219764616 
Step 1647 | loss:2.279857635498047 lr:0.0001815853520543328 tokens_per_second_per_gpu:2194.523924511516 
Step 1648 | loss:2.192365884780884 lr:0.00018156259206864362 tokens_per_second_per_gpu:2149.5499485732253 
Step 1649 | loss:2.1983559131622314 lr:0.0001815398194545145 tokens_per_second_per_gpu:2138.8251130406315 
Step 1650 | loss:2.206939697265625 lr:0.0001815170342154714 tokens_per_second_per_gpu:2179.4780254630414 
Step 1651 | loss:2.2351255416870117 lr:0.00018149423635504218 tokens_per_second_per_gpu:2180.173081084164 
Step 1652 | loss:2.172236204147339 lr:0.0001814714258767566 tokens_per_second_per_gpu:2192.4097040255897 
Step 1653 | loss:2.2137985229492188 lr:0.00018144860278414648 tokens_per_second_per_gpu:2194.9278538877875 
Step 1654 | loss:2.2003633975982666 lr:0.00018142576708074558 tokens_per_second_per_gpu:2103.0229578683197 
Step 1655 | loss:2.2554759979248047 lr:0.0001814029187700895 tokens_per_second_per_gpu:2185.9998934339415 
Step 1656 | loss:2.241454601287842 lr:0.00018138005785571593 tokens_per_second_per_gpu:2116.3088240977495 
Step 1657 | loss:2.175771713256836 lr:0.00018135718434116448 tokens_per_second_per_gpu:2190.1778799553654 
Step 1658 | loss:2.1910817623138428 lr:0.0001813342982299766 tokens_per_second_per_gpu:2195.611547973429 
Step 1659 | loss:2.239572048187256 lr:0.00018131139952569584 tokens_per_second_per_gpu:2129.860152159076 
Step 1660 | loss:2.187100887298584 lr:0.00018128848823186763 tokens_per_second_per_gpu:2168.2010312826856 
Step 1661 | loss:2.20021915435791 lr:0.00018126556435203934 tokens_per_second_per_gpu:2197.992428283924 
Step 1662 | loss:2.1886367797851562 lr:0.0001812426278897603 tokens_per_second_per_gpu:2173.7682554288112 
Step 1663 | loss:2.217207193374634 lr:0.0001812196788485818 tokens_per_second_per_gpu:2192.5628957688555 
Step 1664 | loss:2.2487850189208984 lr:0.00018119671723205706 tokens_per_second_per_gpu:2113.26098927251 
Step 1665 | loss:2.2526745796203613 lr:0.00018117374304374128 tokens_per_second_per_gpu:2178.913498419346 
Step 1666 | loss:2.212794303894043 lr:0.00018115075628719155 tokens_per_second_per_gpu:2129.9556848498673 
Step 1667 | loss:2.289354085922241 lr:0.000181127756965967 tokens_per_second_per_gpu:2149.247169294177 
Step 1668 | loss:2.235295534133911 lr:0.00018110474508362855 tokens_per_second_per_gpu:2146.900863727919 
Step 1669 | loss:2.2554798126220703 lr:0.00018108172064373922 tokens_per_second_per_gpu:2128.8461354083815 
Step 1670 | loss:2.225860118865967 lr:0.00018105868364986393 tokens_per_second_per_gpu:2124.791937623889 
Step 1671 | loss:2.230898857116699 lr:0.00018103563410556948 tokens_per_second_per_gpu:2130.939506603239 
Step 1672 | loss:2.214587688446045 lr:0.00018101257201442469 tokens_per_second_per_gpu:2177.5283537921773 
Step 1673 | loss:2.2640745639801025 lr:0.00018098949738000025 tokens_per_second_per_gpu:2067.761409371584 
Step 1674 | loss:2.2207260131835938 lr:0.0001809664102058689 tokens_per_second_per_gpu:2115.7064678272454 
Step 1675 | loss:2.2464094161987305 lr:0.00018094331049560523 tokens_per_second_per_gpu:2190.4437697480435 
Step 1676 | loss:2.3076553344726562 lr:0.00018092019825278577 tokens_per_second_per_gpu:2091.198086842033 
Step 1677 | loss:2.2825374603271484 lr:0.00018089707348098907 tokens_per_second_per_gpu:2149.246813329441 
Step 1678 | loss:2.23006534576416 lr:0.0001808739361837955 tokens_per_second_per_gpu:2142.429549934586 
Step 1679 | loss:2.200798749923706 lr:0.00018085078636478753 tokens_per_second_per_gpu:2080.486736823462 
Step 1680 | loss:2.1626949310302734 lr:0.00018082762402754936 tokens_per_second_per_gpu:2193.2559670613864 
Step 1681 | loss:2.2422351837158203 lr:0.00018080444917566732 tokens_per_second_per_gpu:2132.8751069513337 
Step 1682 | loss:2.261983871459961 lr:0.00018078126181272962 tokens_per_second_per_gpu:2078.3212635127607 
Step 1683 | loss:2.294311046600342 lr:0.00018075806194232632 tokens_per_second_per_gpu:2187.5943645701163 
Step 1684 | loss:2.2641727924346924 lr:0.0001807348495680495 tokens_per_second_per_gpu:2113.4035990866255 
Step 1685 | loss:2.2384042739868164 lr:0.00018071162469349324 tokens_per_second_per_gpu:2194.4054222365858 
Step 1686 | loss:2.261740207672119 lr:0.0001806883873222534 tokens_per_second_per_gpu:2170.9693520442797 
Step 1687 | loss:2.2601635456085205 lr:0.00018066513745792787 tokens_per_second_per_gpu:2184.2749740934155 
Step 1688 | loss:2.214388847351074 lr:0.00018064187510411644 tokens_per_second_per_gpu:2083.627811846593 
Step 1689 | loss:2.214336395263672 lr:0.0001806186002644209 tokens_per_second_per_gpu:2117.861376134667 
Step 1690 | loss:2.2904715538024902 lr:0.00018059531294244488 tokens_per_second_per_gpu:2167.9238483940167 
Step 1691 | loss:2.227266311645508 lr:0.00018057201314179396 tokens_per_second_per_gpu:2156.781385907366 
Step 1692 | loss:2.28523325920105 lr:0.00018054870086607578 tokens_per_second_per_gpu:2169.3147499938773 
Step 1693 | loss:2.2783665657043457 lr:0.0001805253761188997 tokens_per_second_per_gpu:2166.3160349551445 
Step 1694 | loss:2.267550468444824 lr:0.0001805020389038772 tokens_per_second_per_gpu:2199.5705309518407 
Step 1695 | loss:2.194542169570923 lr:0.00018047868922462152 tokens_per_second_per_gpu:2183.2699389495006 
Step 1696 | loss:2.268176794052124 lr:0.000180455327084748 tokens_per_second_per_gpu:2194.9577680598813 
Step 1697 | loss:2.2424159049987793 lr:0.00018043195248787378 tokens_per_second_per_gpu:2186.075663353122 
Step 1698 | loss:2.3025946617126465 lr:0.00018040856543761804 tokens_per_second_per_gpu:2145.848446298504 
Step 1699 | loss:2.1949212551116943 lr:0.00018038516593760177 tokens_per_second_per_gpu:2170.920009315342 
Step 1700 | loss:2.1750688552856445 lr:0.000180361753991448 tokens_per_second_per_gpu:2195.5675248723987 
Step 1701 | loss:2.2475459575653076 lr:0.00018033832960278153 tokens_per_second_per_gpu:2164.5364792463647 
Step 1702 | loss:2.2597856521606445 lr:0.0001803148927752293 tokens_per_second_per_gpu:2179.973010462499 
Step 1703 | loss:2.224620819091797 lr:0.00018029144351242003 tokens_per_second_per_gpu:2183.5805087374856 
Step 1704 | loss:2.2872776985168457 lr:0.00018026798181798435 tokens_per_second_per_gpu:2179.9530403534272 
Step 1705 | loss:2.171898365020752 lr:0.00018024450769555493 tokens_per_second_per_gpu:2151.437149487248 
Step 1706 | loss:2.287691116333008 lr:0.00018022102114876625 tokens_per_second_per_gpu:2192.9905861992866 
Step 1707 | loss:2.2246005535125732 lr:0.00018019752218125478 tokens_per_second_per_gpu:2169.948587711982 
Step 1708 | loss:2.2138729095458984 lr:0.0001801740107966589 tokens_per_second_per_gpu:2178.9854948179814 
Step 1709 | loss:2.1859095096588135 lr:0.0001801504869986189 tokens_per_second_per_gpu:2190.7724026834903 
Step 1710 | loss:2.1939826011657715 lr:0.00018012695079077702 tokens_per_second_per_gpu:2159.609920146845 
Step 1711 | loss:2.1800575256347656 lr:0.00018010340217677737 tokens_per_second_per_gpu:2173.054617405433 
Step 1712 | loss:2.2815425395965576 lr:0.00018007984116026604 tokens_per_second_per_gpu:2184.3439014241285 
Step 1713 | loss:2.2428715229034424 lr:0.00018005626774489098 tokens_per_second_per_gpu:2188.1343696499925 
Step 1714 | loss:2.2400693893432617 lr:0.0001800326819343021 tokens_per_second_per_gpu:2159.2396832943987 
Step 1715 | loss:2.202442169189453 lr:0.00018000908373215128 tokens_per_second_per_gpu:2111.137546739474 
Step 1716 | loss:2.249309539794922 lr:0.00017998547314209215 tokens_per_second_per_gpu:2192.1739717061228 
Step 1717 | loss:2.217933416366577 lr:0.0001799618501677805 tokens_per_second_per_gpu:2144.9129660635203 
Step 1718 | loss:2.2551021575927734 lr:0.00017993821481287377 tokens_per_second_per_gpu:2171.4810896647236 
Step 1719 | loss:2.2932143211364746 lr:0.00017991456708103153 tokens_per_second_per_gpu:2145.131778780848 
Step 1720 | loss:2.2981083393096924 lr:0.00017989090697591518 tokens_per_second_per_gpu:2167.439655057896 
Step 1721 | loss:2.2633461952209473 lr:0.00017986723450118803 tokens_per_second_per_gpu:2137.8201335164445 
Step 1722 | loss:2.234466791152954 lr:0.00017984354966051535 tokens_per_second_per_gpu:2171.393444151419 
Step 1723 | loss:2.257154941558838 lr:0.00017981985245756426 tokens_per_second_per_gpu:2193.0183660030793 
Step 1724 | loss:2.244384527206421 lr:0.0001797961428960038 tokens_per_second_per_gpu:2183.952938335516 
Step 1725 | loss:2.207639217376709 lr:0.00017977242097950505 tokens_per_second_per_gpu:2175.1604256178707 
Step 1726 | loss:2.2075986862182617 lr:0.00017974868671174083 tokens_per_second_per_gpu:2128.5104016008595 
Step 1727 | loss:2.2448158264160156 lr:0.000179724940096386 tokens_per_second_per_gpu:2119.893937398775 
Step 1728 | loss:2.2986106872558594 lr:0.00017970118113711715 tokens_per_second_per_gpu:2130.0843973056135 
Step 1729 | loss:2.153560161590576 lr:0.0001796774098376131 tokens_per_second_per_gpu:2197.8368819951856 
Step 1730 | loss:2.186642646789551 lr:0.0001796536262015542 tokens_per_second_per_gpu:2194.0835924664266 
Step 1731 | loss:2.3052945137023926 lr:0.00017962983023262304 tokens_per_second_per_gpu:2153.2894947367013 
Step 1732 | loss:2.165726661682129 lr:0.00017960602193450392 tokens_per_second_per_gpu:2184.8038749348634 
Step 1733 | loss:2.2199299335479736 lr:0.00017958220131088318 tokens_per_second_per_gpu:2189.1652911748533 
Step 1734 | loss:2.230123519897461 lr:0.0001795583683654489 tokens_per_second_per_gpu:2183.8094866608185 
Step 1735 | loss:2.1608753204345703 lr:0.00017953452310189117 tokens_per_second_per_gpu:2122.2214432833393 
Step 1736 | loss:2.2030043601989746 lr:0.00017951066552390204 tokens_per_second_per_gpu:2182.5807398615416 
Step 1737 | loss:2.1795926094055176 lr:0.0001794867956351754 tokens_per_second_per_gpu:2063.4917793460936 
Step 1738 | loss:2.2631583213806152 lr:0.000179462913439407 tokens_per_second_per_gpu:2177.4065643409276 
Step 1739 | loss:2.230905055999756 lr:0.00017943901894029463 tokens_per_second_per_gpu:2173.1683993893967 
Step 1740 | loss:2.166020393371582 lr:0.00017941511214153785 tokens_per_second_per_gpu:2169.111305483717 
Step 1741 | loss:2.2702999114990234 lr:0.00017939119304683822 tokens_per_second_per_gpu:2124.2317177378677 
Step 1742 | loss:2.299574851989746 lr:0.00017936726165989914 tokens_per_second_per_gpu:2175.577234011213 
Step 1743 | loss:2.224917411804199 lr:0.00017934331798442595 tokens_per_second_per_gpu:2182.095653847411 
Step 1744 | loss:2.285149097442627 lr:0.00017931936202412581 tokens_per_second_per_gpu:2191.3969662275254 
Step 1745 | loss:2.2493114471435547 lr:0.00017929539378270794 tokens_per_second_per_gpu:2185.6238454688364 
Step 1746 | loss:2.2270171642303467 lr:0.00017927141326388337 tokens_per_second_per_gpu:2187.8362844774488 
Step 1747 | loss:2.2231171131134033 lr:0.000179247420471365 tokens_per_second_per_gpu:2165.1530408429608 
Step 1748 | loss:2.2393743991851807 lr:0.00017922341540886768 tokens_per_second_per_gpu:2189.090243195414 
Step 1749 | loss:2.173107147216797 lr:0.0001791993980801081 tokens_per_second_per_gpu:2172.382983387487 
Step 1750 | loss:2.2521796226501465 lr:0.00017917536848880493 tokens_per_second_per_gpu:2177.8111577058385 
Step 1751 | loss:2.2944178581237793 lr:0.00017915132663867876 tokens_per_second_per_gpu:2165.249783929228 
Step 1752 | loss:2.239840269088745 lr:0.0001791272725334519 tokens_per_second_per_gpu:2163.342103427101 
Step 1753 | loss:2.204982280731201 lr:0.00017910320617684877 tokens_per_second_per_gpu:2193.134257181965 
Step 1754 | loss:2.207334041595459 lr:0.00017907912757259554 tokens_per_second_per_gpu:2092.0596316978786 
Step 1755 | loss:2.2353529930114746 lr:0.00017905503672442042 tokens_per_second_per_gpu:2136.787223572247 
Step 1756 | loss:2.1922497749328613 lr:0.0001790309336360533 tokens_per_second_per_gpu:2151.572536873222 
Step 1757 | loss:2.2544074058532715 lr:0.00017900681831122618 tokens_per_second_per_gpu:2175.897221374591 
Step 1758 | loss:2.247603416442871 lr:0.00017898269075367285 tokens_per_second_per_gpu:2180.2997694147175 
Step 1759 | loss:2.180459976196289 lr:0.000178958550967129 tokens_per_second_per_gpu:2160.5479140561706 
Step 1760 | loss:2.2013659477233887 lr:0.0001789343989553322 tokens_per_second_per_gpu:2185.857649104399 
Step 1761 | loss:2.16312837600708 lr:0.000178910234722022 tokens_per_second_per_gpu:2171.9852060817825 
Step 1762 | loss:2.268021821975708 lr:0.0001788860582709397 tokens_per_second_per_gpu:2189.701890478798 
Step 1763 | loss:2.183204174041748 lr:0.00017886186960582864 tokens_per_second_per_gpu:2177.5652577752985 
Step 1764 | loss:2.1831817626953125 lr:0.00017883766873043393 tokens_per_second_per_gpu:2161.7122069019883 
Step 1765 | loss:2.194303512573242 lr:0.00017881345564850268 tokens_per_second_per_gpu:2169.8536734517443 
Step 1766 | loss:2.279439687728882 lr:0.00017878923036378377 tokens_per_second_per_gpu:2182.2934249555547 
Step 1767 | loss:2.284661054611206 lr:0.00017876499288002807 tokens_per_second_per_gpu:2145.484625323677 
Step 1768 | loss:2.205928325653076 lr:0.0001787407432009883 tokens_per_second_per_gpu:2165.624221371052 
Step 1769 | loss:2.189356565475464 lr:0.00017871648133041906 tokens_per_second_per_gpu:2176.856655806821 
Step 1770 | loss:2.252316951751709 lr:0.00017869220727207682 tokens_per_second_per_gpu:2132.6918651168858 
Step 1771 | loss:2.244441032409668 lr:0.00017866792102972 tokens_per_second_per_gpu:2171.665145757471 
Step 1772 | loss:2.2592248916625977 lr:0.00017864362260710888 tokens_per_second_per_gpu:2165.3614999983924 
Step 1773 | loss:2.2307488918304443 lr:0.00017861931200800556 tokens_per_second_per_gpu:2121.0816204679613 
Step 1774 | loss:2.259639263153076 lr:0.00017859498923617414 tokens_per_second_per_gpu:2180.191556803676 
Step 1775 | loss:2.2106781005859375 lr:0.0001785706542953805 tokens_per_second_per_gpu:2188.8573448774146 
Step 1776 | loss:2.2540836334228516 lr:0.00017854630718939252 tokens_per_second_per_gpu:2188.3164579281956 
Step 1777 | loss:2.245426654815674 lr:0.00017852194792197977 tokens_per_second_per_gpu:2186.2666548645657 
Step 1778 | loss:2.2617859840393066 lr:0.00017849757649691396 tokens_per_second_per_gpu:2130.816382837638 
Step 1779 | loss:2.264838695526123 lr:0.00017847319291796848 tokens_per_second_per_gpu:2127.6360892243115 
Step 1780 | loss:2.24985671043396 lr:0.00017844879718891866 tokens_per_second_per_gpu:2179.0703040373237 
Step 1781 | loss:2.201483726501465 lr:0.00017842438931354177 tokens_per_second_per_gpu:2038.864719654309 
Step 1782 | loss:2.282762050628662 lr:0.00017839996929561687 tokens_per_second_per_gpu:2089.8115192304 
Step 1783 | loss:2.218766212463379 lr:0.00017837553713892493 tokens_per_second_per_gpu:2185.7212155540365 
Step 1784 | loss:2.2115111351013184 lr:0.00017835109284724886 tokens_per_second_per_gpu:2174.7942458637035 
Step 1785 | loss:2.1969804763793945 lr:0.0001783266364243734 tokens_per_second_per_gpu:2091.5504449160485 
Step 1786 | loss:2.2625601291656494 lr:0.00017830216787408513 tokens_per_second_per_gpu:2176.7268352298784 
Step 1787 | loss:2.286378860473633 lr:0.00017827768720017254 tokens_per_second_per_gpu:2182.006496635916 
Step 1788 | loss:2.21968936920166 lr:0.00017825319440642606 tokens_per_second_per_gpu:2129.6898023794265 
Step 1789 | loss:2.1941628456115723 lr:0.0001782286894966379 tokens_per_second_per_gpu:2193.2632085642463 
Step 1790 | loss:2.1748733520507812 lr:0.0001782041724746022 tokens_per_second_per_gpu:2143.8911432518785 
Step 1791 | loss:2.220629930496216 lr:0.00017817964334411498 tokens_per_second_per_gpu:2166.868303614454 
Step 1792 | loss:2.2816576957702637 lr:0.00017815510210897407 tokens_per_second_per_gpu:2186.3487505863363 
Step 1793 | loss:2.292583465576172 lr:0.00017813054877297924 tokens_per_second_per_gpu:2177.961561175466 
Step 1794 | loss:2.240492820739746 lr:0.00017810598333993212 tokens_per_second_per_gpu:2173.772613704731 
Step 1795 | loss:2.243330955505371 lr:0.00017808140581363619 tokens_per_second_per_gpu:2147.332857332497 
Step 1796 | loss:2.241894483566284 lr:0.00017805681619789687 tokens_per_second_per_gpu:2186.8616841252474 
Step 1797 | loss:2.1777689456939697 lr:0.00017803221449652135 tokens_per_second_per_gpu:2187.6284627477 
Step 1798 | loss:2.2251129150390625 lr:0.00017800760071331876 tokens_per_second_per_gpu:2183.421422816859 
Step 1799 | loss:2.2042737007141113 lr:0.00017798297485210012 tokens_per_second_per_gpu:2188.044191361109 
Step 1800 | loss:2.2395153045654297 lr:0.0001779583369166782 tokens_per_second_per_gpu:2183.9968919469757 
Step 1801 | loss:2.2407028675079346 lr:0.00017793368691086778 tokens_per_second_per_gpu:2121.78404947015 
Step 1802 | loss:2.142723798751831 lr:0.00017790902483848546 tokens_per_second_per_gpu:2191.316861653775 
Step 1803 | loss:2.1967968940734863 lr:0.00017788435070334967 tokens_per_second_per_gpu:2121.187282148796 
Step 1804 | loss:2.1957952976226807 lr:0.00017785966450928076 tokens_per_second_per_gpu:2193.463610920941 
Step 1805 | loss:2.1933279037475586 lr:0.00017783496626010088 tokens_per_second_per_gpu:2167.1820205285535 
Step 1806 | loss:2.215118169784546 lr:0.00017781025595963414 tokens_per_second_per_gpu:2172.3340174615078 
Step 1807 | loss:2.2884554862976074 lr:0.00017778553361170646 tokens_per_second_per_gpu:2146.460242825714 
Step 1808 | loss:2.2092032432556152 lr:0.00017776079922014564 tokens_per_second_per_gpu:2126.5665709183577 
Step 1809 | loss:2.22900652885437 lr:0.00017773605278878133 tokens_per_second_per_gpu:2194.422234608082 
Step 1810 | loss:2.2430667877197266 lr:0.000177711294321445 tokens_per_second_per_gpu:2147.027934354825 
Step 1811 | loss:2.1408276557922363 lr:0.0001776865238219701 tokens_per_second_per_gpu:2195.581393480864 
Step 1812 | loss:2.2484660148620605 lr:0.00017766174129419188 tokens_per_second_per_gpu:2036.1548372595887 
Step 1813 | loss:2.2166271209716797 lr:0.0001776369467419474 tokens_per_second_per_gpu:2182.4756070886688 
Step 1814 | loss:2.2327864170074463 lr:0.00017761214016907565 tokens_per_second_per_gpu:2135.860762361212 
Step 1815 | loss:2.2088053226470947 lr:0.00017758732157941752 tokens_per_second_per_gpu:2188.57855522332 
Step 1816 | loss:2.2398266792297363 lr:0.0001775624909768156 tokens_per_second_per_gpu:2163.448956248009 
Step 1817 | loss:2.2282536029815674 lr:0.00017753764836511455 tokens_per_second_per_gpu:2197.9106137510703 
Step 1818 | loss:2.223329544067383 lr:0.0001775127937481607 tokens_per_second_per_gpu:2152.557399599271 
Step 1819 | loss:2.175952911376953 lr:0.00017748792712980236 tokens_per_second_per_gpu:2170.0570327120913 
Step 1820 | loss:2.187063217163086 lr:0.00017746304851388967 tokens_per_second_per_gpu:2186.496360296609 
Step 1821 | loss:2.195467710494995 lr:0.0001774381579042746 tokens_per_second_per_gpu:2189.4441404430727 
Step 1822 | loss:2.1829161643981934 lr:0.000177413255304811 tokens_per_second_per_gpu:2148.024218843373 
Step 1823 | loss:2.1709787845611572 lr:0.00017738834071935456 tokens_per_second_per_gpu:2183.0531299207823 
Step 1824 | loss:2.241055965423584 lr:0.00017736341415176284 tokens_per_second_per_gpu:2152.8646902213136 
Step 1825 | loss:2.219398021697998 lr:0.00017733847560589527 tokens_per_second_per_gpu:2192.8951923474133 
Step 1826 | loss:2.17277193069458 lr:0.0001773135250856131 tokens_per_second_per_gpu:2186.80405274201 
Step 1827 | loss:2.2608189582824707 lr:0.00017728856259477947 tokens_per_second_per_gpu:2194.7897830974725 
Step 1828 | loss:2.2513930797576904 lr:0.00017726358813725934 tokens_per_second_per_gpu:2166.5721393694057 
Step 1829 | loss:2.2500717639923096 lr:0.0001772386017169195 tokens_per_second_per_gpu:2195.8577785471443 
Step 1830 | loss:2.2390518188476562 lr:0.00017721360333762873 tokens_per_second_per_gpu:2193.9794206591205 
Step 1831 | loss:2.292402744293213 lr:0.00017718859300325745 tokens_per_second_per_gpu:2188.4316909724466 
Step 1832 | loss:2.1083009243011475 lr:0.0001771635707176781 tokens_per_second_per_gpu:2178.956751656651 
Step 1833 | loss:2.2377986907958984 lr:0.0001771385364847649 tokens_per_second_per_gpu:2200.4890401886187 
Step 1834 | loss:2.2354536056518555 lr:0.00017711349030839394 tokens_per_second_per_gpu:2121.9006651976156 
Step 1835 | loss:2.2496442794799805 lr:0.00017708843219244315 tokens_per_second_per_gpu:2191.3234447963837 
Step 1836 | loss:2.1135878562927246 lr:0.0001770633621407923 tokens_per_second_per_gpu:2186.8993438221964 
Step 1837 | loss:2.223238468170166 lr:0.00017703828015732303 tokens_per_second_per_gpu:2167.5391205405967 
Step 1838 | loss:2.1604881286621094 lr:0.0001770131862459188 tokens_per_second_per_gpu:2152.8952194284466 
Step 1839 | loss:2.194355010986328 lr:0.00017698808041046493 tokens_per_second_per_gpu:2074.5640137621817 
Step 1840 | loss:2.2226874828338623 lr:0.00017696296265484862 tokens_per_second_per_gpu:2193.049998100142 
Step 1841 | loss:2.210353136062622 lr:0.00017693783298295884 tokens_per_second_per_gpu:2192.2693419885663 
Step 1842 | loss:2.283944606781006 lr:0.0001769126913986865 tokens_per_second_per_gpu:2189.2698657031005 
Step 1843 | loss:2.2511582374572754 lr:0.00017688753790592426 tokens_per_second_per_gpu:2104.3518058690747 
Step 1844 | loss:2.262415885925293 lr:0.0001768623725085667 tokens_per_second_per_gpu:2197.421539877044 
Step 1845 | loss:2.2042622566223145 lr:0.00017683719521051017 tokens_per_second_per_gpu:2101.2387160360204 
Step 1846 | loss:2.1888437271118164 lr:0.00017681200601565294 tokens_per_second_per_gpu:2163.6763853713205 
Step 1847 | loss:2.2668867111206055 lr:0.00017678680492789507 tokens_per_second_per_gpu:2181.7962980140237 
Step 1848 | loss:2.152992010116577 lr:0.0001767615919511385 tokens_per_second_per_gpu:2163.388594675479 
Step 1849 | loss:2.2420477867126465 lr:0.00017673636708928693 tokens_per_second_per_gpu:2165.9109149906676 
Step 1850 | loss:2.184354782104492 lr:0.000176711130346246 tokens_per_second_per_gpu:2192.7602823527436 
Step 1851 | loss:2.198012351989746 lr:0.00017668588172592314 tokens_per_second_per_gpu:2149.053473418131 
Step 1852 | loss:2.1964104175567627 lr:0.00017666062123222767 tokens_per_second_per_gpu:2190.0385871840995 
Step 1853 | loss:2.2244691848754883 lr:0.00017663534886907061 tokens_per_second_per_gpu:2136.4876814023455 
Step 1854 | loss:2.175281524658203 lr:0.00017661006464036498 tokens_per_second_per_gpu:2186.0911541281976 
Step 1855 | loss:2.180846691131592 lr:0.00017658476855002554 tokens_per_second_per_gpu:2198.0551037830037 
Step 1856 | loss:2.314462423324585 lr:0.00017655946060196896 tokens_per_second_per_gpu:2179.88968272303 
Step 1857 | loss:2.238922357559204 lr:0.00017653414080011362 tokens_per_second_per_gpu:2186.5839638820817 
Step 1858 | loss:2.1910030841827393 lr:0.00017650880914837992 tokens_per_second_per_gpu:2195.8026557950984 
Step 1859 | loss:2.205124855041504 lr:0.00017648346565068992 tokens_per_second_per_gpu:2156.927058969446 
Step 1860 | loss:2.2171719074249268 lr:0.0001764581103109676 tokens_per_second_per_gpu:2115.093167260709 
Step 1861 | loss:2.1982674598693848 lr:0.00017643274313313873 tokens_per_second_per_gpu:2175.9924873071395 
Step 1862 | loss:2.19706654548645 lr:0.00017640736412113104 tokens_per_second_per_gpu:2155.738893725775 
Step 1863 | loss:2.245603322982788 lr:0.0001763819732788739 tokens_per_second_per_gpu:2175.864082312861 
Step 1864 | loss:2.212346076965332 lr:0.0001763565706102986 tokens_per_second_per_gpu:2145.2805055467084 
Step 1865 | loss:2.1873862743377686 lr:0.00017633115611933838 tokens_per_second_per_gpu:2130.2179774072592 
Step 1866 | loss:2.2618014812469482 lr:0.0001763057298099281 tokens_per_second_per_gpu:2178.6773563353167 
Step 1867 | loss:2.2219862937927246 lr:0.00017628029168600455 tokens_per_second_per_gpu:2062.8665621842956 
Step 1868 | loss:2.2730019092559814 lr:0.00017625484175150637 tokens_per_second_per_gpu:2180.8019296634507 
Step 1869 | loss:2.2816758155822754 lr:0.00017622938001037402 tokens_per_second_per_gpu:2125.1992988438283 
Step 1870 | loss:2.215564489364624 lr:0.00017620390646654976 tokens_per_second_per_gpu:2198.4002559051305 
Step 1871 | loss:2.249934196472168 lr:0.00017617842112397766 tokens_per_second_per_gpu:2176.0180921318733 
Step 1872 | loss:2.2022461891174316 lr:0.00017615292398660373 tokens_per_second_per_gpu:2143.1022002563845 
Step 1873 | loss:2.198526620864868 lr:0.0001761274150583756 tokens_per_second_per_gpu:2195.7236390560806 
Step 1874 | loss:2.2174291610717773 lr:0.00017610189434324298 tokens_per_second_per_gpu:2135.5287644534496 
Step 1875 | loss:2.204387664794922 lr:0.0001760763618451572 tokens_per_second_per_gpu:2160.159255468525 
Step 1876 | loss:2.183502674102783 lr:0.00017605081756807148 tokens_per_second_per_gpu:2109.056473349217 
Step 1877 | loss:2.2235140800476074 lr:0.0001760252615159409 tokens_per_second_per_gpu:2169.4191554844774 
Step 1878 | loss:2.1957225799560547 lr:0.0001759996936927224 tokens_per_second_per_gpu:2182.9211418352625 
Step 1879 | loss:2.1969053745269775 lr:0.00017597411410237454 tokens_per_second_per_gpu:2075.7278852712284 
Step 1880 | loss:2.227637767791748 lr:0.00017594852274885794 tokens_per_second_per_gpu:2197.851450324482 
Step 1881 | loss:2.2061827182769775 lr:0.00017592291963613492 tokens_per_second_per_gpu:2156.2753674896057 
Step 1882 | loss:2.188544988632202 lr:0.00017589730476816963 tokens_per_second_per_gpu:2157.844830566349 
Step 1883 | loss:2.2032341957092285 lr:0.00017587167814892807 tokens_per_second_per_gpu:2185.2065609952897 
Step 1884 | loss:2.2551803588867188 lr:0.000175846039782378 tokens_per_second_per_gpu:2174.41042366265 
Step 1885 | loss:2.270367383956909 lr:0.0001758203896724891 tokens_per_second_per_gpu:2189.5357779031046 
Step 1886 | loss:2.1903223991394043 lr:0.00017579472782323278 tokens_per_second_per_gpu:2194.11129634854 
Step 1887 | loss:2.2041497230529785 lr:0.0001757690542385823 tokens_per_second_per_gpu:2179.4243794887634 
Step 1888 | loss:2.238400936126709 lr:0.00017574336892251275 tokens_per_second_per_gpu:2136.1800829755603 
Step 1889 | loss:2.1881165504455566 lr:0.00017571767187900096 tokens_per_second_per_gpu:2198.5754026249288 
Step 1890 | loss:2.1776123046875 lr:0.00017569196311202571 tokens_per_second_per_gpu:2193.0936838496846 
Step 1891 | loss:2.2955000400543213 lr:0.00017566624262556747 tokens_per_second_per_gpu:2149.9777177928713 
Step 1892 | loss:2.193272352218628 lr:0.00017564051042360862 tokens_per_second_per_gpu:2185.4153693898543 
Step 1893 | loss:2.2002511024475098 lr:0.00017561476651013327 tokens_per_second_per_gpu:2137.941193302984 
Step 1894 | loss:2.252453565597534 lr:0.00017558901088912744 tokens_per_second_per_gpu:2187.949551274324 
Step 1895 | loss:2.233321189880371 lr:0.00017556324356457877 tokens_per_second_per_gpu:2124.7111430378663 
Step 1896 | loss:2.2086691856384277 lr:0.00017553746454047705 tokens_per_second_per_gpu:2156.771642700947 
Step 1897 | loss:2.218250274658203 lr:0.00017551167382081348 tokens_per_second_per_gpu:2191.532477419621 
Step 1898 | loss:2.2229180335998535 lr:0.00017548587140958142 tokens_per_second_per_gpu:2153.4188033450455 
Step 1899 | loss:2.2040600776672363 lr:0.0001754600573107758 tokens_per_second_per_gpu:2157.913083002679 
Step 1900 | loss:2.1807022094726562 lr:0.0001754342315283935 tokens_per_second_per_gpu:2195.588093371136 
Step 1901 | loss:2.223860740661621 lr:0.00017540839406643313 tokens_per_second_per_gpu:2187.1630071465574 
Step 1902 | loss:2.1877312660217285 lr:0.00017538254492889513 tokens_per_second_per_gpu:2128.1902365679744 
Step 1903 | loss:2.154169797897339 lr:0.00017535668411978179 tokens_per_second_per_gpu:2171.538686657841 
Step 1904 | loss:2.3186683654785156 lr:0.00017533081164309718 tokens_per_second_per_gpu:2193.173468788357 
Step 1905 | loss:2.199239492416382 lr:0.0001753049275028471 tokens_per_second_per_gpu:2195.0210178088323 
Step 1906 | loss:2.192676067352295 lr:0.00017527903170303928 tokens_per_second_per_gpu:2185.9805803695876 
Step 1907 | loss:2.1858391761779785 lr:0.00017525312424768318 tokens_per_second_per_gpu:2184.663008737322 
Step 1908 | loss:2.2174391746520996 lr:0.00017522720514079006 tokens_per_second_per_gpu:2186.7555067603976 
Step 1909 | loss:2.16536283493042 lr:0.00017520127438637307 tokens_per_second_per_gpu:2195.750298885489 
Step 1910 | loss:2.197871208190918 lr:0.00017517533198844708 tokens_per_second_per_gpu:2144.0438653792185 
Step 1911 | loss:2.2120704650878906 lr:0.0001751493779510288 tokens_per_second_per_gpu:2191.969798254 
Step 1912 | loss:2.2633724212646484 lr:0.00017512341227813666 tokens_per_second_per_gpu:2047.9889386181214 
Step 1913 | loss:2.177619457244873 lr:0.00017509743497379102 tokens_per_second_per_gpu:2122.843239708738 
Step 1914 | loss:2.1842446327209473 lr:0.00017507144604201393 tokens_per_second_per_gpu:2183.015287854809 
Step 1915 | loss:2.2467007637023926 lr:0.00017504544548682934 tokens_per_second_per_gpu:2159.889444153395 
Step 1916 | loss:2.2260570526123047 lr:0.00017501943331226291 tokens_per_second_per_gpu:2186.386009896947 
Step 1917 | loss:2.2156975269317627 lr:0.00017499340952234217 tokens_per_second_per_gpu:2082.9270254152907 
Step 1918 | loss:2.2085936069488525 lr:0.00017496737412109637 tokens_per_second_per_gpu:2188.9592173889296 
Step 1919 | loss:2.209401845932007 lr:0.00017494132711255665 tokens_per_second_per_gpu:2199.146168414477 
Step 1920 | loss:2.1693763732910156 lr:0.00017491526850075593 tokens_per_second_per_gpu:2191.493527715564 
Step 1921 | loss:2.171367645263672 lr:0.0001748891982897288 tokens_per_second_per_gpu:2107.133003657489 
Step 1922 | loss:2.167329788208008 lr:0.00017486311648351184 tokens_per_second_per_gpu:2142.029052214253 
Step 1923 | loss:2.1852927207946777 lr:0.00017483702308614327 tokens_per_second_per_gpu:2187.721702204288 
Step 1924 | loss:2.2480955123901367 lr:0.00017481091810166318 tokens_per_second_per_gpu:2182.98364821089 
Step 1925 | loss:2.154904365539551 lr:0.00017478480153411345 tokens_per_second_per_gpu:2159.455913662847 
Step 1926 | loss:2.1831748485565186 lr:0.00017475867338753774 tokens_per_second_per_gpu:2183.1314142980473 
Step 1927 | loss:2.1989517211914062 lr:0.00017473253366598148 tokens_per_second_per_gpu:2192.430734265292 
Step 1928 | loss:2.2323875427246094 lr:0.00017470638237349192 tokens_per_second_per_gpu:2108.556626782884 
Step 1929 | loss:2.1903085708618164 lr:0.00017468021951411812 tokens_per_second_per_gpu:2197.406054634506 
Step 1930 | loss:2.23258113861084 lr:0.0001746540450919109 tokens_per_second_per_gpu:2198.3608251827523 
Step 1931 | loss:2.280097007751465 lr:0.00017462785911092287 tokens_per_second_per_gpu:2157.0579475032278 
Step 1932 | loss:2.214822292327881 lr:0.00017460166157520847 tokens_per_second_per_gpu:2198.7317320606207 
Step 1933 | loss:2.2565720081329346 lr:0.00017457545248882386 tokens_per_second_per_gpu:2178.01003703242 
Step 1934 | loss:2.180541515350342 lr:0.00017454923185582704 tokens_per_second_per_gpu:2193.1868801914425 
Step 1935 | loss:2.204014778137207 lr:0.0001745229996802778 tokens_per_second_per_gpu:2048.4733800025706 
Step 1936 | loss:2.217531204223633 lr:0.00017449675596623764 tokens_per_second_per_gpu:2166.726469155606 
Step 1937 | loss:2.2417516708374023 lr:0.00017447050071777 tokens_per_second_per_gpu:2198.8340838758663 
Step 1938 | loss:2.1933979988098145 lr:0.00017444423393893997 tokens_per_second_per_gpu:2077.176121873834 
Step 1939 | loss:2.1734719276428223 lr:0.00017441795563381444 tokens_per_second_per_gpu:2143.5832391049485 
Step 1940 | loss:2.1764678955078125 lr:0.00017439166580646216 tokens_per_second_per_gpu:2196.7739751918584 
Step 1941 | loss:2.25030517578125 lr:0.00017436536446095358 tokens_per_second_per_gpu:2193.192658981922 
Step 1942 | loss:2.155644416809082 lr:0.000174339051601361 tokens_per_second_per_gpu:2185.3090464890415 
Step 1943 | loss:2.172738552093506 lr:0.00017431272723175844 tokens_per_second_per_gpu:2155.9094499461244 
Step 1944 | loss:2.2184958457946777 lr:0.00017428639135622177 tokens_per_second_per_gpu:2150.0123578310954 
Step 1945 | loss:2.2397572994232178 lr:0.00017426004397882858 tokens_per_second_per_gpu:2156.370774422697 
Step 1946 | loss:2.186526298522949 lr:0.0001742336851036583 tokens_per_second_per_gpu:2181.4605682564957 
Step 1947 | loss:2.230180263519287 lr:0.0001742073147347921 tokens_per_second_per_gpu:2122.126949424006 
Step 1948 | loss:2.2088093757629395 lr:0.00017418093287631292 tokens_per_second_per_gpu:2122.5292764095057 
Step 1949 | loss:2.1658225059509277 lr:0.00017415453953230548 tokens_per_second_per_gpu:2139.64561060977 
Step 1950 | loss:2.183988094329834 lr:0.00017412813470685633 tokens_per_second_per_gpu:2157.6994594551247 
Step 1951 | loss:2.1942930221557617 lr:0.0001741017184040538 tokens_per_second_per_gpu:2188.0479868449756 
Step 1952 | loss:2.2102532386779785 lr:0.00017407529062798784 tokens_per_second_per_gpu:2072.1921358635254 
Step 1953 | loss:2.213261127471924 lr:0.0001740488513827504 tokens_per_second_per_gpu:2100.6421718217616 
Step 1954 | loss:2.153825044631958 lr:0.00017402240067243506 tokens_per_second_per_gpu:2117.9438557710764 
Step 1955 | loss:2.270212411880493 lr:0.00017399593850113724 tokens_per_second_per_gpu:2136.426259099344 
Step 1956 | loss:2.1385931968688965 lr:0.0001739694648729541 tokens_per_second_per_gpu:2162.973934793896 
Step 1957 | loss:2.222510814666748 lr:0.00017394297979198456 tokens_per_second_per_gpu:2191.0713937557985 
Step 1958 | loss:2.1862480640411377 lr:0.0001739164832623294 tokens_per_second_per_gpu:2180.337629373114 
Step 1959 | loss:2.170264720916748 lr:0.00017388997528809105 tokens_per_second_per_gpu:2173.6984687543804 
Step 1960 | loss:2.263155937194824 lr:0.0001738634558733738 tokens_per_second_per_gpu:2145.8713434394313 
Step 1961 | loss:2.2240090370178223 lr:0.0001738369250222837 tokens_per_second_per_gpu:2186.581389046744 
Step 1962 | loss:2.2648072242736816 lr:0.00017381038273892854 tokens_per_second_per_gpu:2068.2928763593054 
Step 1963 | loss:2.1546740531921387 lr:0.00017378382902741787 tokens_per_second_per_gpu:2193.9511705023833 
Step 1964 | loss:2.2061452865600586 lr:0.00017375726389186306 tokens_per_second_per_gpu:2191.792463915775 
Step 1965 | loss:2.212379217147827 lr:0.00017373068733637722 tokens_per_second_per_gpu:2189.337008702949 
Step 1966 | loss:2.203101396560669 lr:0.00017370409936507525 tokens_per_second_per_gpu:2196.095081506241 
Step 1967 | loss:2.259812831878662 lr:0.0001736774999820738 tokens_per_second_per_gpu:2173.2444318069743 
Step 1968 | loss:2.2115588188171387 lr:0.00017365088919149124 tokens_per_second_per_gpu:2082.0161363010448 
Step 1969 | loss:2.164581298828125 lr:0.0001736242669974478 tokens_per_second_per_gpu:2171.460910186123 
Step 1970 | loss:2.1824636459350586 lr:0.0001735976334040654 tokens_per_second_per_gpu:2086.699407338343 
Step 1971 | loss:2.185075283050537 lr:0.00017357098841546775 tokens_per_second_per_gpu:2062.5407565570167 
Step 1972 | loss:2.2168421745300293 lr:0.00017354433203578038 tokens_per_second_per_gpu:2089.7425200665057 
Step 1973 | loss:2.2020320892333984 lr:0.00017351766426913046 tokens_per_second_per_gpu:2192.551764349145 
Step 1974 | loss:2.180030345916748 lr:0.00017349098511964704 tokens_per_second_per_gpu:2197.4926427358773 
Step 1975 | loss:2.1883325576782227 lr:0.00017346429459146086 tokens_per_second_per_gpu:2167.034795860392 
Step 1976 | loss:2.1741552352905273 lr:0.00017343759268870448 tokens_per_second_per_gpu:2115.604914953243 
Step 1977 | loss:2.161496639251709 lr:0.00017341087941551218 tokens_per_second_per_gpu:2155.9623352356716 
Step 1978 | loss:2.1920852661132812 lr:0.00017338415477601997 tokens_per_second_per_gpu:2191.0796184833694 
Step 1979 | loss:2.1787774562835693 lr:0.0001733574187743657 tokens_per_second_per_gpu:2173.562936182863 
Step 1980 | loss:2.173825263977051 lr:0.00017333067141468895 tokens_per_second_per_gpu:2184.567140040429 
Step 1981 | loss:2.14005708694458 lr:0.000173303912701131 tokens_per_second_per_gpu:2164.5143875528756 
Step 1982 | loss:2.134554862976074 lr:0.000173277142637835 tokens_per_second_per_gpu:2192.7362684126533 
Step 1983 | loss:2.157418727874756 lr:0.00017325036122894575 tokens_per_second_per_gpu:2186.2583126211325 
Step 1984 | loss:2.1833529472351074 lr:0.00017322356847860983 tokens_per_second_per_gpu:2145.002668919567 
Step 1985 | loss:2.1666922569274902 lr:0.00017319676439097562 tokens_per_second_per_gpu:2090.8615323348604 
Step 1986 | loss:2.187620162963867 lr:0.0001731699489701933 tokens_per_second_per_gpu:2191.441484937037 
Step 1987 | loss:2.1896138191223145 lr:0.00017314312222041457 tokens_per_second_per_gpu:2055.9243784364207 
Step 1988 | loss:2.202176332473755 lr:0.00017311628414579323 tokens_per_second_per_gpu:2164.834401793133 
Step 1989 | loss:2.126842498779297 lr:0.00017308943475048452 tokens_per_second_per_gpu:2177.006520467948 
Step 1990 | loss:2.221013069152832 lr:0.00017306257403864564 tokens_per_second_per_gpu:2159.638283637997 
Step 1991 | loss:2.1443352699279785 lr:0.00017303570201443545 tokens_per_second_per_gpu:2077.489195879665 
Step 1992 | loss:2.231299638748169 lr:0.00017300881868201456 tokens_per_second_per_gpu:2167.22003310777 
Step 1993 | loss:2.239771842956543 lr:0.00017298192404554538 tokens_per_second_per_gpu:2184.0503855921174 
Step 1994 | loss:2.226832389831543 lr:0.00017295501810919204 tokens_per_second_per_gpu:2162.7424630499736 
Step 1995 | loss:2.1811091899871826 lr:0.00017292810087712036 tokens_per_second_per_gpu:2094.7258495555916 
Step 1996 | loss:2.2222166061401367 lr:0.00017290117235349808 tokens_per_second_per_gpu:2162.99104579989 
Step 1997 | loss:2.221774101257324 lr:0.00017287423254249448 tokens_per_second_per_gpu:2153.42720594232 
Step 1998 | loss:2.166959285736084 lr:0.00017284728144828073 tokens_per_second_per_gpu:2184.77967988146 
Step 1999 | loss:2.191534996032715 lr:0.00017282031907502968 tokens_per_second_per_gpu:2195.274962402468 
Step 2000 | loss:2.1767234802246094 lr:0.00017279334542691596 tokens_per_second_per_gpu:2062.796402831377 
Step 2001 | loss:2.1881942749023438 lr:0.00017276636050811596 tokens_per_second_per_gpu:2211.0627874250813 
Step 2002 | loss:2.2071571350097656 lr:0.00017273936432280772 tokens_per_second_per_gpu:2197.810410619174 
Step 2003 | loss:2.2179369926452637 lr:0.00017271235687517117 tokens_per_second_per_gpu:2204.234572144818 
Step 2004 | loss:2.163933753967285 lr:0.0001726853381693879 tokens_per_second_per_gpu:2147.2770836404466 
Step 2005 | loss:2.212678909301758 lr:0.00017265830820964117 tokens_per_second_per_gpu:2165.7228489974077 
Step 2006 | loss:2.187743663787842 lr:0.00017263126700011616 tokens_per_second_per_gpu:2194.900781581894 
Step 2007 | loss:2.2144365310668945 lr:0.0001726042145449996 tokens_per_second_per_gpu:2182.476565702386 
Step 2008 | loss:2.1647229194641113 lr:0.00017257715084848018 tokens_per_second_per_gpu:2190.1252594625303 
Step 2009 | loss:2.210235595703125 lr:0.0001725500759147481 tokens_per_second_per_gpu:2194.408017078821 
Step 2010 | loss:2.234619379043579 lr:0.00017252298974799546 tokens_per_second_per_gpu:2186.159030732642 
Step 2011 | loss:2.125483989715576 lr:0.00017249589235241602 tokens_per_second_per_gpu:2111.3949418013676 
Step 2012 | loss:2.2635324001312256 lr:0.00017246878373220533 tokens_per_second_per_gpu:2151.635337938286 
Step 2013 | loss:2.2261881828308105 lr:0.0001724416638915606 tokens_per_second_per_gpu:2137.750074856856 
Step 2014 | loss:2.173881769180298 lr:0.00017241453283468088 tokens_per_second_per_gpu:2189.093475434902 
Step 2015 | loss:2.1882052421569824 lr:0.0001723873905657669 tokens_per_second_per_gpu:2158.8202882853993 
Step 2016 | loss:2.1400270462036133 lr:0.00017236023708902111 tokens_per_second_per_gpu:2139.3191492164833 
Step 2017 | loss:2.205352306365967 lr:0.00017233307240864773 tokens_per_second_per_gpu:2057.104114589379 
Step 2018 | loss:2.181814193725586 lr:0.0001723058965288527 tokens_per_second_per_gpu:2170.9829163326103 
Step 2019 | loss:2.240230083465576 lr:0.0001722787094538437 tokens_per_second_per_gpu:2189.0527630260076 
Step 2020 | loss:2.211334705352783 lr:0.00017225151118783013 tokens_per_second_per_gpu:2159.9881078287203 
Step 2021 | loss:2.2659871578216553 lr:0.00017222430173502318 tokens_per_second_per_gpu:2195.8372725448107 
Step 2022 | loss:2.2061939239501953 lr:0.00017219708109963565 tokens_per_second_per_gpu:2152.8246392119036 
Step 2023 | loss:2.1932406425476074 lr:0.0001721698492858822 tokens_per_second_per_gpu:2196.0895190426286 
Step 2024 | loss:2.1897735595703125 lr:0.00017214260629797913 tokens_per_second_per_gpu:2159.0680218447046 
Step 2025 | loss:2.193291664123535 lr:0.0001721153521401445 tokens_per_second_per_gpu:2185.915286242253 
Step 2026 | loss:2.237405776977539 lr:0.00017208808681659816 tokens_per_second_per_gpu:2189.148212706983 
Step 2027 | loss:2.2451229095458984 lr:0.0001720608103315616 tokens_per_second_per_gpu:2119.400948417343 
Step 2028 | loss:2.217641830444336 lr:0.00017203352268925807 tokens_per_second_per_gpu:2182.485586210446 
Step 2029 | loss:2.225104331970215 lr:0.00017200622389391254 tokens_per_second_per_gpu:2154.012011772371 
Step 2030 | loss:2.3074562549591064 lr:0.00017197891394975178 tokens_per_second_per_gpu:2162.2966497631187 
Step 2031 | loss:2.199772834777832 lr:0.00017195159286100413 tokens_per_second_per_gpu:2191.9055393025396 
Step 2032 | loss:2.2032766342163086 lr:0.00017192426063189983 tokens_per_second_per_gpu:2139.4896571079894 
Step 2033 | loss:2.2106363773345947 lr:0.0001718969172666707 tokens_per_second_per_gpu:2140.590156920294 
Step 2034 | loss:2.134995937347412 lr:0.0001718695627695504 tokens_per_second_per_gpu:2196.7917897460793 
Step 2035 | loss:2.2318503856658936 lr:0.0001718421971447742 tokens_per_second_per_gpu:2172.5862388622045 
Step 2036 | loss:2.1854398250579834 lr:0.00017181482039657926 tokens_per_second_per_gpu:2184.701919898701 
Step 2037 | loss:2.2518022060394287 lr:0.00017178743252920425 tokens_per_second_per_gpu:2123.265233362674 
Step 2038 | loss:2.200866937637329 lr:0.00017176003354688968 tokens_per_second_per_gpu:2172.632470249014 
Step 2039 | loss:2.127702474594116 lr:0.00017173262345387787 tokens_per_second_per_gpu:2155.4121716270256 
Step 2040 | loss:2.198850154876709 lr:0.00017170520225441262 tokens_per_second_per_gpu:2187.9961376690185 
Step 2041 | loss:2.2154030799865723 lr:0.00017167776995273968 tokens_per_second_per_gpu:2198.0103690184924 
Step 2042 | loss:2.2578048706054688 lr:0.0001716503265531064 tokens_per_second_per_gpu:2129.905269106678 
Step 2043 | loss:2.127178192138672 lr:0.0001716228720597619 tokens_per_second_per_gpu:2187.1105097997315 
Step 2044 | loss:2.15969181060791 lr:0.00017159540647695696 tokens_per_second_per_gpu:2189.895389045372 
Step 2045 | loss:2.1910829544067383 lr:0.00017156792980894416 tokens_per_second_per_gpu:2194.716030158539 
Step 2046 | loss:2.1574032306671143 lr:0.00017154044205997768 tokens_per_second_per_gpu:2197.070577690396 
Step 2047 | loss:2.139566421508789 lr:0.00017151294323431354 tokens_per_second_per_gpu:2141.9099060437766 
Step 2048 | loss:2.2256522178649902 lr:0.0001714854333362094 tokens_per_second_per_gpu:2167.4202084162303 
Step 2049 | loss:2.194148063659668 lr:0.00017145791236992461 tokens_per_second_per_gpu:2197.583994401326 
Step 2050 | loss:2.1541056632995605 lr:0.00017143038033972033 tokens_per_second_per_gpu:2179.4920346429835 
Step 2051 | loss:2.1433091163635254 lr:0.0001714028372498594 tokens_per_second_per_gpu:2168.9493057257714 
Step 2052 | loss:2.2159833908081055 lr:0.00017137528310460628 tokens_per_second_per_gpu:2166.296770093381 
Step 2053 | loss:2.196938991546631 lr:0.00017134771790822722 tokens_per_second_per_gpu:2156.8395160023397 
Step 2054 | loss:2.164586305618286 lr:0.00017132014166499026 tokens_per_second_per_gpu:2193.8809192468684 
Step 2055 | loss:2.191941261291504 lr:0.00017129255437916497 tokens_per_second_per_gpu:2103.0440237297107 
Step 2056 | loss:2.1570827960968018 lr:0.0001712649560550228 tokens_per_second_per_gpu:2104.293446508429 
Step 2057 | loss:2.1921048164367676 lr:0.00017123734669683677 tokens_per_second_per_gpu:2122.804165957073 
Step 2058 | loss:2.1722002029418945 lr:0.0001712097263088817 tokens_per_second_per_gpu:2188.656355664808 
Step 2059 | loss:2.1695125102996826 lr:0.0001711820948954341 tokens_per_second_per_gpu:2170.5739278862507 
Step 2060 | loss:2.197042465209961 lr:0.00017115445246077219 tokens_per_second_per_gpu:2133.351922436368 
Step 2061 | loss:2.2475099563598633 lr:0.00017112679900917579 tokens_per_second_per_gpu:2172.6300653700173 
Step 2062 | loss:2.1253340244293213 lr:0.0001710991345449266 tokens_per_second_per_gpu:2102.413624019285 
Step 2063 | loss:2.230680465698242 lr:0.00017107145907230796 tokens_per_second_per_gpu:2189.543676138824 
Step 2064 | loss:2.170393466949463 lr:0.00017104377259560488 tokens_per_second_per_gpu:2165.0270756580067 
Step 2065 | loss:2.17974853515625 lr:0.00017101607511910407 tokens_per_second_per_gpu:2139.30358491841 
Step 2066 | loss:2.2366766929626465 lr:0.000170988366647094 tokens_per_second_per_gpu:2194.8021359333825 
Step 2067 | loss:2.1454615592956543 lr:0.00017096064718386474 tokens_per_second_per_gpu:2194.352293218723 
Step 2068 | loss:2.1135454177856445 lr:0.0001709329167337082 tokens_per_second_per_gpu:2184.354722182693 
Step 2069 | loss:2.201314926147461 lr:0.00017090517530091788 tokens_per_second_per_gpu:2095.742168648211 
Step 2070 | loss:2.1200308799743652 lr:0.00017087742288978905 tokens_per_second_per_gpu:2171.39881254034 
Step 2071 | loss:2.2127456665039062 lr:0.00017084965950461866 tokens_per_second_per_gpu:2112.215048564336 
Step 2072 | loss:2.1630444526672363 lr:0.0001708218851497053 tokens_per_second_per_gpu:2146.673554809415 
Step 2073 | loss:2.2370359897613525 lr:0.00017079409982934934 tokens_per_second_per_gpu:2171.5470143308007 
Step 2074 | loss:2.0995144844055176 lr:0.00017076630354785283 tokens_per_second_per_gpu:2159.0891465908494 
Step 2075 | loss:2.2431411743164062 lr:0.0001707384963095195 tokens_per_second_per_gpu:2191.4964347517175 
Step 2076 | loss:2.2018775939941406 lr:0.00017071067811865476 tokens_per_second_per_gpu:2169.4647106457846 
Step 2077 | loss:2.20878267288208 lr:0.00017068284897956576 tokens_per_second_per_gpu:2196.8716217591177 
Step 2078 | loss:2.196005344390869 lr:0.00017065500889656127 tokens_per_second_per_gpu:2177.3315211296917 
Step 2079 | loss:2.2507083415985107 lr:0.00017062715787395186 tokens_per_second_per_gpu:2183.4799224447393 
Step 2080 | loss:2.2134056091308594 lr:0.0001705992959160497 tokens_per_second_per_gpu:2137.7514154002642 
Step 2081 | loss:2.2264444828033447 lr:0.00017057142302716872 tokens_per_second_per_gpu:2148.401408964968 
Step 2082 | loss:2.2010912895202637 lr:0.00017054353921162454 tokens_per_second_per_gpu:2195.905916987842 
Step 2083 | loss:2.183004379272461 lr:0.00017051564447373438 tokens_per_second_per_gpu:2148.0066251456833 
Step 2084 | loss:2.2678253650665283 lr:0.00017048773881781726 tokens_per_second_per_gpu:2135.4904891308342 
Step 2085 | loss:2.179046392440796 lr:0.00017045982224819385 tokens_per_second_per_gpu:2166.0591734692384 
Step 2086 | loss:2.183922290802002 lr:0.00017043189476918647 tokens_per_second_per_gpu:2163.851743599286 
Step 2087 | loss:2.2190520763397217 lr:0.00017040395638511923 tokens_per_second_per_gpu:2055.150614151849 
Step 2088 | loss:2.2364649772644043 lr:0.00017037600710031783 tokens_per_second_per_gpu:2168.9302033984163 
Step 2089 | loss:2.1843760013580322 lr:0.00017034804691910967 tokens_per_second_per_gpu:2185.10917981072 
Step 2090 | loss:2.2508978843688965 lr:0.0001703200758458239 tokens_per_second_per_gpu:2178.6460238669288 
Step 2091 | loss:2.10444974899292 lr:0.00017029209388479127 tokens_per_second_per_gpu:2176.842431777134 
Step 2092 | loss:2.2124085426330566 lr:0.00017026410104034433 tokens_per_second_per_gpu:2163.4086304851635 
Step 2093 | loss:2.128950834274292 lr:0.00017023609731681722 tokens_per_second_per_gpu:2174.764919830148 
Step 2094 | loss:2.21096134185791 lr:0.00017020808271854575 tokens_per_second_per_gpu:2181.9877036132248 
Step 2095 | loss:2.1310956478118896 lr:0.00017018005724986753 tokens_per_second_per_gpu:2172.036106938843 
Step 2096 | loss:2.23396635055542 lr:0.0001701520209151217 tokens_per_second_per_gpu:2184.6323888671886 
Step 2097 | loss:2.2214674949645996 lr:0.00017012397371864922 tokens_per_second_per_gpu:2183.1935228495386 
Step 2098 | loss:2.1945419311523438 lr:0.00017009591566479265 tokens_per_second_per_gpu:2184.097563749898 
Step 2099 | loss:2.2420971393585205 lr:0.00017006784675789623 tokens_per_second_per_gpu:2195.280762464195 
Step 2100 | loss:2.2110800743103027 lr:0.000170039767002306 tokens_per_second_per_gpu:2198.5244545566293 
Step 2101 | loss:2.168696165084839 lr:0.00017001167640236947 tokens_per_second_per_gpu:2143.7021026015695 
Step 2102 | loss:2.1982858180999756 lr:0.00016998357496243597 tokens_per_second_per_gpu:2152.943492325424 
Step 2103 | loss:2.122283458709717 lr:0.00016995546268685653 tokens_per_second_per_gpu:2164.048071625329 
Step 2104 | loss:2.2092227935791016 lr:0.0001699273395799838 tokens_per_second_per_gpu:2175.268438672339 
Step 2105 | loss:2.2047181129455566 lr:0.00016989920564617207 tokens_per_second_per_gpu:2138.6629037561916 
Step 2106 | loss:2.2274460792541504 lr:0.00016987106088977737 tokens_per_second_per_gpu:2111.985068300791 
Step 2107 | loss:2.182194232940674 lr:0.00016984290531515744 tokens_per_second_per_gpu:2169.5863796649987 
Step 2108 | loss:2.197878837585449 lr:0.00016981473892667154 tokens_per_second_per_gpu:2186.9623358350927 
Step 2109 | loss:2.1899757385253906 lr:0.00016978656172868083 tokens_per_second_per_gpu:2161.673656676949 
Step 2110 | loss:2.2123501300811768 lr:0.00016975837372554793 tokens_per_second_per_gpu:2137.4437767311088 
Step 2111 | loss:2.172851085662842 lr:0.00016973017492163725 tokens_per_second_per_gpu:2194.8404959651934 
Step 2112 | loss:2.154780864715576 lr:0.00016970196532131487 tokens_per_second_per_gpu:2162.1414354152653 
Step 2113 | loss:2.1813900470733643 lr:0.0001696737449289485 tokens_per_second_per_gpu:2054.9696969448455 
Step 2114 | loss:2.172574996948242 lr:0.00016964551374890754 tokens_per_second_per_gpu:2146.9470489819337 
Step 2115 | loss:2.1736507415771484 lr:0.00016961727178556305 tokens_per_second_per_gpu:2106.612772122681 
Step 2116 | loss:2.209258556365967 lr:0.0001695890190432878 tokens_per_second_per_gpu:2186.4909653662166 
Step 2117 | loss:2.2464492321014404 lr:0.00016956075552645615 tokens_per_second_per_gpu:2184.7175108923993 
Step 2118 | loss:2.1870946884155273 lr:0.0001695324812394442 tokens_per_second_per_gpu:2111.758406869546 
Step 2119 | loss:2.2359275817871094 lr:0.00016950419618662972 tokens_per_second_per_gpu:2155.036313298075 
Step 2120 | loss:2.19301438331604 lr:0.00016947590037239208 tokens_per_second_per_gpu:2186.4555505247763 
Step 2121 | loss:2.1732070446014404 lr:0.00016944759380111237 tokens_per_second_per_gpu:2116.852057014174 
Step 2122 | loss:2.132565975189209 lr:0.00016941927647717338 tokens_per_second_per_gpu:2146.105973118312 
Step 2123 | loss:2.1714491844177246 lr:0.00016939094840495941 tokens_per_second_per_gpu:2174.5512802531457 
Step 2124 | loss:2.2105374336242676 lr:0.00016936260958885663 tokens_per_second_per_gpu:2140.7704010362636 
Step 2125 | loss:2.1565823554992676 lr:0.00016933426003325276 tokens_per_second_per_gpu:2169.1313860305995 
Step 2126 | loss:2.1623098850250244 lr:0.00016930589974253714 tokens_per_second_per_gpu:2197.4054291287543 
Step 2127 | loss:2.2099480628967285 lr:0.0001692775287211009 tokens_per_second_per_gpu:2129.196482499396 
Step 2128 | loss:2.152311325073242 lr:0.0001692491469733367 tokens_per_second_per_gpu:2178.7944749216854 
Step 2129 | loss:2.1834139823913574 lr:0.00016922075450363897 tokens_per_second_per_gpu:2141.162148917566 
Step 2130 | loss:2.1399378776550293 lr:0.00016919235131640373 tokens_per_second_per_gpu:2121.1690161660904 
Step 2131 | loss:2.2737131118774414 lr:0.00016916393741602868 tokens_per_second_per_gpu:2199.5893197936207 
Step 2132 | loss:2.157472610473633 lr:0.0001691355128069132 tokens_per_second_per_gpu:2156.6334478975045 
Step 2133 | loss:2.1802568435668945 lr:0.00016910707749345826 tokens_per_second_per_gpu:2194.1649745409436 
Step 2134 | loss:2.1749954223632812 lr:0.0001690786314800666 tokens_per_second_per_gpu:2171.4369644562976 
Step 2135 | loss:2.1470813751220703 lr:0.0001690501747711425 tokens_per_second_per_gpu:2096.4815671843135 
Step 2136 | loss:2.1737217903137207 lr:0.000169021707371092 tokens_per_second_per_gpu:2137.5623281178173 
Step 2137 | loss:2.1694998741149902 lr:0.00016899322928432274 tokens_per_second_per_gpu:2187.1213446144516 
Step 2138 | loss:2.1758322715759277 lr:0.00016896474051524392 tokens_per_second_per_gpu:2167.7943235321222 
Step 2139 | loss:2.2002930641174316 lr:0.00016893624106826662 tokens_per_second_per_gpu:2196.641312273149 
Step 2140 | loss:2.184288740158081 lr:0.00016890773094780336 tokens_per_second_per_gpu:2168.4755807831516 
Step 2141 | loss:2.199575662612915 lr:0.00016887921015826845 tokens_per_second_per_gpu:2144.784838884303 
Step 2142 | loss:2.2515223026275635 lr:0.00016885067870407776 tokens_per_second_per_gpu:2172.4624981611023 
Step 2143 | loss:2.185957193374634 lr:0.00016882213658964888 tokens_per_second_per_gpu:2189.483334385768 
Step 2144 | loss:2.146437644958496 lr:0.00016879358381940103 tokens_per_second_per_gpu:2171.427701259986 
Step 2145 | loss:2.174947738647461 lr:0.00016876502039775502 tokens_per_second_per_gpu:2191.6314639595803 
Step 2146 | loss:2.0998106002807617 lr:0.00016873644632913343 tokens_per_second_per_gpu:2191.656549951624 
Step 2147 | loss:2.128798484802246 lr:0.0001687078616179604 tokens_per_second_per_gpu:2086.489773650409 
Step 2148 | loss:2.2092232704162598 lr:0.00016867926626866166 tokens_per_second_per_gpu:2097.7044166753017 
Step 2149 | loss:2.1758384704589844 lr:0.00016865066028566477 tokens_per_second_per_gpu:2039.5179163487785 
Step 2150 | loss:2.0968141555786133 lr:0.00016862204367339875 tokens_per_second_per_gpu:2195.6780013129746 
Step 2151 | loss:2.193901538848877 lr:0.00016859341643629441 tokens_per_second_per_gpu:2165.7880478211177 
Step 2152 | loss:2.1495604515075684 lr:0.00016856477857878413 tokens_per_second_per_gpu:2146.136288399845 
Step 2153 | loss:2.1973764896392822 lr:0.00016853613010530189 tokens_per_second_per_gpu:2141.390731053439 
Step 2154 | loss:2.1906559467315674 lr:0.00016850747102028346 tokens_per_second_per_gpu:2187.4790397538973 
Step 2155 | loss:2.131011486053467 lr:0.0001684788013281661 tokens_per_second_per_gpu:2157.990502912683 
Step 2156 | loss:2.219712257385254 lr:0.00016845012103338877 tokens_per_second_per_gpu:2142.0397334942336 
Step 2157 | loss:2.148000717163086 lr:0.0001684214301403921 tokens_per_second_per_gpu:2183.2245384824714 
Step 2158 | loss:2.141984462738037 lr:0.00016839272865361833 tokens_per_second_per_gpu:2172.5229339263915 
Step 2159 | loss:2.2149648666381836 lr:0.00016836401657751134 tokens_per_second_per_gpu:2159.1603025224663 
Step 2160 | loss:2.1751043796539307 lr:0.0001683352939165167 tokens_per_second_per_gpu:2151.8104785511205 
Step 2161 | loss:2.130770683288574 lr:0.00016830656067508151 tokens_per_second_per_gpu:2195.2654725445987 
Step 2162 | loss:2.15303373336792 lr:0.00016827781685765464 tokens_per_second_per_gpu:2190.6944739528053 
Step 2163 | loss:2.2814669609069824 lr:0.00016824906246868648 tokens_per_second_per_gpu:2146.6833910738774 
Step 2164 | loss:2.208832263946533 lr:0.0001682202975126291 tokens_per_second_per_gpu:2190.6625231066982 
Step 2165 | loss:2.217360496520996 lr:0.0001681915219939363 tokens_per_second_per_gpu:2164.472990189459 
Step 2166 | loss:2.1995396614074707 lr:0.00016816273591706334 tokens_per_second_per_gpu:2182.867053230958 
Step 2167 | loss:2.1057024002075195 lr:0.00016813393928646723 tokens_per_second_per_gpu:2115.1421560726485 
Step 2168 | loss:2.166897773742676 lr:0.00016810513210660662 tokens_per_second_per_gpu:2160.9155316215947 
Step 2169 | loss:2.25897216796875 lr:0.00016807631438194173 tokens_per_second_per_gpu:2171.4700052727912 
Step 2170 | loss:2.179168939590454 lr:0.00016804748611693447 tokens_per_second_per_gpu:2180.2945233084924 
Step 2171 | loss:2.238726854324341 lr:0.00016801864731604831 tokens_per_second_per_gpu:2187.6229405226973 
Step 2172 | loss:2.2347116470336914 lr:0.00016798979798374845 tokens_per_second_per_gpu:2194.370698016717 
Step 2173 | loss:2.25325345993042 lr:0.00016796093812450162 tokens_per_second_per_gpu:2159.8021802548697 
Step 2174 | loss:2.1889710426330566 lr:0.0001679320677427763 tokens_per_second_per_gpu:2183.139351718322 
Step 2175 | loss:2.224212169647217 lr:0.00016790318684304246 tokens_per_second_per_gpu:2189.846068948267 
Step 2176 | loss:2.2237162590026855 lr:0.0001678742954297718 tokens_per_second_per_gpu:2185.9123676769054 
Step 2177 | loss:2.2123613357543945 lr:0.0001678453935074376 tokens_per_second_per_gpu:2193.587975096481 
Step 2178 | loss:2.1559972763061523 lr:0.00016781648108051477 tokens_per_second_per_gpu:2148.8907611760696 
Step 2179 | loss:2.186723232269287 lr:0.00016778755815347992 tokens_per_second_per_gpu:2181.5878402971853 
Step 2180 | loss:2.186256170272827 lr:0.00016775862473081114 tokens_per_second_per_gpu:2184.5787967808615 
Step 2181 | loss:2.2021164894104004 lr:0.00016772968081698827 tokens_per_second_per_gpu:2173.0638402688096 
Step 2182 | loss:2.257678747177124 lr:0.00016770072641649275 tokens_per_second_per_gpu:2182.614657387723 
Step 2183 | loss:2.2101693153381348 lr:0.00016767176153380763 tokens_per_second_per_gpu:2183.6410995773554 
Step 2184 | loss:2.1686623096466064 lr:0.0001676427861734175 tokens_per_second_per_gpu:2192.821553173845 
Step 2185 | loss:2.189845561981201 lr:0.00016761380033980872 tokens_per_second_per_gpu:2140.5001561850595 
Step 2186 | loss:2.235506534576416 lr:0.0001675848040374692 tokens_per_second_per_gpu:2185.4285950472554 
Step 2187 | loss:2.175694704055786 lr:0.0001675557972708885 tokens_per_second_per_gpu:2171.1520616229614 
Step 2188 | loss:2.1804704666137695 lr:0.00016752678004455768 tokens_per_second_per_gpu:2145.5340462923336 
Step 2189 | loss:2.2431983947753906 lr:0.00016749775236296963 tokens_per_second_per_gpu:2180.8573195925323 
Step 2190 | loss:2.1937997341156006 lr:0.00016746871423061865 tokens_per_second_per_gpu:2152.137726210024 
Step 2191 | loss:2.1727981567382812 lr:0.0001674396656520008 tokens_per_second_per_gpu:2190.0535026914367 
Step 2192 | loss:2.2069783210754395 lr:0.00016741060663161373 tokens_per_second_per_gpu:2151.8881373047757 
Step 2193 | loss:2.1871371269226074 lr:0.0001673815371739566 tokens_per_second_per_gpu:2152.2094332763477 
Step 2194 | loss:2.2066798210144043 lr:0.00016735245728353036 tokens_per_second_per_gpu:2120.0554563697997 
Step 2195 | loss:2.2479090690612793 lr:0.00016732336696483743 tokens_per_second_per_gpu:2194.0672845053823 
Step 2196 | loss:2.1628456115722656 lr:0.0001672942662223819 tokens_per_second_per_gpu:2187.61548619593 
Step 2197 | loss:2.1738357543945312 lr:0.00016726515506066956 tokens_per_second_per_gpu:2152.331925648579 
Step 2198 | loss:2.2242202758789062 lr:0.00016723603348420762 tokens_per_second_per_gpu:2171.058230809342 
Step 2199 | loss:2.1494064331054688 lr:0.00016720690149750508 tokens_per_second_per_gpu:2140.976560793383 
Step 2200 | loss:2.173969030380249 lr:0.0001671777591050724 tokens_per_second_per_gpu:2155.826399859159 
Step 2201 | loss:2.1492960453033447 lr:0.00016714860631142185 tokens_per_second_per_gpu:2169.2400427380626 
Step 2202 | loss:2.189178943634033 lr:0.0001671194431210671 tokens_per_second_per_gpu:2163.2635816774678 
Step 2203 | loss:2.168593645095825 lr:0.0001670902695385236 tokens_per_second_per_gpu:2165.5696788619457 
Step 2204 | loss:2.1672091484069824 lr:0.00016706108556830825 tokens_per_second_per_gpu:2175.4181625321544 
Step 2205 | loss:2.1624808311462402 lr:0.0001670318912149397 tokens_per_second_per_gpu:2158.6873906197534 
Step 2206 | loss:2.1584503650665283 lr:0.00016700268648293815 tokens_per_second_per_gpu:2166.8903892530907 
Step 2207 | loss:2.082942008972168 lr:0.00016697347137682535 tokens_per_second_per_gpu:2108.2794520917314 
Step 2208 | loss:2.265099048614502 lr:0.00016694424590112477 tokens_per_second_per_gpu:2160.343141858235 
Step 2209 | loss:2.1814417839050293 lr:0.0001669150100603614 tokens_per_second_per_gpu:2097.6778622272395 
Step 2210 | loss:2.1369028091430664 lr:0.0001668857638590619 tokens_per_second_per_gpu:2193.605924689069 
Step 2211 | loss:2.221344232559204 lr:0.00016685650730175445 tokens_per_second_per_gpu:2184.271051764855 
Step 2212 | loss:2.1805872917175293 lr:0.00016682724039296888 tokens_per_second_per_gpu:2185.872020785583 
Step 2213 | loss:2.1949543952941895 lr:0.00016679796313723668 tokens_per_second_per_gpu:2156.98799187919 
Step 2214 | loss:2.229937791824341 lr:0.00016676867553909078 tokens_per_second_per_gpu:2183.4573179283143 
Step 2215 | loss:2.221184730529785 lr:0.00016673937760306595 tokens_per_second_per_gpu:2031.5145069199325 
Step 2216 | loss:2.1593713760375977 lr:0.0001667100693336983 tokens_per_second_per_gpu:2102.792875987245 
Step 2217 | loss:2.205331325531006 lr:0.00016668075073552574 tokens_per_second_per_gpu:2055.168685801832 
Step 2218 | loss:2.212188959121704 lr:0.00016665142181308771 tokens_per_second_per_gpu:2158.600120554398 
Step 2219 | loss:2.2221155166625977 lr:0.00016662208257092523 tokens_per_second_per_gpu:2151.7703794665617 
Step 2220 | loss:2.2220864295959473 lr:0.0001665927330135809 tokens_per_second_per_gpu:2095.4826695857155 
Step 2221 | loss:2.184823989868164 lr:0.00016656337314559897 tokens_per_second_per_gpu:2133.8898297653523 
Step 2222 | loss:2.210427761077881 lr:0.00016653400297152532 tokens_per_second_per_gpu:2172.534182356614 
Step 2223 | loss:2.1721837520599365 lr:0.00016650462249590727 tokens_per_second_per_gpu:2156.7592306738534 
Step 2224 | loss:2.2028086185455322 lr:0.0001664752317232939 tokens_per_second_per_gpu:2181.1044784369647 
Step 2225 | loss:2.1845102310180664 lr:0.0001664458306582358 tokens_per_second_per_gpu:2135.9106225985784 
Step 2226 | loss:2.2092278003692627 lr:0.0001664164193052852 tokens_per_second_per_gpu:2180.022054131364 
Step 2227 | loss:2.1204543113708496 lr:0.00016638699766899587 tokens_per_second_per_gpu:2092.7768842214045 
Step 2228 | loss:2.1765918731689453 lr:0.00016635756575392324 tokens_per_second_per_gpu:2098.2803666934797 
Step 2229 | loss:2.2434229850769043 lr:0.00016632812356462423 tokens_per_second_per_gpu:2146.4338627892735 
Step 2230 | loss:2.187720775604248 lr:0.00016629867110565745 tokens_per_second_per_gpu:2092.188443921492 
Step 2231 | loss:2.2998757362365723 lr:0.00016626920838158307 tokens_per_second_per_gpu:2147.2805247997676 
Step 2232 | loss:2.2164814472198486 lr:0.00016623973539696283 tokens_per_second_per_gpu:2192.773324799729 
Step 2233 | loss:2.14752459526062 lr:0.00016621025215636002 tokens_per_second_per_gpu:2187.5384806565467 
Step 2234 | loss:2.1969122886657715 lr:0.00016618075866433967 tokens_per_second_per_gpu:2146.7722808796325 
Step 2235 | loss:2.191451072692871 lr:0.00016615125492546823 tokens_per_second_per_gpu:2187.432152848722 
Step 2236 | loss:2.185321569442749 lr:0.00016612174094431377 tokens_per_second_per_gpu:2179.2827997456984 
Step 2237 | loss:2.234804391860962 lr:0.00016609221672544603 tokens_per_second_per_gpu:2143.487997653027 
Step 2238 | loss:2.1532645225524902 lr:0.0001660626822734363 tokens_per_second_per_gpu:2152.3309100304473 
Step 2239 | loss:2.184483051300049 lr:0.00016603313759285738 tokens_per_second_per_gpu:2151.1960100877263 
Step 2240 | loss:2.132065534591675 lr:0.00016600358268828376 tokens_per_second_per_gpu:2115.677633586092 
Step 2241 | loss:2.2267050743103027 lr:0.00016597401756429138 tokens_per_second_per_gpu:2125.5637507250462 
Step 2242 | loss:2.2321784496307373 lr:0.00016594444222545798 tokens_per_second_per_gpu:2168.502079886294 
Step 2243 | loss:2.169131278991699 lr:0.00016591485667636263 tokens_per_second_per_gpu:2178.7747253427333 
Step 2244 | loss:2.1624550819396973 lr:0.00016588526092158615 tokens_per_second_per_gpu:2191.4532491626132 
Step 2245 | loss:2.1866493225097656 lr:0.0001658556549657109 tokens_per_second_per_gpu:2139.903628742998 
Step 2246 | loss:2.1652302742004395 lr:0.00016582603881332077 tokens_per_second_per_gpu:2151.3303860274773 
Step 2247 | loss:2.1861934661865234 lr:0.0001657964124690013 tokens_per_second_per_gpu:2135.5018356413802 
Step 2248 | loss:2.1275744438171387 lr:0.00016576677593733953 tokens_per_second_per_gpu:2122.1011126329395 
Step 2249 | loss:2.172440528869629 lr:0.00016573712922292417 tokens_per_second_per_gpu:2190.1711868504717 
Step 2250 | loss:2.1270225048065186 lr:0.0001657074723303454 tokens_per_second_per_gpu:2151.09949457028 
Step 2251 | loss:2.173886299133301 lr:0.00016567780526419512 tokens_per_second_per_gpu:2136.1971034270987 
Step 2252 | loss:2.1768059730529785 lr:0.00016564812802906666 tokens_per_second_per_gpu:2115.922663406542 
Step 2253 | loss:2.1397414207458496 lr:0.00016561844062955498 tokens_per_second_per_gpu:2188.0213197595763 
Step 2254 | loss:2.1920628547668457 lr:0.00016558874307025668 tokens_per_second_per_gpu:2113.539566015201 
Step 2255 | loss:2.159989833831787 lr:0.00016555903535576976 tokens_per_second_per_gpu:2161.697245588781 
Step 2256 | loss:2.170227289199829 lr:0.00016552931749069403 tokens_per_second_per_gpu:2186.453433684112 
Step 2257 | loss:2.2309818267822266 lr:0.00016549958947963066 tokens_per_second_per_gpu:2138.1657206338145 
Step 2258 | loss:2.1164023876190186 lr:0.00016546985132718248 tokens_per_second_per_gpu:2188.9033825325705 
Step 2259 | loss:2.0805611610412598 lr:0.00016544010303795394 tokens_per_second_per_gpu:2192.238067476374 
Step 2260 | loss:2.202082633972168 lr:0.00016541034461655096 tokens_per_second_per_gpu:2129.4390547210332 
Step 2261 | loss:2.1534485816955566 lr:0.00016538057606758108 tokens_per_second_per_gpu:2162.645703524513 
Step 2262 | loss:2.1860666275024414 lr:0.00016535079739565342 tokens_per_second_per_gpu:2093.114883536525 
Step 2263 | loss:2.1826300621032715 lr:0.00016532100860537863 tokens_per_second_per_gpu:2181.6957988293366 
Step 2264 | loss:2.1747584342956543 lr:0.00016529120970136893 tokens_per_second_per_gpu:2187.728415310554 
Step 2265 | loss:2.175534725189209 lr:0.0001652614006882382 tokens_per_second_per_gpu:2091.245824016349 
Step 2266 | loss:2.1631813049316406 lr:0.0001652315815706017 tokens_per_second_per_gpu:2157.673805867602 
Step 2267 | loss:2.211315155029297 lr:0.00016520175235307645 tokens_per_second_per_gpu:2169.753069063824 
Step 2268 | loss:2.1510932445526123 lr:0.00016517191304028087 tokens_per_second_per_gpu:2171.35641579743 
Step 2269 | loss:2.14536452293396 lr:0.0001651420636368351 tokens_per_second_per_gpu:2136.7487145842792 
Step 2270 | loss:2.1864876747131348 lr:0.00016511220414736072 tokens_per_second_per_gpu:2136.151588656315 
Step 2271 | loss:2.1843037605285645 lr:0.0001650823345764809 tokens_per_second_per_gpu:2118.092447477388 
Step 2272 | loss:2.1164159774780273 lr:0.00016505245492882042 tokens_per_second_per_gpu:2168.000622849812 
Step 2273 | loss:2.1798391342163086 lr:0.00016502256520900551 tokens_per_second_per_gpu:2136.253150797217 
Step 2274 | loss:2.194758653640747 lr:0.00016499266542166412 tokens_per_second_per_gpu:2178.823541788416 
Step 2275 | loss:2.1812596321105957 lr:0.00016496275557142565 tokens_per_second_per_gpu:2173.1078843105597 
Step 2276 | loss:2.223165512084961 lr:0.00016493283566292104 tokens_per_second_per_gpu:2140.108453538203 
Step 2277 | loss:2.2228775024414062 lr:0.00016490290570078287 tokens_per_second_per_gpu:2194.9126836529995 
Step 2278 | loss:2.1839897632598877 lr:0.00016487296568964524 tokens_per_second_per_gpu:2156.885083833657 
Step 2279 | loss:2.1936020851135254 lr:0.00016484301563414374 tokens_per_second_per_gpu:2187.391089062104 
Step 2280 | loss:2.2067651748657227 lr:0.00016481305553891563 tokens_per_second_per_gpu:2172.86671959591 
Step 2281 | loss:2.235234260559082 lr:0.00016478308540859965 tokens_per_second_per_gpu:2149.897513462192 
Step 2282 | loss:2.15413236618042 lr:0.00016475310524783612 tokens_per_second_per_gpu:2186.283470068485 
Step 2283 | loss:2.1944892406463623 lr:0.00016472311506126689 tokens_per_second_per_gpu:2158.8467585179924 
Step 2284 | loss:2.1768550872802734 lr:0.0001646931148535354 tokens_per_second_per_gpu:2103.730544042598 
Step 2285 | loss:2.177769660949707 lr:0.00016466310462928663 tokens_per_second_per_gpu:2169.3790649721586 
Step 2286 | loss:2.2407660484313965 lr:0.00016463308439316706 tokens_per_second_per_gpu:2148.805497311918 
Step 2287 | loss:2.142393112182617 lr:0.00016460305414982477 tokens_per_second_per_gpu:2084.3895815604205 
Step 2288 | loss:2.1257526874542236 lr:0.00016457301390390943 tokens_per_second_per_gpu:2165.7146522451835 
Step 2289 | loss:2.157825231552124 lr:0.00016454296366007217 tokens_per_second_per_gpu:2081.506298530694 
Step 2290 | loss:2.1138381958007812 lr:0.00016451290342296574 tokens_per_second_per_gpu:2111.8615867873714 
Step 2291 | loss:2.1910581588745117 lr:0.00016448283319724433 tokens_per_second_per_gpu:2095.945203352999 
Step 2292 | loss:2.175065517425537 lr:0.00016445275298756378 tokens_per_second_per_gpu:2095.3201661032176 
Step 2293 | loss:2.1570639610290527 lr:0.00016442266279858151 tokens_per_second_per_gpu:2191.736563087208 
Step 2294 | loss:2.190924644470215 lr:0.0001643925626349564 tokens_per_second_per_gpu:2193.913050407954 
Step 2295 | loss:2.1394219398498535 lr:0.00016436245250134882 tokens_per_second_per_gpu:2032.908574221843 
Step 2296 | loss:2.173783779144287 lr:0.00016433233240242085 tokens_per_second_per_gpu:2162.1741252604565 
Step 2297 | loss:2.126919984817505 lr:0.00016430220234283597 tokens_per_second_per_gpu:2189.7439985661645 
Step 2298 | loss:2.2408676147460938 lr:0.0001642720623272593 tokens_per_second_per_gpu:2121.2813162946077 
Step 2299 | loss:2.173799991607666 lr:0.0001642419123603574 tokens_per_second_per_gpu:2092.1564829095405 
Step 2300 | loss:2.191737174987793 lr:0.0001642117524467985 tokens_per_second_per_gpu:2139.9278518999545 
Step 2301 | loss:2.1857166290283203 lr:0.00016418158259125218 tokens_per_second_per_gpu:2030.4043198484608 
Step 2302 | loss:2.149689197540283 lr:0.00016415140279838982 tokens_per_second_per_gpu:2152.3844956585117 
Step 2303 | loss:2.163503885269165 lr:0.0001641212130728841 tokens_per_second_per_gpu:2146.5639695211967 
Step 2304 | loss:2.147794723510742 lr:0.00016409101341940938 tokens_per_second_per_gpu:2156.0086653813037 
Step 2305 | loss:2.1935033798217773 lr:0.00016406080384264148 tokens_per_second_per_gpu:2179.7176407287734 
Step 2306 | loss:2.171814441680908 lr:0.00016403058434725782 tokens_per_second_per_gpu:2156.2913523564107 
Step 2307 | loss:2.172706365585327 lr:0.00016400035493793728 tokens_per_second_per_gpu:2150.0217406613856 
Step 2308 | loss:2.1994919776916504 lr:0.00016397011561936035 tokens_per_second_per_gpu:2152.7731886685556 
Step 2309 | loss:2.1718454360961914 lr:0.00016393986639620903 tokens_per_second_per_gpu:2143.713126207411 
Step 2310 | loss:2.1301584243774414 lr:0.00016390960727316682 tokens_per_second_per_gpu:2118.2283852011187 
Step 2311 | loss:2.2073264122009277 lr:0.00016387933825491878 tokens_per_second_per_gpu:2145.4726491926453 
Step 2312 | loss:2.177285671234131 lr:0.0001638490593461515 tokens_per_second_per_gpu:2188.002644795274 
Step 2313 | loss:2.180075168609619 lr:0.00016381877055155316 tokens_per_second_per_gpu:2191.634289139473 
Step 2314 | loss:2.210503578186035 lr:0.00016378847187581332 tokens_per_second_per_gpu:2191.612135184767 
Step 2315 | loss:2.181386947631836 lr:0.00016375816332362322 tokens_per_second_per_gpu:2156.975605253612 
Step 2316 | loss:2.1906557083129883 lr:0.00016372784489967557 tokens_per_second_per_gpu:2126.6995479615316 
Step 2317 | loss:2.131446361541748 lr:0.00016369751660866454 tokens_per_second_per_gpu:2183.3918548432157 
Step 2318 | loss:2.1339569091796875 lr:0.00016366717845528602 tokens_per_second_per_gpu:2177.2430167521625 
Step 2319 | loss:2.15090274810791 lr:0.0001636368304442372 tokens_per_second_per_gpu:2183.625625041652 
Step 2320 | loss:2.1904335021972656 lr:0.00016360647258021696 tokens_per_second_per_gpu:2124.9878346912737 
Step 2321 | loss:2.2263827323913574 lr:0.00016357610486792562 tokens_per_second_per_gpu:2167.944067305694 
Step 2322 | loss:2.174686908721924 lr:0.0001635457273120651 tokens_per_second_per_gpu:2172.038779523764 
Step 2323 | loss:2.189138174057007 lr:0.00016351533991733872 tokens_per_second_per_gpu:2158.4340773747854 
Step 2324 | loss:2.2078135013580322 lr:0.00016348494268845145 tokens_per_second_per_gpu:2187.1591301188055 
Step 2325 | loss:2.1703617572784424 lr:0.00016345453563010968 tokens_per_second_per_gpu:2174.9671852998626 
Step 2326 | loss:2.1752617359161377 lr:0.00016342411874702142 tokens_per_second_per_gpu:2168.6862834185904 
Step 2327 | loss:2.204699993133545 lr:0.00016339369204389616 tokens_per_second_per_gpu:2137.1818605117755 
Step 2328 | loss:2.1360158920288086 lr:0.00016336325552544488 tokens_per_second_per_gpu:2186.4610481204118 
Step 2329 | loss:2.1803786754608154 lr:0.00016333280919638015 tokens_per_second_per_gpu:2125.7494459266263 
Step 2330 | loss:2.213332176208496 lr:0.00016330235306141595 tokens_per_second_per_gpu:2122.964424649051 
Step 2331 | loss:2.1158900260925293 lr:0.00016327188712526787 tokens_per_second_per_gpu:2175.630953311455 
Step 2332 | loss:2.181023120880127 lr:0.000163241411392653 tokens_per_second_per_gpu:2146.2181168233783 
Step 2333 | loss:2.2045936584472656 lr:0.0001632109258682899 tokens_per_second_per_gpu:2102.94501593657 
Step 2334 | loss:2.2031266689300537 lr:0.00016318043055689872 tokens_per_second_per_gpu:2191.3179423964916 
Step 2335 | loss:2.217508316040039 lr:0.0001631499254632011 tokens_per_second_per_gpu:2167.4094806648473 
Step 2336 | loss:2.222116470336914 lr:0.00016311941059192012 tokens_per_second_per_gpu:2112.85850701788 
Step 2337 | loss:2.168184280395508 lr:0.0001630888859477805 tokens_per_second_per_gpu:2088.226106463754 
Step 2338 | loss:2.1447336673736572 lr:0.0001630583515355084 tokens_per_second_per_gpu:2133.392541685177 
Step 2339 | loss:2.1887078285217285 lr:0.00016302780735983147 tokens_per_second_per_gpu:2190.3399690188844 
Step 2340 | loss:2.1656832695007324 lr:0.00016299725342547894 tokens_per_second_per_gpu:2159.973762919637 
Step 2341 | loss:2.1603012084960938 lr:0.00016296668973718144 tokens_per_second_per_gpu:2132.0636987578937 
Step 2342 | loss:2.1865711212158203 lr:0.0001629361162996713 tokens_per_second_per_gpu:2118.3984197302552 
Step 2343 | loss:2.119903564453125 lr:0.00016290553311768216 tokens_per_second_per_gpu:2186.157973274604 
Step 2344 | loss:2.181135654449463 lr:0.00016287494019594928 tokens_per_second_per_gpu:2071.483396072467 
Step 2345 | loss:2.1074085235595703 lr:0.00016284433753920943 tokens_per_second_per_gpu:2105.355916456505 
Step 2346 | loss:2.1444759368896484 lr:0.00016281372515220078 tokens_per_second_per_gpu:2144.855894890715 
Step 2347 | loss:2.23281192779541 lr:0.00016278310303966315 tokens_per_second_per_gpu:2199.28296848211 
Step 2348 | loss:2.1836748123168945 lr:0.00016275247120633779 tokens_per_second_per_gpu:2197.9481130325753 
Step 2349 | loss:2.1603586673736572 lr:0.00016272182965696742 tokens_per_second_per_gpu:2192.888032862437 
Step 2350 | loss:2.1826024055480957 lr:0.0001626911783962964 tokens_per_second_per_gpu:2119.955917344612 
Step 2351 | loss:2.1482467651367188 lr:0.00016266051742907042 tokens_per_second_per_gpu:2180.837174194632 
Step 2352 | loss:2.2784929275512695 lr:0.00016262984676003678 tokens_per_second_per_gpu:2170.2502630393456 
Step 2353 | loss:2.115436553955078 lr:0.0001625991663939443 tokens_per_second_per_gpu:2180.581299609036 
Step 2354 | loss:2.2484140396118164 lr:0.0001625684763355432 tokens_per_second_per_gpu:2183.0682705873596 
Step 2355 | loss:2.1742537021636963 lr:0.0001625377765895853 tokens_per_second_per_gpu:2179.6874532655766 
Step 2356 | loss:2.1444807052612305 lr:0.00016250706716082388 tokens_per_second_per_gpu:2141.779781209658 
Step 2357 | loss:2.1868772506713867 lr:0.0001624763480540137 tokens_per_second_per_gpu:2160.0715195686857 
Step 2358 | loss:2.15496826171875 lr:0.00016244561927391103 tokens_per_second_per_gpu:2132.894915209228 
Step 2359 | loss:2.192671060562134 lr:0.00016241488082527366 tokens_per_second_per_gpu:2192.4410529705224 
Step 2360 | loss:2.203979015350342 lr:0.0001623841327128609 tokens_per_second_per_gpu:2173.5695272355956 
Step 2361 | loss:2.2036800384521484 lr:0.0001623533749414335 tokens_per_second_per_gpu:2164.1753446119787 
Step 2362 | loss:2.1616058349609375 lr:0.00016232260751575367 tokens_per_second_per_gpu:2176.949301924551 
Step 2363 | loss:2.1496639251708984 lr:0.0001622918304405852 tokens_per_second_per_gpu:2187.885595182914 
Step 2364 | loss:2.1377925872802734 lr:0.00016226104372069338 tokens_per_second_per_gpu:2039.189099128525 
Step 2365 | loss:2.1367673873901367 lr:0.0001622302473608449 tokens_per_second_per_gpu:2185.7608783051855 
Step 2366 | loss:2.1600465774536133 lr:0.00016219944136580807 tokens_per_second_per_gpu:2176.7461982503414 
Step 2367 | loss:2.1306912899017334 lr:0.00016216862574035257 tokens_per_second_per_gpu:2091.0840599664625 
Step 2368 | loss:2.180436372756958 lr:0.00016213780048924962 tokens_per_second_per_gpu:2154.6986326008273 
Step 2369 | loss:2.130310535430908 lr:0.00016210696561727196 tokens_per_second_per_gpu:2189.4783303842487 
Step 2370 | loss:2.1741669178009033 lr:0.00016207612112919376 tokens_per_second_per_gpu:2173.9773783425335 
Step 2371 | loss:2.0939488410949707 lr:0.00016204526702979076 tokens_per_second_per_gpu:2187.361178903646 
Step 2372 | loss:2.1460494995117188 lr:0.0001620144033238401 tokens_per_second_per_gpu:2193.3226555660885 
Step 2373 | loss:2.137211799621582 lr:0.00016198353001612047 tokens_per_second_per_gpu:2147.4729256851947 
Step 2374 | loss:2.168961763381958 lr:0.000161952647111412 tokens_per_second_per_gpu:2165.3735630180095 
Step 2375 | loss:2.107569694519043 lr:0.00016192175461449633 tokens_per_second_per_gpu:2125.029588983025 
Step 2376 | loss:2.1562647819519043 lr:0.00016189085253015656 tokens_per_second_per_gpu:2161.261403239916 
Step 2377 | loss:2.2417800426483154 lr:0.0001618599408631774 tokens_per_second_per_gpu:2194.428444888111 
Step 2378 | loss:2.1509244441986084 lr:0.00016182901961834484 tokens_per_second_per_gpu:2159.554737436218 
Step 2379 | loss:2.1746621131896973 lr:0.00016179808880044654 tokens_per_second_per_gpu:2138.188747118916 
Step 2380 | loss:2.208921432495117 lr:0.00016176714841427146 tokens_per_second_per_gpu:2190.767968640282 
Step 2381 | loss:2.1656200885772705 lr:0.0001617361984646102 tokens_per_second_per_gpu:2168.1261438692177 
Step 2382 | loss:2.174687623977661 lr:0.0001617052389562548 tokens_per_second_per_gpu:2124.6231421663265 
Step 2383 | loss:2.201023578643799 lr:0.0001616742698939987 tokens_per_second_per_gpu:2121.1363713240266 
Step 2384 | loss:2.127108573913574 lr:0.0001616432912826369 tokens_per_second_per_gpu:2191.1431728722177 
Step 2385 | loss:2.16829776763916 lr:0.00016161230312696588 tokens_per_second_per_gpu:2189.2965315896818 
Step 2386 | loss:2.144876480102539 lr:0.00016158130543178357 tokens_per_second_per_gpu:2162.746797897053 
Step 2387 | loss:2.153810501098633 lr:0.00016155029820188937 tokens_per_second_per_gpu:2134.878762924177 
Step 2388 | loss:2.133599281311035 lr:0.00016151928144208418 tokens_per_second_per_gpu:2187.9112341882696 
Step 2389 | loss:2.1722464561462402 lr:0.00016148825515717032 tokens_per_second_per_gpu:2173.0422925049506 
Step 2390 | loss:2.174835681915283 lr:0.00016145721935195172 tokens_per_second_per_gpu:2140.2481220579266 
Step 2391 | loss:2.160201072692871 lr:0.00016142617403123365 tokens_per_second_per_gpu:2190.362273302399 
Step 2392 | loss:2.124466896057129 lr:0.00016139511919982283 tokens_per_second_per_gpu:2159.9979022467737 
Step 2393 | loss:2.1013898849487305 lr:0.0001613640548625276 tokens_per_second_per_gpu:2123.6892268988986 
Step 2394 | loss:2.1814849376678467 lr:0.0001613329810241577 tokens_per_second_per_gpu:2157.5613137508026 
Step 2395 | loss:2.169342517852783 lr:0.00016130189768952423 tokens_per_second_per_gpu:2183.7874129122097 
Step 2396 | loss:2.1010241508483887 lr:0.00016127080486343998 tokens_per_second_per_gpu:2163.7724665395785 
Step 2397 | loss:2.1700692176818848 lr:0.00016123970255071902 tokens_per_second_per_gpu:2132.4996461623077 
Step 2398 | loss:2.1763076782226562 lr:0.00016120859075617703 tokens_per_second_per_gpu:2181.5377728302747 
Step 2399 | loss:2.219736337661743 lr:0.000161177469484631 tokens_per_second_per_gpu:2191.9168128738143 
Step 2400 | loss:2.194612503051758 lr:0.00016114633874089954 tokens_per_second_per_gpu:2188.8339638603006 
Step 2401 | loss:2.144162893295288 lr:0.00016111519852980263 tokens_per_second_per_gpu:2191.454993131571 
Step 2402 | loss:2.1469035148620605 lr:0.00016108404885616174 tokens_per_second_per_gpu:2103.3297643721885 
Step 2403 | loss:2.1216378211975098 lr:0.00016105288972479987 tokens_per_second_per_gpu:2158.2447806043533 
Step 2404 | loss:2.163983106613159 lr:0.00016102172114054137 tokens_per_second_per_gpu:2130.770416088871 
Step 2405 | loss:2.151036262512207 lr:0.00016099054310821215 tokens_per_second_per_gpu:2180.5357957033584 
Step 2406 | loss:2.2144012451171875 lr:0.0001609593556326395 tokens_per_second_per_gpu:2186.6033209600923 
Step 2407 | loss:2.1891369819641113 lr:0.00016092815871865228 tokens_per_second_per_gpu:2097.9487418528465 
Step 2408 | loss:2.1843953132629395 lr:0.00016089695237108068 tokens_per_second_per_gpu:2183.115415456997 
Step 2409 | loss:2.163851737976074 lr:0.0001608657365947565 tokens_per_second_per_gpu:2146.4726910775244 
Step 2410 | loss:2.0718631744384766 lr:0.0001608345113945128 tokens_per_second_per_gpu:2188.4542197311866 
Step 2411 | loss:2.1401376724243164 lr:0.0001608032767751843 tokens_per_second_per_gpu:2176.5789940220066 
Step 2412 | loss:2.1852221488952637 lr:0.0001607720327416071 tokens_per_second_per_gpu:2181.8297749370245 
Step 2413 | loss:2.1495461463928223 lr:0.00016074077929861876 tokens_per_second_per_gpu:2147.9462931976927 
Step 2414 | loss:2.1861422061920166 lr:0.00016070951645105822 tokens_per_second_per_gpu:2187.561992273704 
Step 2415 | loss:2.123380184173584 lr:0.00016067824420376602 tokens_per_second_per_gpu:2119.38980223339 
Step 2416 | loss:2.199004888534546 lr:0.00016064696256158406 tokens_per_second_per_gpu:2123.8170279588694 
Step 2417 | loss:2.1601433753967285 lr:0.00016061567152935572 tokens_per_second_per_gpu:2109.6599981521817 
Step 2418 | loss:2.127951145172119 lr:0.0001605843711119258 tokens_per_second_per_gpu:2152.486811063684 
Step 2419 | loss:2.170482635498047 lr:0.0001605530613141406 tokens_per_second_per_gpu:2190.878441406917 
Step 2420 | loss:2.09085750579834 lr:0.00016052174214084786 tokens_per_second_per_gpu:2184.6555058702565 
Step 2421 | loss:2.1598384380340576 lr:0.00016049041359689675 tokens_per_second_per_gpu:2147.8013857192755 
Step 2422 | loss:2.135399341583252 lr:0.00016045907568713798 tokens_per_second_per_gpu:2144.885199233243 
Step 2423 | loss:2.1393885612487793 lr:0.00016042772841642355 tokens_per_second_per_gpu:2190.539451317509 
Step 2424 | loss:2.112299919128418 lr:0.00016039637178960704 tokens_per_second_per_gpu:2193.0936320286155 
Step 2425 | loss:2.211338520050049 lr:0.00016036500581154343 tokens_per_second_per_gpu:2164.455571474367 
Step 2426 | loss:2.197187900543213 lr:0.00016033363048708913 tokens_per_second_per_gpu:2174.6989482834215 
Step 2427 | loss:2.1497700214385986 lr:0.0001603022458211021 tokens_per_second_per_gpu:2047.9993544243716 
Step 2428 | loss:2.1727511882781982 lr:0.00016027085181844156 tokens_per_second_per_gpu:2163.3571572215387 
Step 2429 | loss:2.1748929023742676 lr:0.00016023944848396834 tokens_per_second_per_gpu:2161.148829780717 
Step 2430 | loss:2.1422476768493652 lr:0.00016020803582254467 tokens_per_second_per_gpu:2162.073040233729 
Step 2431 | loss:2.139230251312256 lr:0.0001601766138390342 tokens_per_second_per_gpu:2187.386182578146 
Step 2432 | loss:2.1003258228302 lr:0.000160145182538302 tokens_per_second_per_gpu:2163.677927518068 
Step 2433 | loss:2.133270740509033 lr:0.00016011374192521468 tokens_per_second_per_gpu:2191.0436252338154 
Step 2434 | loss:2.169994354248047 lr:0.00016008229200464022 tokens_per_second_per_gpu:2130.017555527389 
Step 2435 | loss:2.179656982421875 lr:0.00016005083278144798 tokens_per_second_per_gpu:2151.52636274916 
Step 2436 | loss:2.2320709228515625 lr:0.00016001936426050892 tokens_per_second_per_gpu:2164.599614503247 
Step 2437 | loss:2.166940212249756 lr:0.00015998788644669532 tokens_per_second_per_gpu:2168.386762686017 
Step 2438 | loss:2.1453118324279785 lr:0.0001599563993448809 tokens_per_second_per_gpu:2183.417401281292 
Step 2439 | loss:2.1746840476989746 lr:0.00015992490295994088 tokens_per_second_per_gpu:2196.1545885095466 
Step 2440 | loss:2.110544443130493 lr:0.00015989339729675188 tokens_per_second_per_gpu:2145.7043220523356 
Step 2441 | loss:2.1602110862731934 lr:0.00015986188236019196 tokens_per_second_per_gpu:2183.919458372965 
Step 2442 | loss:2.1999802589416504 lr:0.00015983035815514063 tokens_per_second_per_gpu:2192.3616553920024 
Step 2443 | loss:2.17217755317688 lr:0.00015979882468647878 tokens_per_second_per_gpu:2180.548504956009 
Step 2444 | loss:2.2133681774139404 lr:0.00015976728195908884 tokens_per_second_per_gpu:2193.4967481645685 
Step 2445 | loss:2.1827940940856934 lr:0.00015973572997785452 tokens_per_second_per_gpu:2171.0101678897 
Step 2446 | loss:2.1469409465789795 lr:0.00015970416874766118 tokens_per_second_per_gpu:2111.4710626219944 
Step 2447 | loss:2.1792526245117188 lr:0.0001596725982733954 tokens_per_second_per_gpu:2135.3878225775234 
Step 2448 | loss:2.1645419597625732 lr:0.00015964101855994527 tokens_per_second_per_gpu:2186.6659116171154 
Step 2449 | loss:2.236593008041382 lr:0.00015960942961220034 tokens_per_second_per_gpu:2176.6402164902047 
Step 2450 | loss:2.170114517211914 lr:0.0001595778314350516 tokens_per_second_per_gpu:2174.120067084518 
Step 2451 | loss:2.177029609680176 lr:0.00015954622403339136 tokens_per_second_per_gpu:2175.138216978665 
Step 2452 | loss:2.179043769836426 lr:0.00015951460741211353 tokens_per_second_per_gpu:2179.269310675476 
Step 2453 | loss:2.1721043586730957 lr:0.00015948298157611324 tokens_per_second_per_gpu:2137.675019618272 
Step 2454 | loss:2.1588830947875977 lr:0.00015945134653028728 tokens_per_second_per_gpu:2134.3591135377305 
Step 2455 | loss:2.1841397285461426 lr:0.00015941970227953365 tokens_per_second_per_gpu:2101.736769637983 
Step 2456 | loss:2.1606240272521973 lr:0.00015938804882875189 tokens_per_second_per_gpu:2178.176574684276 
Step 2457 | loss:2.2111902236938477 lr:0.00015935638618284296 tokens_per_second_per_gpu:2190.488529803415 
Step 2458 | loss:2.239348888397217 lr:0.00015932471434670925 tokens_per_second_per_gpu:2113.6917779739824 
Step 2459 | loss:2.163060426712036 lr:0.00015929303332525452 tokens_per_second_per_gpu:2147.6822164863024 
Step 2460 | loss:2.16633939743042 lr:0.00015926134312338396 tokens_per_second_per_gpu:2157.146629182039 
Step 2461 | loss:2.178260326385498 lr:0.00015922964374600425 tokens_per_second_per_gpu:2187.1947476562686 
Step 2462 | loss:2.162147283554077 lr:0.0001591979351980234 tokens_per_second_per_gpu:2144.6693888772925 
Step 2463 | loss:2.187623977661133 lr:0.00015916621748435095 tokens_per_second_per_gpu:2195.6469783685434 
Step 2464 | loss:2.1356725692749023 lr:0.00015913449060989774 tokens_per_second_per_gpu:2186.133134116008 
Step 2465 | loss:2.199104070663452 lr:0.00015910275457957612 tokens_per_second_per_gpu:2077.056766921284 
Step 2466 | loss:2.162297487258911 lr:0.00015907100939829976 tokens_per_second_per_gpu:2184.941277004972 
Step 2467 | loss:2.1687216758728027 lr:0.00015903925507098387 tokens_per_second_per_gpu:2146.0241117230494 
Step 2468 | loss:2.170114517211914 lr:0.00015900749160254499 tokens_per_second_per_gpu:2107.4441191500377 
Step 2469 | loss:2.1559081077575684 lr:0.00015897571899790107 tokens_per_second_per_gpu:2191.3468363447764 
Step 2470 | loss:2.234196186065674 lr:0.00015894393726197155 tokens_per_second_per_gpu:2132.2855944974426 
Step 2471 | loss:2.182105541229248 lr:0.0001589121463996772 tokens_per_second_per_gpu:2184.78800383005 
Step 2472 | loss:2.153489828109741 lr:0.00015888034641594026 tokens_per_second_per_gpu:2175.509936637557 
Step 2473 | loss:2.1419105529785156 lr:0.00015884853731568436 tokens_per_second_per_gpu:2134.6718696326625 
Step 2474 | loss:2.185086250305176 lr:0.00015881671910383455 tokens_per_second_per_gpu:2181.8658671356143 
Step 2475 | loss:2.111504077911377 lr:0.00015878489178531723 tokens_per_second_per_gpu:2180.838323378001 
Step 2476 | loss:2.1484732627868652 lr:0.00015875305536506039 tokens_per_second_per_gpu:2172.502583036183 
Step 2477 | loss:2.2132818698883057 lr:0.00015872120984799314 tokens_per_second_per_gpu:2179.733649395991 
Step 2478 | loss:2.1921424865722656 lr:0.0001586893552390463 tokens_per_second_per_gpu:2192.2846386398583 
Step 2479 | loss:2.177076816558838 lr:0.0001586574915431519 tokens_per_second_per_gpu:2164.4559238057345 
Step 2480 | loss:2.1230340003967285 lr:0.00015862561876524338 tokens_per_second_per_gpu:2162.2741738583154 
Step 2481 | loss:2.118405818939209 lr:0.00015859373691025575 tokens_per_second_per_gpu:2123.811150342879 
Step 2482 | loss:2.1663284301757812 lr:0.00015856184598312528 tokens_per_second_per_gpu:2167.6537155761457 
Step 2483 | loss:2.1407055854797363 lr:0.00015852994598878963 tokens_per_second_per_gpu:2166.003991740122 
Step 2484 | loss:2.106480598449707 lr:0.00015849803693218802 tokens_per_second_per_gpu:2121.2175362322128 
Step 2485 | loss:2.164865255355835 lr:0.00015846611881826088 tokens_per_second_per_gpu:2183.0338771970646 
Step 2486 | loss:2.1990091800689697 lr:0.00015843419165195014 tokens_per_second_per_gpu:2159.026738168981 
Step 2487 | loss:2.1300430297851562 lr:0.0001584022554381992 tokens_per_second_per_gpu:2167.7859854591743 
Step 2488 | loss:2.135897397994995 lr:0.00015837031018195268 tokens_per_second_per_gpu:2159.126263587046 
Step 2489 | loss:2.1309738159179688 lr:0.00015833835588815678 tokens_per_second_per_gpu:2175.974927890789 
Step 2490 | loss:2.1912314891815186 lr:0.000158306392561759 tokens_per_second_per_gpu:2174.9467264933255 
Step 2491 | loss:2.210264205932617 lr:0.00015827442020770825 tokens_per_second_per_gpu:2189.8193738022046 
Step 2492 | loss:2.206150531768799 lr:0.0001582424388309549 tokens_per_second_per_gpu:2163.32133230555 
Step 2493 | loss:2.1666617393493652 lr:0.0001582104484364506 tokens_per_second_per_gpu:2162.714146893463 
Step 2494 | loss:2.1874117851257324 lr:0.00015817844902914847 tokens_per_second_per_gpu:2132.739634256167 
Step 2495 | loss:2.168706178665161 lr:0.0001581464406140031 tokens_per_second_per_gpu:2188.2209174769846 
Step 2496 | loss:2.1775259971618652 lr:0.00015811442319597026 tokens_per_second_per_gpu:2196.9360235868708 
Step 2497 | loss:2.126455307006836 lr:0.0001580823967800074 tokens_per_second_per_gpu:2101.565516128493 
Step 2498 | loss:2.181993007659912 lr:0.00015805036137107309 tokens_per_second_per_gpu:2188.7327512703346 
Step 2499 | loss:2.1969690322875977 lr:0.00015801831697412748 tokens_per_second_per_gpu:2188.981184691226 
Step 2500 | loss:2.108114242553711 lr:0.000157986263594132 tokens_per_second_per_gpu:2147.396516325094 
Step 2501 | loss:2.2009506225585938 lr:0.00015795420123604952 tokens_per_second_per_gpu:2183.3675329128855 
Step 2502 | loss:2.1797842979431152 lr:0.00015792212990484438 tokens_per_second_per_gpu:2183.8168021236875 
Step 2503 | loss:2.1436612606048584 lr:0.00015789004960548212 tokens_per_second_per_gpu:2117.2049060388385 
Step 2504 | loss:2.2375733852386475 lr:0.0001578579603429298 tokens_per_second_per_gpu:2186.5899818526987 
Step 2505 | loss:2.181525707244873 lr:0.00015782586212215586 tokens_per_second_per_gpu:2155.547004268392 
Step 2506 | loss:2.1728692054748535 lr:0.00015779375494813015 tokens_per_second_per_gpu:2190.955400001776 
Step 2507 | loss:2.131385326385498 lr:0.00015776163882582372 tokens_per_second_per_gpu:2170.8681832161487 
Step 2508 | loss:2.126485824584961 lr:0.00015772951376020932 tokens_per_second_per_gpu:2197.169137965949 
Step 2509 | loss:2.170524835586548 lr:0.00015769737975626083 tokens_per_second_per_gpu:2187.0719685342615 
Step 2510 | loss:2.1303157806396484 lr:0.0001576652368189536 tokens_per_second_per_gpu:2132.2347769621124 
Step 2511 | loss:2.123504638671875 lr:0.00015763308495326438 tokens_per_second_per_gpu:2174.0366514072116 
Step 2512 | loss:2.2226452827453613 lr:0.00015760092416417125 tokens_per_second_per_gpu:2140.5993839921575 
Step 2513 | loss:2.114985942840576 lr:0.00015756875445665375 tokens_per_second_per_gpu:2164.986054453716 
Step 2514 | loss:2.1589183807373047 lr:0.00015753657583569275 tokens_per_second_per_gpu:2144.299706412943 
Step 2515 | loss:2.1929733753204346 lr:0.00015750438830627048 tokens_per_second_per_gpu:2114.8570293781545 
Step 2516 | loss:2.1686110496520996 lr:0.0001574721918733706 tokens_per_second_per_gpu:2157.151030968415 
Step 2517 | loss:2.147298812866211 lr:0.00015743998654197812 tokens_per_second_per_gpu:2148.536685369305 
Step 2518 | loss:2.1373209953308105 lr:0.0001574077723170794 tokens_per_second_per_gpu:2190.096430010514 
Step 2519 | loss:2.1941237449645996 lr:0.00015737554920366227 tokens_per_second_per_gpu:2176.61589143885 
Step 2520 | loss:2.1360411643981934 lr:0.00015734331720671584 tokens_per_second_per_gpu:2101.0555777564446 
Step 2521 | loss:2.2289514541625977 lr:0.00015731107633123063 tokens_per_second_per_gpu:2137.1621577828155 
Step 2522 | loss:2.170147657394409 lr:0.00015727882658219856 tokens_per_second_per_gpu:2198.931038573826 
Step 2523 | loss:2.233652353286743 lr:0.00015724656796461286 tokens_per_second_per_gpu:2189.7185900088416 
Step 2524 | loss:2.1947309970855713 lr:0.0001572143004834682 tokens_per_second_per_gpu:2150.000996180133 
Step 2525 | loss:2.1321935653686523 lr:0.00015718202414376057 tokens_per_second_per_gpu:2199.769209814602 
Step 2526 | loss:2.218017101287842 lr:0.0001571497389504874 tokens_per_second_per_gpu:2192.027287223158 
Step 2527 | loss:2.1706080436706543 lr:0.0001571174449086474 tokens_per_second_per_gpu:2166.972554712049 
Step 2528 | loss:2.1603407859802246 lr:0.00015708514202324075 tokens_per_second_per_gpu:2189.5399406171987 
Step 2529 | loss:2.136969566345215 lr:0.0001570528302992689 tokens_per_second_per_gpu:2146.068496766189 
Step 2530 | loss:2.1155245304107666 lr:0.00015702050974173473 tokens_per_second_per_gpu:2164.4451087295433 
Step 2531 | loss:2.1216092109680176 lr:0.00015698818035564247 tokens_per_second_per_gpu:2174.506557606082 
Step 2532 | loss:2.1369433403015137 lr:0.00015695584214599776 tokens_per_second_per_gpu:2094.5697994730463 
Step 2533 | loss:2.1774654388427734 lr:0.00015692349511780749 tokens_per_second_per_gpu:2144.0834724599617 
Step 2534 | loss:2.1421594619750977 lr:0.00015689113927608005 tokens_per_second_per_gpu:2151.7597325284673 
Step 2535 | loss:2.075688123703003 lr:0.00015685877462582514 tokens_per_second_per_gpu:2159.55360383776 
Step 2536 | loss:2.132178783416748 lr:0.00015682640117205377 tokens_per_second_per_gpu:2158.2367645403933 
Step 2537 | loss:2.135446071624756 lr:0.00015679401891977837 tokens_per_second_per_gpu:2184.6697527292085 
Step 2538 | loss:2.1203384399414062 lr:0.00015676162787401282 tokens_per_second_per_gpu:2076.83510306078 
Step 2539 | loss:2.1526386737823486 lr:0.00015672922803977213 tokens_per_second_per_gpu:2191.205302959254 
Step 2540 | loss:2.1583118438720703 lr:0.00015669681942207287 tokens_per_second_per_gpu:2134.238711134548 
Step 2541 | loss:2.155569553375244 lr:0.00015666440202593296 tokens_per_second_per_gpu:2137.9371094643175 
Step 2542 | loss:2.2001919746398926 lr:0.00015663197585637155 tokens_per_second_per_gpu:2194.436946518155 
Step 2543 | loss:2.174274444580078 lr:0.00015659954091840924 tokens_per_second_per_gpu:2171.1702279118635 
Step 2544 | loss:2.1707844734191895 lr:0.00015656709721706798 tokens_per_second_per_gpu:2184.979134753186 
Step 2545 | loss:2.2036991119384766 lr:0.00015653464475737109 tokens_per_second_per_gpu:2106.046852679613 
Step 2546 | loss:2.158489227294922 lr:0.00015650218354434323 tokens_per_second_per_gpu:2133.1537629317872 
Step 2547 | loss:2.1561336517333984 lr:0.00015646971358301037 tokens_per_second_per_gpu:2120.0546689887633 
Step 2548 | loss:2.1430282592773438 lr:0.0001564372348783999 tokens_per_second_per_gpu:2157.831793666825 
Step 2549 | loss:2.1556105613708496 lr:0.00015640474743554053 tokens_per_second_per_gpu:2124.551260992917 
Step 2550 | loss:2.203030586242676 lr:0.00015637225125946232 tokens_per_second_per_gpu:2165.1297030534115 
Step 2551 | loss:2.202085018157959 lr:0.00015633974635519674 tokens_per_second_per_gpu:2174.251972095745 
Step 2552 | loss:2.1152260303497314 lr:0.00015630723272777654 tokens_per_second_per_gpu:2179.3195988964703 
Step 2553 | loss:2.141805648803711 lr:0.0001562747103822358 tokens_per_second_per_gpu:2152.7533333735973 
Step 2554 | loss:2.21513032913208 lr:0.0001562421793236101 tokens_per_second_per_gpu:2185.945978277532 
Step 2555 | loss:2.1243159770965576 lr:0.00015620963955693617 tokens_per_second_per_gpu:2178.987355020409 
Step 2556 | loss:2.136418104171753 lr:0.00015617709108725224 tokens_per_second_per_gpu:2140.374511448556 
Step 2557 | loss:2.180629253387451 lr:0.0001561445339195978 tokens_per_second_per_gpu:2148.836396413547 
Step 2558 | loss:2.220248222351074 lr:0.00015611196805901368 tokens_per_second_per_gpu:2195.1916492979003 
Step 2559 | loss:2.1479005813598633 lr:0.0001560793935105422 tokens_per_second_per_gpu:2158.795558562309 
Step 2560 | loss:2.184311866760254 lr:0.00015604681027922684 tokens_per_second_per_gpu:2177.7823149502697 
Step 2561 | loss:2.158742904663086 lr:0.00015601421837011252 tokens_per_second_per_gpu:2171.7542757154797 
Step 2562 | loss:2.117443084716797 lr:0.00015598161778824552 tokens_per_second_per_gpu:2149.835876797314 
Step 2563 | loss:2.1443369388580322 lr:0.00015594900853867333 tokens_per_second_per_gpu:2152.9426441462647 
Step 2564 | loss:2.2094993591308594 lr:0.000155916390626445 tokens_per_second_per_gpu:2198.624018095585 
Step 2565 | loss:2.1574559211730957 lr:0.00015588376405661076 tokens_per_second_per_gpu:2196.277058050062 
Step 2566 | loss:2.14841628074646 lr:0.0001558511288342222 tokens_per_second_per_gpu:2120.754677042967 
Step 2567 | loss:2.2072362899780273 lr:0.00015581848496433226 tokens_per_second_per_gpu:2169.9505494380633 
Step 2568 | loss:2.177105665206909 lr:0.00015578583245199533 tokens_per_second_per_gpu:2187.785225722785 
Step 2569 | loss:2.1345138549804688 lr:0.0001557531713022669 tokens_per_second_per_gpu:2016.04498413962 
Step 2570 | loss:2.1267480850219727 lr:0.0001557205015202041 tokens_per_second_per_gpu:2185.56271361854 
Step 2571 | loss:2.1194138526916504 lr:0.00015568782311086503 tokens_per_second_per_gpu:2196.958186368384 
Step 2572 | loss:2.176347017288208 lr:0.00015565513607930954 tokens_per_second_per_gpu:2182.087645075736 
Step 2573 | loss:2.200218915939331 lr:0.00015562244043059844 tokens_per_second_per_gpu:2148.0282825194818 
Step 2574 | loss:2.1080706119537354 lr:0.00015558973616979413 tokens_per_second_per_gpu:2188.3097779189584 
Step 2575 | loss:2.1771254539489746 lr:0.00015555702330196023 tokens_per_second_per_gpu:2110.0898915472267 
Step 2576 | loss:2.0843024253845215 lr:0.0001555243018321617 tokens_per_second_per_gpu:2166.3323011238826 
Step 2577 | loss:2.2028450965881348 lr:0.0001554915717654649 tokens_per_second_per_gpu:2154.2692488325556 
Step 2578 | loss:2.1899492740631104 lr:0.00015545883310693741 tokens_per_second_per_gpu:2110.3546719407823 
Step 2579 | loss:2.210094928741455 lr:0.0001554260858616482 tokens_per_second_per_gpu:2192.4065484946686 
Step 2580 | loss:2.137000322341919 lr:0.00015539333003466757 tokens_per_second_per_gpu:2182.2888245212935 
Step 2581 | loss:2.1374025344848633 lr:0.0001553605656310672 tokens_per_second_per_gpu:2162.1541952464936 
Step 2582 | loss:2.1678850650787354 lr:0.00015532779265591999 tokens_per_second_per_gpu:2165.467077685576 
Step 2583 | loss:2.214165210723877 lr:0.00015529501111430025 tokens_per_second_per_gpu:2169.849850839494 
Step 2584 | loss:2.1485986709594727 lr:0.00015526222101128355 tokens_per_second_per_gpu:2200.59123005012 
Step 2585 | loss:2.174561023712158 lr:0.00015522942235194682 tokens_per_second_per_gpu:2150.1648891107716 
Step 2586 | loss:2.156987190246582 lr:0.0001551966151413684 tokens_per_second_per_gpu:2144.448713409743 
Step 2587 | loss:2.1732687950134277 lr:0.00015516379938462782 tokens_per_second_per_gpu:2198.5537093839503 
Step 2588 | loss:2.209157705307007 lr:0.00015513097508680594 tokens_per_second_per_gpu:2183.3229261994056 
Step 2589 | loss:2.1663403511047363 lr:0.00015509814225298505 tokens_per_second_per_gpu:2184.9545153453855 
Step 2590 | loss:2.119800567626953 lr:0.0001550653008882487 tokens_per_second_per_gpu:2183.1031622145792 
Step 2591 | loss:2.1573548316955566 lr:0.0001550324509976817 tokens_per_second_per_gpu:2141.8981909229656 
Step 2592 | loss:2.134178400039673 lr:0.0001549995925863703 tokens_per_second_per_gpu:2159.012126605022 
Step 2593 | loss:2.0874176025390625 lr:0.000154966725659402 tokens_per_second_per_gpu:2175.431254934003 
Step 2594 | loss:2.1709980964660645 lr:0.00015493385022186562 tokens_per_second_per_gpu:2192.6481417993314 
Step 2595 | loss:2.14024019241333 lr:0.00015490096627885128 tokens_per_second_per_gpu:2139.4321135407877 
Step 2596 | loss:2.1494874954223633 lr:0.0001548680738354505 tokens_per_second_per_gpu:2196.164994360555 
Step 2597 | loss:2.209376096725464 lr:0.00015483517289675603 tokens_per_second_per_gpu:2195.7648707890335 
Step 2598 | loss:2.1279654502868652 lr:0.00015480226346786192 tokens_per_second_per_gpu:2125.447647375284 
Step 2599 | loss:2.0975637435913086 lr:0.00015476934555386365 tokens_per_second_per_gpu:2153.162108436379 
Step 2600 | loss:2.1952733993530273 lr:0.0001547364191598579 tokens_per_second_per_gpu:2196.937262737606 
Step 2601 | loss:2.2103378772735596 lr:0.00015470348429094273 tokens_per_second_per_gpu:2138.1849761682784 
Step 2602 | loss:2.120699644088745 lr:0.00015467054095221744 tokens_per_second_per_gpu:2177.8443022593024 
Step 2603 | loss:2.155552864074707 lr:0.00015463758914878274 tokens_per_second_per_gpu:2158.6012110311644 
Step 2604 | loss:2.098489284515381 lr:0.0001546046288857406 tokens_per_second_per_gpu:2184.3480126424242 
Step 2605 | loss:2.069134473800659 lr:0.00015457166016819428 tokens_per_second_per_gpu:2187.723805146386 
Step 2606 | loss:2.1500492095947266 lr:0.00015453868300124838 tokens_per_second_per_gpu:2115.3749299489036 
Step 2607 | loss:2.1724720001220703 lr:0.00015450569739000876 tokens_per_second_per_gpu:2188.8826924654654 
Step 2608 | loss:2.1371545791625977 lr:0.00015447270333958265 tokens_per_second_per_gpu:2186.2777085517523 
Step 2609 | loss:2.1134564876556396 lr:0.0001544397008550786 tokens_per_second_per_gpu:2178.2810735291837 
Step 2610 | loss:2.117095470428467 lr:0.00015440668994160637 tokens_per_second_per_gpu:2191.1580488627897 
Step 2611 | loss:2.192600965499878 lr:0.0001543736706042771 tokens_per_second_per_gpu:2174.4683167478825 
Step 2612 | loss:2.193467140197754 lr:0.0001543406428482032 tokens_per_second_per_gpu:2133.866593944743 
Step 2613 | loss:2.1563405990600586 lr:0.00015430760667849844 tokens_per_second_per_gpu:2187.3671931810086 
Step 2614 | loss:2.096762180328369 lr:0.00015427456210027782 tokens_per_second_per_gpu:2178.252827674103 
Step 2615 | loss:2.1534476280212402 lr:0.0001542415091186577 tokens_per_second_per_gpu:2195.954001735694 
Step 2616 | loss:2.101327419281006 lr:0.00015420844773875568 tokens_per_second_per_gpu:2129.2137792405547 
Step 2617 | loss:2.1664977073669434 lr:0.0001541753779656907 tokens_per_second_per_gpu:2162.3554185685657 
Step 2618 | loss:2.1881914138793945 lr:0.00015414229980458303 tokens_per_second_per_gpu:2152.638585548794 
Step 2619 | loss:2.145728349685669 lr:0.00015410921326055422 tokens_per_second_per_gpu:2098.800931353123 
Step 2620 | loss:2.1195390224456787 lr:0.000154076118338727 tokens_per_second_per_gpu:2121.0598870350423 
Step 2621 | loss:2.1624755859375 lr:0.0001540430150442256 tokens_per_second_per_gpu:2174.1703348402107 
Step 2622 | loss:2.2306442260742188 lr:0.0001540099033821754 tokens_per_second_per_gpu:2159.168053440818 
Step 2623 | loss:2.1817240715026855 lr:0.00015397678335770314 tokens_per_second_per_gpu:2160.589675223932 
Step 2624 | loss:2.1460342407226562 lr:0.00015394365497593682 tokens_per_second_per_gpu:2190.007761902841 
Step 2625 | loss:2.183149814605713 lr:0.0001539105182420057 tokens_per_second_per_gpu:2142.347170927323 
Step 2626 | loss:2.111361503601074 lr:0.00015387737316104052 tokens_per_second_per_gpu:2160.393508784429 
Step 2627 | loss:2.1327569484710693 lr:0.00015384421973817304 tokens_per_second_per_gpu:2117.960149577851 
Step 2628 | loss:2.157931327819824 lr:0.00015381105797853653 tokens_per_second_per_gpu:2187.0848148729415 
Step 2629 | loss:2.2154359817504883 lr:0.0001537778878872654 tokens_per_second_per_gpu:2164.071639121947 
Step 2630 | loss:2.1707630157470703 lr:0.00015374470946949548 tokens_per_second_per_gpu:2191.192048302286 
Step 2631 | loss:2.144144296646118 lr:0.0001537115227303638 tokens_per_second_per_gpu:2129.562510198348 
Step 2632 | loss:2.176673412322998 lr:0.0001536783276750087 tokens_per_second_per_gpu:2103.2502064607384 
Step 2633 | loss:2.138899564743042 lr:0.00015364512430856984 tokens_per_second_per_gpu:2189.9456930925676 
Step 2634 | loss:2.1374220848083496 lr:0.0001536119126361881 tokens_per_second_per_gpu:2175.3023632153013 
Step 2635 | loss:2.1680054664611816 lr:0.0001535786926630057 tokens_per_second_per_gpu:2108.795020216011 
Step 2636 | loss:2.1605758666992188 lr:0.0001535454643941661 tokens_per_second_per_gpu:2178.6563566327886 
Step 2637 | loss:2.1255040168762207 lr:0.00015351222783481416 tokens_per_second_per_gpu:2166.2788893082284 
Step 2638 | loss:2.135709285736084 lr:0.0001534789829900959 tokens_per_second_per_gpu:2144.9177173727953 
Step 2639 | loss:2.1610403060913086 lr:0.0001534457298651586 tokens_per_second_per_gpu:2171.3312059651844 
Step 2640 | loss:2.1761903762817383 lr:0.00015341246846515096 tokens_per_second_per_gpu:2163.1608359030124 
Step 2641 | loss:2.140315532684326 lr:0.00015337919879522283 tokens_per_second_per_gpu:2190.9120557021397 
Step 2642 | loss:2.1152374744415283 lr:0.00015334592086052546 tokens_per_second_per_gpu:2181.4996009160104 
Step 2643 | loss:2.176938533782959 lr:0.00015331263466621125 tokens_per_second_per_gpu:2154.096910850206 
Step 2644 | loss:2.07918643951416 lr:0.00015327934021743399 tokens_per_second_per_gpu:2197.382548829528 
Step 2645 | loss:2.0758211612701416 lr:0.0001532460375193487 tokens_per_second_per_gpu:2173.0159751416413 
Step 2646 | loss:2.1260924339294434 lr:0.00015321272657711164 tokens_per_second_per_gpu:2186.383802788195 
Step 2647 | loss:2.21468186378479 lr:0.00015317940739588038 tokens_per_second_per_gpu:2188.537844291148 
Step 2648 | loss:2.137784481048584 lr:0.00015314607998081386 tokens_per_second_per_gpu:2161.892688178237 
Step 2649 | loss:2.1766128540039062 lr:0.00015311274433707207 tokens_per_second_per_gpu:2120.4399176409347 
Step 2650 | loss:2.1045475006103516 lr:0.00015307940046981657 tokens_per_second_per_gpu:2165.0532979019263 
Step 2651 | loss:2.209301471710205 lr:0.0001530460483842099 tokens_per_second_per_gpu:2081.1362001059497 
Step 2652 | loss:2.1848373413085938 lr:0.00015301268808541604 tokens_per_second_per_gpu:2174.671432596308 
Step 2653 | loss:2.1848320960998535 lr:0.0001529793195786003 tokens_per_second_per_gpu:2194.2236603456004 
Step 2654 | loss:2.1728830337524414 lr:0.00015294594286892904 tokens_per_second_per_gpu:2168.1689313366533 
Step 2655 | loss:2.1406893730163574 lr:0.00015291255796157004 tokens_per_second_per_gpu:2133.3382130141226 
Step 2656 | loss:2.139094352722168 lr:0.0001528791648616924 tokens_per_second_per_gpu:2140.0484898152763 
Step 2657 | loss:2.149784564971924 lr:0.00015284576357446636 tokens_per_second_per_gpu:2191.464489275462 
Step 2658 | loss:2.151930332183838 lr:0.0001528123541050635 tokens_per_second_per_gpu:2177.8498685587265 
Step 2659 | loss:2.145651340484619 lr:0.00015277893645865667 tokens_per_second_per_gpu:2161.35543369325 
Step 2660 | loss:2.2016727924346924 lr:0.0001527455106404199 tokens_per_second_per_gpu:2128.449269373696 
Step 2661 | loss:2.1449735164642334 lr:0.0001527120766555286 tokens_per_second_per_gpu:2185.881070803621 
Step 2662 | loss:2.1932473182678223 lr:0.00015267863450915944 tokens_per_second_per_gpu:2124.9839099772257 
Step 2663 | loss:2.1733479499816895 lr:0.00015264518420649023 tokens_per_second_per_gpu:2175.6823756307135 
Step 2664 | loss:2.1517953872680664 lr:0.00015261172575270016 tokens_per_second_per_gpu:2144.215327059889 
Step 2665 | loss:2.1054115295410156 lr:0.00015257825915296965 tokens_per_second_per_gpu:2149.651681344886 
Step 2666 | loss:2.132530689239502 lr:0.00015254478441248035 tokens_per_second_per_gpu:2153.0664604413505 
Step 2667 | loss:2.135268211364746 lr:0.00015251130153641523 tokens_per_second_per_gpu:2191.6306688792583 
Step 2668 | loss:2.1306471824645996 lr:0.00015247781052995846 tokens_per_second_per_gpu:2117.7959916651052 
Step 2669 | loss:2.128251075744629 lr:0.0001524443113982955 tokens_per_second_per_gpu:2136.970245071575 
Step 2670 | loss:2.2178804874420166 lr:0.00015241080414661308 tokens_per_second_per_gpu:2031.1037608064191 
Step 2671 | loss:2.0874412059783936 lr:0.00015237728878009915 tokens_per_second_per_gpu:2006.9762144919566 
Step 2672 | loss:2.201467990875244 lr:0.00015234376530394295 tokens_per_second_per_gpu:2158.0830496226376 
Step 2673 | loss:2.1271862983703613 lr:0.00015231023372333494 tokens_per_second_per_gpu:2114.911081245484 
Step 2674 | loss:2.1734132766723633 lr:0.00015227669404346692 tokens_per_second_per_gpu:2136.877872815182 
Step 2675 | loss:2.141767740249634 lr:0.00015224314626953182 tokens_per_second_per_gpu:2117.0713534912634 
Step 2676 | loss:2.1292190551757812 lr:0.00015220959040672386 tokens_per_second_per_gpu:2174.946065995242 
Step 2677 | loss:2.1569886207580566 lr:0.00015217602646023864 tokens_per_second_per_gpu:2179.030032647032 
Step 2678 | loss:2.110774517059326 lr:0.00015214245443527285 tokens_per_second_per_gpu:2184.8172881085356 
Step 2679 | loss:2.1726064682006836 lr:0.00015210887433702444 tokens_per_second_per_gpu:2199.719417860245 
Step 2680 | loss:2.1651382446289062 lr:0.00015207528617069272 tokens_per_second_per_gpu:2138.8482563513094 
Step 2681 | loss:2.1860437393188477 lr:0.00015204168994147817 tokens_per_second_per_gpu:2191.5937890504847 
Step 2682 | loss:2.1478195190429688 lr:0.00015200808565458252 tokens_per_second_per_gpu:2161.6729943523414 
Step 2683 | loss:2.1812286376953125 lr:0.00015197447331520884 tokens_per_second_per_gpu:2076.689213244387 
Step 2684 | loss:2.168144464492798 lr:0.0001519408529285613 tokens_per_second_per_gpu:2155.9695556291276 
Step 2685 | loss:2.105928897857666 lr:0.00015190722449984537 tokens_per_second_per_gpu:2179.4949713837655 
Step 2686 | loss:2.142897129058838 lr:0.00015187358803426786 tokens_per_second_per_gpu:2191.063732971596 
Step 2687 | loss:2.107372522354126 lr:0.0001518399435370367 tokens_per_second_per_gpu:2137.3580710777837 
Step 2688 | loss:2.1361589431762695 lr:0.00015180629101336108 tokens_per_second_per_gpu:2129.446537737083 
Step 2689 | loss:2.112128734588623 lr:0.0001517726304684515 tokens_per_second_per_gpu:2175.419664650732 
Step 2690 | loss:2.1121280193328857 lr:0.00015173896190751968 tokens_per_second_per_gpu:2086.5225636742257 
Step 2691 | loss:2.162651300430298 lr:0.00015170528533577855 tokens_per_second_per_gpu:2166.600228681992 
Step 2692 | loss:2.1331727504730225 lr:0.00015167160075844227 tokens_per_second_per_gpu:2115.125095000817 
Step 2693 | loss:2.1188457012176514 lr:0.00015163790818072635 tokens_per_second_per_gpu:2113.3233265073727 
Step 2694 | loss:2.178053379058838 lr:0.00015160420760784732 tokens_per_second_per_gpu:2157.1378552523097 
Step 2695 | loss:2.2141222953796387 lr:0.00015157049904502317 tokens_per_second_per_gpu:2120.3679409365245 
Step 2696 | loss:2.179532766342163 lr:0.00015153678249747306 tokens_per_second_per_gpu:2129.380202007822 
Step 2697 | loss:2.135655641555786 lr:0.00015150305797041733 tokens_per_second_per_gpu:2144.0722606721315 
Step 2698 | loss:2.175558567047119 lr:0.0001514693254690776 tokens_per_second_per_gpu:2183.311928504636 
Step 2699 | loss:2.1371166706085205 lr:0.0001514355849986767 tokens_per_second_per_gpu:2167.0787388723884 
Step 2700 | loss:2.1666507720947266 lr:0.0001514018365644387 tokens_per_second_per_gpu:2156.52643266795 
Step 2701 | loss:2.2098517417907715 lr:0.00015136808017158894 tokens_per_second_per_gpu:2163.7289503266575 
Step 2702 | loss:2.156846046447754 lr:0.000151334315825354 tokens_per_second_per_gpu:2196.6820961168933 
Step 2703 | loss:2.1828038692474365 lr:0.00015130054353096155 tokens_per_second_per_gpu:2108.976780091772 
Step 2704 | loss:2.085783004760742 lr:0.00015126676329364072 tokens_per_second_per_gpu:2177.5881923120346 
Step 2705 | loss:2.134230136871338 lr:0.00015123297511862168 tokens_per_second_per_gpu:2179.347396590803 
Step 2706 | loss:2.1419010162353516 lr:0.00015119917901113588 tokens_per_second_per_gpu:2193.721473996279 
Step 2707 | loss:2.1219334602355957 lr:0.00015116537497641605 tokens_per_second_per_gpu:2100.3463173665245 
Step 2708 | loss:2.144423007965088 lr:0.00015113156301969612 tokens_per_second_per_gpu:2188.3793392987327 
Step 2709 | loss:2.1678266525268555 lr:0.0001510977431462112 tokens_per_second_per_gpu:2195.8517926692734 
Step 2710 | loss:2.2131919860839844 lr:0.00015106391536119767 tokens_per_second_per_gpu:2096.895478417722 
Step 2711 | loss:2.2253246307373047 lr:0.00015103007966989318 tokens_per_second_per_gpu:2111.2651238306958 
Step 2712 | loss:2.169750690460205 lr:0.0001509962360775365 tokens_per_second_per_gpu:2189.8257041761412 
Step 2713 | loss:2.1715846061706543 lr:0.0001509623845893677 tokens_per_second_per_gpu:2192.594299130347 
Step 2714 | loss:2.2136642932891846 lr:0.00015092852521062807 tokens_per_second_per_gpu:2157.2733424187836 
Step 2715 | loss:2.1971912384033203 lr:0.00015089465794656002 tokens_per_second_per_gpu:2188.674689408047 
Step 2716 | loss:2.1806435585021973 lr:0.00015086078280240732 tokens_per_second_per_gpu:2193.372583651671 
Step 2717 | loss:2.188797950744629 lr:0.00015082689978341494 tokens_per_second_per_gpu:2200.2205244792767 
Step 2718 | loss:2.22002911567688 lr:0.00015079300889482892 tokens_per_second_per_gpu:2200.7437015890537 
Step 2719 | loss:2.171776294708252 lr:0.00015075911014189675 tokens_per_second_per_gpu:2189.0523703650433 
Step 2720 | loss:2.112140417098999 lr:0.00015072520352986697 tokens_per_second_per_gpu:2139.7090686285915 
Step 2721 | loss:2.1044631004333496 lr:0.00015069128906398935 tokens_per_second_per_gpu:2163.6511124788212 
Step 2722 | loss:2.113220691680908 lr:0.00015065736674951493 tokens_per_second_per_gpu:2180.7503570912168 
Step 2723 | loss:2.1576197147369385 lr:0.000150623436591696 tokens_per_second_per_gpu:2161.6918554498457 
Step 2724 | loss:2.1620945930480957 lr:0.0001505894985957859 tokens_per_second_per_gpu:2195.7840974334954 
Step 2725 | loss:2.223231315612793 lr:0.0001505555527670394 tokens_per_second_per_gpu:2198.466234786981 
Step 2726 | loss:2.091855525970459 lr:0.00015052159911071233 tokens_per_second_per_gpu:2197.3362961938697 
Step 2727 | loss:2.1309831142425537 lr:0.00015048763763206172 tokens_per_second_per_gpu:2066.57509146564 
Step 2728 | loss:2.222627639770508 lr:0.000150453668336346 tokens_per_second_per_gpu:2118.713089873784 
Step 2729 | loss:2.1071038246154785 lr:0.00015041969122882458 tokens_per_second_per_gpu:2168.2941912987735 
Step 2730 | loss:2.145977020263672 lr:0.00015038570631475818 tokens_per_second_per_gpu:2111.328087264879 
Step 2731 | loss:2.1521432399749756 lr:0.0001503517135994088 tokens_per_second_per_gpu:2199.5110176256526 
Step 2732 | loss:2.2188806533813477 lr:0.0001503177130880395 tokens_per_second_per_gpu:2198.4975793730955 
Step 2733 | loss:2.138676404953003 lr:0.00015028370478591466 tokens_per_second_per_gpu:2121.358306429764 
Step 2734 | loss:2.1928234100341797 lr:0.0001502496886982998 tokens_per_second_per_gpu:2136.2766593102897 
Step 2735 | loss:2.179776668548584 lr:0.00015021566483046172 tokens_per_second_per_gpu:2160.3655255194867 
Step 2736 | loss:2.159298896789551 lr:0.00015018163318766833 tokens_per_second_per_gpu:2195.6389886931865 
Step 2737 | loss:2.21447491645813 lr:0.00015014759377518885 tokens_per_second_per_gpu:2116.40881528724 
Step 2738 | loss:2.113377571105957 lr:0.0001501135465982936 tokens_per_second_per_gpu:2189.9219593277817 
Step 2739 | loss:2.110924482345581 lr:0.00015007949166225413 tokens_per_second_per_gpu:2107.3040680396193 
Step 2740 | loss:2.143496036529541 lr:0.00015004542897234326 tokens_per_second_per_gpu:2163.9136942643245 
Step 2741 | loss:2.112920045852661 lr:0.00015001135853383494 tokens_per_second_per_gpu:2190.7479873888333 
Step 2742 | loss:2.211421251296997 lr:0.00014997728035200434 tokens_per_second_per_gpu:2177.773454434561 
Step 2743 | loss:2.136047601699829 lr:0.0001499431944321278 tokens_per_second_per_gpu:2168.3824223420393 
Step 2744 | loss:2.174830675125122 lr:0.00014990910077948292 tokens_per_second_per_gpu:2164.05985315373 
Step 2745 | loss:2.1894052028656006 lr:0.00014987499939934847 tokens_per_second_per_gpu:2160.774194862018 
Step 2746 | loss:2.143249034881592 lr:0.0001498408902970044 tokens_per_second_per_gpu:2155.5318839359957 
Step 2747 | loss:2.081594467163086 lr:0.00014980677347773184 tokens_per_second_per_gpu:2149.8508305598903 
Step 2748 | loss:2.1570963859558105 lr:0.00014977264894681317 tokens_per_second_per_gpu:2179.883003535271 
Step 2749 | loss:2.138082981109619 lr:0.00014973851670953191 tokens_per_second_per_gpu:2188.4894712475793 
Step 2750 | loss:2.1364030838012695 lr:0.00014970437677117287 tokens_per_second_per_gpu:2111.660540138415 
Step 2751 | loss:2.0440456867218018 lr:0.00014967022913702188 tokens_per_second_per_gpu:2184.4137654317965 
Step 2752 | loss:2.1689579486846924 lr:0.00014963607381236608 tokens_per_second_per_gpu:2175.3220728038664 
Step 2753 | loss:2.1409692764282227 lr:0.00014960191080249383 tokens_per_second_per_gpu:2166.978905281979 
Step 2754 | loss:2.0725884437561035 lr:0.0001495677401126946 tokens_per_second_per_gpu:2182.7489262333215 
Step 2755 | loss:2.1665544509887695 lr:0.0001495335617482591 tokens_per_second_per_gpu:2115.5010411807843 
Step 2756 | loss:2.1687445640563965 lr:0.00014949937571447926 tokens_per_second_per_gpu:2168.759146445065 
Step 2757 | loss:2.1192808151245117 lr:0.00014946518201664798 tokens_per_second_per_gpu:2194.8838506847706 
Step 2758 | loss:2.1079940795898438 lr:0.0001494309806600597 tokens_per_second_per_gpu:2136.656154260735 
Step 2759 | loss:2.1104495525360107 lr:0.00014939677165000975 tokens_per_second_per_gpu:2175.4994033559124 
Step 2760 | loss:2.15783429145813 lr:0.0001493625549917948 tokens_per_second_per_gpu:2197.528856302639 
Step 2761 | loss:2.187931537628174 lr:0.00014932833069071264 tokens_per_second_per_gpu:2120.1914370862846 
Step 2762 | loss:2.168935775756836 lr:0.00014929409875206226 tokens_per_second_per_gpu:2181.6656984571778 
Step 2763 | loss:2.1777095794677734 lr:0.00014925985918114385 tokens_per_second_per_gpu:2174.302434618035 
Step 2764 | loss:2.189602851867676 lr:0.00014922561198325878 tokens_per_second_per_gpu:2171.28810318189 
Step 2765 | loss:2.138101100921631 lr:0.0001491913571637095 tokens_per_second_per_gpu:2185.8639774173807 
Step 2766 | loss:2.0848686695098877 lr:0.00014915709472779985 tokens_per_second_per_gpu:2169.4031949815294 
Step 2767 | loss:2.1429800987243652 lr:0.00014912282468083462 tokens_per_second_per_gpu:2169.3325858472585 
Step 2768 | loss:2.1680097579956055 lr:0.00014908854702811998 tokens_per_second_per_gpu:2167.264526997694 
Step 2769 | loss:2.175264358520508 lr:0.00014905426177496314 tokens_per_second_per_gpu:2169.6444042046132 
Step 2770 | loss:2.159316062927246 lr:0.0001490199689266725 tokens_per_second_per_gpu:2131.0415436572953 
Step 2771 | loss:2.180222988128662 lr:0.00014898566848855772 tokens_per_second_per_gpu:2194.923151593054 
Step 2772 | loss:2.1417253017425537 lr:0.0001489513604659295 tokens_per_second_per_gpu:2127.5919158320066 
Step 2773 | loss:2.1096553802490234 lr:0.00014891704486409989 tokens_per_second_per_gpu:2167.251927790124 
Step 2774 | loss:2.1307272911071777 lr:0.00014888272168838196 tokens_per_second_per_gpu:2200.445768495575 
Step 2775 | loss:2.1577301025390625 lr:0.00014884839094409002 tokens_per_second_per_gpu:2185.189335943756 
Step 2776 | loss:2.1078763008117676 lr:0.00014881405263653954 tokens_per_second_per_gpu:2171.6440236344774 
Step 2777 | loss:2.1525702476501465 lr:0.0001487797067710472 tokens_per_second_per_gpu:2200.9148965830695 
Step 2778 | loss:2.1409740447998047 lr:0.00014874535335293078 tokens_per_second_per_gpu:2195.7364272785057 
Step 2779 | loss:2.171907424926758 lr:0.00014871099238750925 tokens_per_second_per_gpu:2197.791812193876 
Step 2780 | loss:2.1077260971069336 lr:0.0001486766238801028 tokens_per_second_per_gpu:2093.665410586902 
Step 2781 | loss:2.138716697692871 lr:0.00014864224783603272 tokens_per_second_per_gpu:2155.4896007421994 
Step 2782 | loss:2.1265406608581543 lr:0.00014860786426062152 tokens_per_second_per_gpu:2145.066249724863 
Step 2783 | loss:2.204561233520508 lr:0.00014857347315919283 tokens_per_second_per_gpu:2147.7091012165715 
Step 2784 | loss:2.147279739379883 lr:0.00014853907453707147 tokens_per_second_per_gpu:2102.196835396712 
Step 2785 | loss:2.133641004562378 lr:0.00014850466839958347 tokens_per_second_per_gpu:2142.7546284287087 
Step 2786 | loss:2.1110005378723145 lr:0.00014847025475205592 tokens_per_second_per_gpu:2156.117569627209 
Step 2787 | loss:2.1500096321105957 lr:0.00014843583359981711 tokens_per_second_per_gpu:2185.5007692646645 
Step 2788 | loss:2.1355342864990234 lr:0.00014840140494819658 tokens_per_second_per_gpu:2177.3413875039405 
Step 2789 | loss:2.1386914253234863 lr:0.00014836696880252495 tokens_per_second_per_gpu:2102.06757508834 
Step 2790 | loss:2.151843309402466 lr:0.00014833252516813393 tokens_per_second_per_gpu:2169.929874754594 
Step 2791 | loss:2.1418848037719727 lr:0.00014829807405035658 tokens_per_second_per_gpu:2028.7339877406034 
Step 2792 | loss:2.0990991592407227 lr:0.00014826361545452696 tokens_per_second_per_gpu:2159.7507194042537 
Step 2793 | loss:2.117434024810791 lr:0.00014822914938598033 tokens_per_second_per_gpu:2163.9505042318024 
Step 2794 | loss:2.1428067684173584 lr:0.00014819467585005313 tokens_per_second_per_gpu:2157.0738573936987 
Step 2795 | loss:2.1659231185913086 lr:0.00014816019485208295 tokens_per_second_per_gpu:2165.5258975312872 
Step 2796 | loss:2.178879737854004 lr:0.0001481257063974085 tokens_per_second_per_gpu:2151.7357737982047 
Step 2797 | loss:2.214200496673584 lr:0.00014809121049136968 tokens_per_second_per_gpu:2153.0835752685 
Step 2798 | loss:2.159269332885742 lr:0.00014805670713930757 tokens_per_second_per_gpu:2179.502540289151 
Step 2799 | loss:2.1033732891082764 lr:0.00014802219634656432 tokens_per_second_per_gpu:2187.427231454056 
Step 2800 | loss:2.154637575149536 lr:0.0001479876781184833 tokens_per_second_per_gpu:2150.580342346707 
Step 2801 | loss:2.1397571563720703 lr:0.00014795315246040903 tokens_per_second_per_gpu:2196.1820285307917 
Step 2802 | loss:2.118928909301758 lr:0.0001479186193776871 tokens_per_second_per_gpu:2181.840206880265 
Step 2803 | loss:2.1530017852783203 lr:0.0001478840788756644 tokens_per_second_per_gpu:2168.559592303838 
Step 2804 | loss:2.2046024799346924 lr:0.00014784953095968881 tokens_per_second_per_gpu:2184.2382120527213 
Step 2805 | loss:2.175150156021118 lr:0.00014781497563510945 tokens_per_second_per_gpu:2155.028856820806 
Step 2806 | loss:2.165508270263672 lr:0.00014778041290727656 tokens_per_second_per_gpu:2142.9349952886237 
Step 2807 | loss:2.1689648628234863 lr:0.00014774584278154157 tokens_per_second_per_gpu:2002.387298979828 
Step 2808 | loss:2.1676316261291504 lr:0.00014771126526325694 tokens_per_second_per_gpu:2127.7193932582654 
Step 2809 | loss:2.0925307273864746 lr:0.00014767668035777642 tokens_per_second_per_gpu:2091.564153343146 
Step 2810 | loss:2.139522075653076 lr:0.00014764208807045479 tokens_per_second_per_gpu:2144.7268970005907 
Step 2811 | loss:2.1268365383148193 lr:0.00014760748840664804 tokens_per_second_per_gpu:2184.470574008633 
Step 2812 | loss:2.155515193939209 lr:0.0001475728813717133 tokens_per_second_per_gpu:2163.1607701231837 
Step 2813 | loss:2.177399158477783 lr:0.00014753826697100879 tokens_per_second_per_gpu:2189.953980484565 
Step 2814 | loss:2.105083465576172 lr:0.0001475036452098939 tokens_per_second_per_gpu:2078.9880647750538 
Step 2815 | loss:2.1590542793273926 lr:0.0001474690160937292 tokens_per_second_per_gpu:2161.866875471144 
Step 2816 | loss:2.1576526165008545 lr:0.0001474343796278763 tokens_per_second_per_gpu:2198.4986654807403 
Step 2817 | loss:2.0967936515808105 lr:0.00014739973581769805 tokens_per_second_per_gpu:2172.233399554687 
Step 2818 | loss:2.177529811859131 lr:0.00014736508466855837 tokens_per_second_per_gpu:2189.8665167058057 
Step 2819 | loss:2.188821792602539 lr:0.00014733042618582238 tokens_per_second_per_gpu:2180.1748132225052 
Step 2820 | loss:2.2020580768585205 lr:0.00014729576037485626 tokens_per_second_per_gpu:2194.070410029701 
Step 2821 | loss:2.1176419258117676 lr:0.00014726108724102738 tokens_per_second_per_gpu:2192.8610173347042 
Step 2822 | loss:2.114793300628662 lr:0.00014722640678970422 tokens_per_second_per_gpu:2188.7611726474224 
Step 2823 | loss:2.111032485961914 lr:0.00014719171902625642 tokens_per_second_per_gpu:2186.671221617788 
Step 2824 | loss:2.18580961227417 lr:0.0001471570239560547 tokens_per_second_per_gpu:2166.3713466712074 
Step 2825 | loss:2.150956392288208 lr:0.00014712232158447096 tokens_per_second_per_gpu:2194.0873200258757 
Step 2826 | loss:2.1487274169921875 lr:0.00014708761191687815 tokens_per_second_per_gpu:2178.349972653923 
Step 2827 | loss:2.1368250846862793 lr:0.0001470528949586505 tokens_per_second_per_gpu:2141.6223119900565 
Step 2828 | loss:2.1130244731903076 lr:0.00014701817071516326 tokens_per_second_per_gpu:2149.388171419111 
Step 2829 | loss:2.2243738174438477 lr:0.0001469834391917928 tokens_per_second_per_gpu:2198.2027284883598 
Step 2830 | loss:2.1347904205322266 lr:0.00014694870039391665 tokens_per_second_per_gpu:2152.6016929278585 
Step 2831 | loss:2.102281093597412 lr:0.00014691395432691354 tokens_per_second_per_gpu:2164.5388380604463 
Step 2832 | loss:2.121366262435913 lr:0.00014687920099616311 tokens_per_second_per_gpu:2178.2414520402517 
Step 2833 | loss:2.1257681846618652 lr:0.00014684444040704634 tokens_per_second_per_gpu:2189.714957215175 
Step 2834 | loss:2.1727547645568848 lr:0.00014680967256494528 tokens_per_second_per_gpu:2108.0138186838703 
Step 2835 | loss:2.107206344604492 lr:0.00014677489747524304 tokens_per_second_per_gpu:2180.1964138206877 
Step 2836 | loss:2.1717517375946045 lr:0.00014674011514332388 tokens_per_second_per_gpu:2172.5457506245475 
Step 2837 | loss:2.126319408416748 lr:0.00014670532557457323 tokens_per_second_per_gpu:2125.546079908556 
Step 2838 | loss:2.1432623863220215 lr:0.0001466705287743776 tokens_per_second_per_gpu:2170.8780309323624 
Step 2839 | loss:2.2226791381835938 lr:0.0001466357247481246 tokens_per_second_per_gpu:2137.5753913149197 
Step 2840 | loss:2.130941867828369 lr:0.00014660091350120297 tokens_per_second_per_gpu:2155.171768649681 
Step 2841 | loss:2.14329195022583 lr:0.0001465660950390026 tokens_per_second_per_gpu:2161.729847549735 
Step 2842 | loss:2.1962356567382812 lr:0.0001465312693669145 tokens_per_second_per_gpu:2171.6948258709176 
Step 2843 | loss:2.136906862258911 lr:0.00014649643649033078 tokens_per_second_per_gpu:2175.268571408053 
Step 2844 | loss:2.177450656890869 lr:0.00014646159641464458 tokens_per_second_per_gpu:2196.322588502311 
Step 2845 | loss:2.0857162475585938 lr:0.0001464267491452503 tokens_per_second_per_gpu:2189.931694370944 
Step 2846 | loss:2.1735432147979736 lr:0.00014639189468754337 tokens_per_second_per_gpu:2188.5282629298945 
Step 2847 | loss:2.13997483253479 lr:0.00014635703304692035 tokens_per_second_per_gpu:2081.257128338946 
Step 2848 | loss:2.2316598892211914 lr:0.0001463221642287789 tokens_per_second_per_gpu:2165.672728642598 
Step 2849 | loss:2.203932762145996 lr:0.00014628728823851784 tokens_per_second_per_gpu:2185.216991460787 
Step 2850 | loss:2.1859636306762695 lr:0.00014625240508153703 tokens_per_second_per_gpu:2091.8010835477385 
Step 2851 | loss:2.092865467071533 lr:0.00014621751476323746 tokens_per_second_per_gpu:2158.614896936593 
Step 2852 | loss:2.0972537994384766 lr:0.00014618261728902132 tokens_per_second_per_gpu:2197.898677082284 
Step 2853 | loss:2.113391160964966 lr:0.00014614771266429174 tokens_per_second_per_gpu:2163.964084756583 
Step 2854 | loss:2.179107666015625 lr:0.00014611280089445305 tokens_per_second_per_gpu:2184.739313436314 
Step 2855 | loss:2.1009302139282227 lr:0.00014607788198491077 tokens_per_second_per_gpu:2149.6716553756296 
Step 2856 | loss:2.1506972312927246 lr:0.00014604295594107137 tokens_per_second_per_gpu:2168.4202856747393 
Step 2857 | loss:2.2192955017089844 lr:0.00014600802276834248 tokens_per_second_per_gpu:2188.6331837989133 
Step 2858 | loss:2.143939971923828 lr:0.00014597308247213294 tokens_per_second_per_gpu:2123.5855533864087 
Step 2859 | loss:2.1157541275024414 lr:0.00014593813505785249 tokens_per_second_per_gpu:2190.896395041974 
Step 2860 | loss:2.1318185329437256 lr:0.00014590318053091215 tokens_per_second_per_gpu:2185.102397847763 
Step 2861 | loss:2.1656570434570312 lr:0.00014586821889672394 tokens_per_second_per_gpu:2197.8565719761887 
Step 2862 | loss:2.166102409362793 lr:0.00014583325016070104 tokens_per_second_per_gpu:2127.6798604788196 
Step 2863 | loss:2.1825270652770996 lr:0.0001457982743282577 tokens_per_second_per_gpu:2182.780516111822 
Step 2864 | loss:2.1481759548187256 lr:0.00014576329140480925 tokens_per_second_per_gpu:2160.2092231800452 
Step 2865 | loss:2.1352179050445557 lr:0.00014572830139577216 tokens_per_second_per_gpu:2184.1650387460895 
Step 2866 | loss:2.127551555633545 lr:0.00014569330430656399 tokens_per_second_per_gpu:2194.0358274518044 
Step 2867 | loss:2.134598970413208 lr:0.00014565830014260332 tokens_per_second_per_gpu:2190.1437358742096 
Step 2868 | loss:2.1591787338256836 lr:0.00014562328890930997 tokens_per_second_per_gpu:2165.188480052275 
Step 2869 | loss:2.087772846221924 lr:0.00014558827061210474 tokens_per_second_per_gpu:2175.9300292201065 
Step 2870 | loss:2.1713857650756836 lr:0.00014555324525640956 tokens_per_second_per_gpu:2175.196098643599 
Step 2871 | loss:2.1118998527526855 lr:0.00014551821284764746 tokens_per_second_per_gpu:2191.042662096182 
Step 2872 | loss:2.1385879516601562 lr:0.00014548317339124252 tokens_per_second_per_gpu:2188.497599384499 
Step 2873 | loss:2.1435933113098145 lr:0.00014544812689262 tokens_per_second_per_gpu:2188.2849221187494 
Step 2874 | loss:2.210355758666992 lr:0.0001454130733572061 tokens_per_second_per_gpu:2197.6331809933163 
Step 2875 | loss:2.1427974700927734 lr:0.0001453780127904283 tokens_per_second_per_gpu:2180.0646518057374 
Step 2876 | loss:2.0550575256347656 lr:0.00014534294519771504 tokens_per_second_per_gpu:2144.655542951945 
Step 2877 | loss:2.1099841594696045 lr:0.00014530787058449586 tokens_per_second_per_gpu:2194.485719362326 
Step 2878 | loss:2.16029691696167 lr:0.00014527278895620142 tokens_per_second_per_gpu:2194.013999129304 
Step 2879 | loss:2.1640853881835938 lr:0.00014523770031826344 tokens_per_second_per_gpu:2099.551873408296 
Step 2880 | loss:2.1607494354248047 lr:0.0001452026046761148 tokens_per_second_per_gpu:2190.553514614595 
Step 2881 | loss:2.096705675125122 lr:0.0001451675020351893 tokens_per_second_per_gpu:2158.473924024663 
Step 2882 | loss:2.1497457027435303 lr:0.00014513239240092202 tokens_per_second_per_gpu:2176.902072463517 
Step 2883 | loss:2.1630682945251465 lr:0.000145097275778749 tokens_per_second_per_gpu:2134.851245265192 
Step 2884 | loss:2.0878610610961914 lr:0.00014506215217410736 tokens_per_second_per_gpu:2138.164418976368 
Step 2885 | loss:2.1381990909576416 lr:0.00014502702159243532 tokens_per_second_per_gpu:2173.2887153690162 
Step 2886 | loss:2.1304287910461426 lr:0.0001449918840391723 tokens_per_second_per_gpu:2172.086084077045 
Step 2887 | loss:2.1719021797180176 lr:0.00014495673951975857 tokens_per_second_per_gpu:2146.0819514537293 
Step 2888 | loss:2.1099202632904053 lr:0.00014492158803963568 tokens_per_second_per_gpu:2188.940500941824 
Step 2889 | loss:2.1086413860321045 lr:0.00014488642960424613 tokens_per_second_per_gpu:2188.309114552124 
Step 2890 | loss:2.1385207176208496 lr:0.00014485126421903357 tokens_per_second_per_gpu:2087.778091100237 
Step 2891 | loss:2.1643195152282715 lr:0.0001448160918894427 tokens_per_second_per_gpu:2196.429637245828 
Step 2892 | loss:2.103445529937744 lr:0.00014478091262091927 tokens_per_second_per_gpu:2192.7915112692203 
Step 2893 | loss:2.1809096336364746 lr:0.00014474572641891018 tokens_per_second_per_gpu:2193.533018193062 
Step 2894 | loss:2.12371826171875 lr:0.00014471053328886333 tokens_per_second_per_gpu:2183.854466774712 
Step 2895 | loss:2.100795269012451 lr:0.0001446753332362277 tokens_per_second_per_gpu:2148.767889488225 
Step 2896 | loss:2.10019588470459 lr:0.00014464012626645335 tokens_per_second_per_gpu:2138.8572809299103 
Step 2897 | loss:2.1002912521362305 lr:0.0001446049123849915 tokens_per_second_per_gpu:2144.716328910004 
Step 2898 | loss:2.1371564865112305 lr:0.0001445696915972943 tokens_per_second_per_gpu:2168.1087430105113 
Step 2899 | loss:2.1462130546569824 lr:0.00014453446390881496 tokens_per_second_per_gpu:2154.7686555843343 
Step 2900 | loss:2.1426122188568115 lr:0.00014449922932500799 tokens_per_second_per_gpu:2183.5735128557294 
Step 2901 | loss:2.082530975341797 lr:0.00014446398785132865 tokens_per_second_per_gpu:2209.635841523791 
Step 2902 | loss:2.1441149711608887 lr:0.00014442873949323351 tokens_per_second_per_gpu:2204.1102833096043 
Step 2903 | loss:2.1374125480651855 lr:0.00014439348425618014 tokens_per_second_per_gpu:2077.8009932218483 
Step 2904 | loss:2.1457481384277344 lr:0.00014435822214562704 tokens_per_second_per_gpu:2191.6460047146 
Step 2905 | loss:2.104536533355713 lr:0.000144322953167034 tokens_per_second_per_gpu:2089.2494616920376 
Step 2906 | loss:2.0860037803649902 lr:0.00014428767732586173 tokens_per_second_per_gpu:2120.3892833134146 
Step 2907 | loss:2.1893908977508545 lr:0.00014425239462757198 tokens_per_second_per_gpu:2195.604891925223 
Step 2908 | loss:2.130277156829834 lr:0.00014421710507762768 tokens_per_second_per_gpu:2141.7114062027917 
Step 2909 | loss:2.1339845657348633 lr:0.00014418180868149274 tokens_per_second_per_gpu:2110.3060172264936 
Step 2910 | loss:2.1216158866882324 lr:0.00014414650544463214 tokens_per_second_per_gpu:2186.3650333777055 
Step 2911 | loss:2.143187999725342 lr:0.00014411119537251189 tokens_per_second_per_gpu:2182.433134951149 
Step 2912 | loss:2.1453824043273926 lr:0.00014407587847059913 tokens_per_second_per_gpu:2131.822520276914 
Step 2913 | loss:2.113765239715576 lr:0.00014404055474436206 tokens_per_second_per_gpu:2169.1564872582235 
Step 2914 | loss:2.098900079727173 lr:0.00014400522419926983 tokens_per_second_per_gpu:2101.7955010121846 
Step 2915 | loss:2.1130971908569336 lr:0.00014396988684079273 tokens_per_second_per_gpu:2173.533709353947 
Step 2916 | loss:2.0959701538085938 lr:0.00014393454267440213 tokens_per_second_per_gpu:2174.802976661561 
Step 2917 | loss:2.071889877319336 lr:0.00014389919170557032 tokens_per_second_per_gpu:2149.8500694017916 
Step 2918 | loss:2.110546112060547 lr:0.00014386383393977085 tokens_per_second_per_gpu:2166.760164073895 
Step 2919 | loss:2.1492466926574707 lr:0.00014382846938247815 tokens_per_second_per_gpu:2185.3326859851218 
Step 2920 | loss:2.125749111175537 lr:0.0001437930980391677 tokens_per_second_per_gpu:2180.9211396549167 
Step 2921 | loss:2.157435417175293 lr:0.00014375771991531624 tokens_per_second_per_gpu:2164.558466404402 
Step 2922 | loss:2.052901268005371 lr:0.00014372233501640128 tokens_per_second_per_gpu:2185.4890265214776 
Step 2923 | loss:2.099255084991455 lr:0.00014368694334790155 tokens_per_second_per_gpu:2163.063614798965 
Step 2924 | loss:2.1459646224975586 lr:0.0001436515449152968 tokens_per_second_per_gpu:2139.132752506113 
Step 2925 | loss:2.1485042572021484 lr:0.00014361613972406777 tokens_per_second_per_gpu:2193.762996965116 
Step 2926 | loss:2.10921573638916 lr:0.00014358072777969632 tokens_per_second_per_gpu:2174.196144656816 
Step 2927 | loss:2.099285125732422 lr:0.0001435453090876654 tokens_per_second_per_gpu:2176.896955880708 
Step 2928 | loss:2.1276817321777344 lr:0.00014350988365345878 tokens_per_second_per_gpu:2195.9163754677047 
Step 2929 | loss:2.150393009185791 lr:0.00014347445148256153 tokens_per_second_per_gpu:2176.3424610445463 
Step 2930 | loss:2.1857187747955322 lr:0.00014343901258045966 tokens_per_second_per_gpu:2174.2415946488277 
Step 2931 | loss:2.130366325378418 lr:0.0001434035669526402 tokens_per_second_per_gpu:2091.9063601347234 
Step 2932 | loss:2.15128755569458 lr:0.0001433681146045912 tokens_per_second_per_gpu:2075.2115560621464 
Step 2933 | loss:2.11187744140625 lr:0.00014333265554180183 tokens_per_second_per_gpu:2181.2253399686724 
Step 2934 | loss:2.12330961227417 lr:0.0001432971897697623 tokens_per_second_per_gpu:2140.8486798511717 
Step 2935 | loss:2.161701202392578 lr:0.00014326171729396375 tokens_per_second_per_gpu:2186.4015395239667 
Step 2936 | loss:2.190786838531494 lr:0.00014322623811989843 tokens_per_second_per_gpu:2127.2917678732165 
Step 2937 | loss:2.1292076110839844 lr:0.00014319075225305972 tokens_per_second_per_gpu:2187.185259298431 
Step 2938 | loss:2.146789312362671 lr:0.00014315525969894183 tokens_per_second_per_gpu:2158.447154659728 
Step 2939 | loss:2.15195369720459 lr:0.00014311976046304015 tokens_per_second_per_gpu:2134.508866843518 
Step 2940 | loss:2.1009061336517334 lr:0.00014308425455085116 tokens_per_second_per_gpu:2161.6621596472564 
Step 2941 | loss:2.1423583030700684 lr:0.00014304874196787216 tokens_per_second_per_gpu:2195.2004672502694 
Step 2942 | loss:2.110386610031128 lr:0.00014301322271960165 tokens_per_second_per_gpu:2173.5397489545303 
Step 2943 | loss:2.1624398231506348 lr:0.00014297769681153913 tokens_per_second_per_gpu:2173.873039366189 
Step 2944 | loss:2.061176300048828 lr:0.00014294216424918515 tokens_per_second_per_gpu:2178.9716283352636 
Step 2945 | loss:2.153261661529541 lr:0.00014290662503804123 tokens_per_second_per_gpu:2143.4099739045305 
Step 2946 | loss:2.111820936203003 lr:0.00014287107918360993 tokens_per_second_per_gpu:2195.702668186516 
Step 2947 | loss:2.086047649383545 lr:0.00014283552669139488 tokens_per_second_per_gpu:2191.451226784341 
Step 2948 | loss:2.1407899856567383 lr:0.00014279996756690075 tokens_per_second_per_gpu:2182.3041404224623 
Step 2949 | loss:2.169893741607666 lr:0.00014276440181563318 tokens_per_second_per_gpu:2195.1810672506194 
Step 2950 | loss:2.149672508239746 lr:0.00014272882944309882 tokens_per_second_per_gpu:2186.5654624340996 
Step 2951 | loss:2.1069464683532715 lr:0.0001426932504548055 tokens_per_second_per_gpu:2156.6277239933634 
Step 2952 | loss:2.1324572563171387 lr:0.0001426576648562618 tokens_per_second_per_gpu:2132.214351537961 
Step 2953 | loss:2.1405935287475586 lr:0.0001426220726529776 tokens_per_second_per_gpu:2169.4157601480533 
Step 2954 | loss:2.1406068801879883 lr:0.00014258647385046363 tokens_per_second_per_gpu:2073.2423825185015 
Step 2955 | loss:2.1291847229003906 lr:0.00014255086845423176 tokens_per_second_per_gpu:2196.17097085121 
Step 2956 | loss:2.168717384338379 lr:0.00014251525646979474 tokens_per_second_per_gpu:2146.735828234079 
Step 2957 | loss:2.15889835357666 lr:0.0001424796379026665 tokens_per_second_per_gpu:2156.6806274832957 
Step 2958 | loss:2.1441335678100586 lr:0.00014244401275836187 tokens_per_second_per_gpu:2151.854010339081 
Step 2959 | loss:2.1229114532470703 lr:0.0001424083810423967 tokens_per_second_per_gpu:2168.932011435266 
Step 2960 | loss:2.1504509449005127 lr:0.0001423727427602879 tokens_per_second_per_gpu:2186.064564563059 
Step 2961 | loss:2.086268424987793 lr:0.00014233709791755346 tokens_per_second_per_gpu:2186.1602117147922 
Step 2962 | loss:2.151660919189453 lr:0.0001423014465197123 tokens_per_second_per_gpu:2010.5120283617814 
Step 2963 | loss:2.1476168632507324 lr:0.00014226578857228427 tokens_per_second_per_gpu:2183.2834850965382 
Step 2964 | loss:2.1098875999450684 lr:0.00014223012408079048 tokens_per_second_per_gpu:2193.9036815343193 
Step 2965 | loss:2.1483564376831055 lr:0.0001421944530507528 tokens_per_second_per_gpu:2189.7245633366524 
Step 2966 | loss:2.099484443664551 lr:0.00014215877548769427 tokens_per_second_per_gpu:2177.586268218753 
Step 2967 | loss:2.147343158721924 lr:0.00014212309139713887 tokens_per_second_per_gpu:2171.499105996208 
Step 2968 | loss:2.139774799346924 lr:0.00014208740078461166 tokens_per_second_per_gpu:2153.834090288029 
Step 2969 | loss:2.1084282398223877 lr:0.0001420517036556386 tokens_per_second_per_gpu:2133.9038193589386 
Step 2970 | loss:2.1360373497009277 lr:0.00014201600001574678 tokens_per_second_per_gpu:2150.8008950007256 
Step 2971 | loss:2.164062976837158 lr:0.00014198028987046413 tokens_per_second_per_gpu:2192.0172594009414 
Step 2972 | loss:2.09098744392395 lr:0.00014194457322531985 tokens_per_second_per_gpu:2195.2842838370557 
Step 2973 | loss:2.22872257232666 lr:0.00014190885008584395 tokens_per_second_per_gpu:2170.38794349938 
Step 2974 | loss:2.1157097816467285 lr:0.00014187312045756738 tokens_per_second_per_gpu:2175.975689701809 
Step 2975 | loss:2.114933490753174 lr:0.00014183738434602234 tokens_per_second_per_gpu:2159.0367559079828 
Step 2976 | loss:2.095197916030884 lr:0.00014180164175674184 tokens_per_second_per_gpu:2158.789001446338 
Step 2977 | loss:2.0946967601776123 lr:0.0001417658926952599 tokens_per_second_per_gpu:2195.1246593211154 
Step 2978 | loss:2.166594982147217 lr:0.0001417301371671117 tokens_per_second_per_gpu:2155.438787247464 
Step 2979 | loss:2.146695137023926 lr:0.00014169437517783323 tokens_per_second_per_gpu:2195.315702591074 
Step 2980 | loss:2.1534390449523926 lr:0.0001416586067329616 tokens_per_second_per_gpu:2186.0339054168726 
Step 2981 | loss:2.1424427032470703 lr:0.00014162283183803492 tokens_per_second_per_gpu:2178.9226111961184 
Step 2982 | loss:2.2094886302948 lr:0.00014158705049859216 tokens_per_second_per_gpu:2132.8841780094317 
Step 2983 | loss:2.133002996444702 lr:0.00014155126272017346 tokens_per_second_per_gpu:2187.6269012250805 
Step 2984 | loss:2.123873710632324 lr:0.00014151546850831988 tokens_per_second_per_gpu:2178.9764220224224 
Step 2985 | loss:2.121285915374756 lr:0.0001414796678685735 tokens_per_second_per_gpu:2165.4384909384266 
Step 2986 | loss:2.146514892578125 lr:0.00014144386080647734 tokens_per_second_per_gpu:2154.16352282751 
Step 2987 | loss:2.1874189376831055 lr:0.00014140804732757546 tokens_per_second_per_gpu:2178.211206205695 
Step 2988 | loss:2.084503650665283 lr:0.00014137222743741297 tokens_per_second_per_gpu:2188.506306262208 
Step 2989 | loss:2.152270793914795 lr:0.0001413364011415358 tokens_per_second_per_gpu:2069.42720051413 
Step 2990 | loss:2.119683265686035 lr:0.00014130056844549106 tokens_per_second_per_gpu:2197.496298142413 
Step 2991 | loss:2.0859079360961914 lr:0.00014126472935482677 tokens_per_second_per_gpu:2168.0605974109744 
Step 2992 | loss:2.1524786949157715 lr:0.00014122888387509193 tokens_per_second_per_gpu:2191.186547978312 
Step 2993 | loss:2.118556499481201 lr:0.0001411930320118365 tokens_per_second_per_gpu:2185.290108680417 
Step 2994 | loss:2.1210737228393555 lr:0.00014115717377061152 tokens_per_second_per_gpu:2154.966594193515 
Step 2995 | loss:2.127312183380127 lr:0.00014112130915696893 tokens_per_second_per_gpu:2067.014765740631 
Step 2996 | loss:2.0817008018493652 lr:0.00014108543817646174 tokens_per_second_per_gpu:2158.2479148081998 
Step 2997 | loss:2.129744052886963 lr:0.0001410495608346439 tokens_per_second_per_gpu:2031.319161051349 
Step 2998 | loss:2.13301682472229 lr:0.00014101367713707026 tokens_per_second_per_gpu:2108.121675005813 
Step 2999 | loss:2.1409833431243896 lr:0.00014097778708929682 tokens_per_second_per_gpu:2200.4228351249735 
Step 3000 | loss:2.144500255584717 lr:0.00014094189069688046 tokens_per_second_per_gpu:2144.8038096716436 
Step 3001 | loss:2.136641025543213 lr:0.00014090598796537906 tokens_per_second_per_gpu:2173.1315106989878 
Step 3002 | loss:2.0957655906677246 lr:0.0001408700789003515 tokens_per_second_per_gpu:2208.319643760593 
Step 3003 | loss:2.17684268951416 lr:0.0001408341635073576 tokens_per_second_per_gpu:2144.5945474267546 
Step 3004 | loss:2.1400671005249023 lr:0.00014079824179195823 tokens_per_second_per_gpu:2201.6675872091596 
Step 3005 | loss:2.0640487670898438 lr:0.00014076231375971513 tokens_per_second_per_gpu:2202.6105787011625 
Step 3006 | loss:2.0850024223327637 lr:0.00014072637941619113 tokens_per_second_per_gpu:2186.2835440532313 
Step 3007 | loss:2.0568671226501465 lr:0.00014069043876694997 tokens_per_second_per_gpu:2186.8084807534533 
Step 3008 | loss:2.105374813079834 lr:0.00014065449181755642 tokens_per_second_per_gpu:2183.352866155748 
Step 3009 | loss:2.115013599395752 lr:0.00014061853857357616 tokens_per_second_per_gpu:2153.3882962450593 
Step 3010 | loss:2.1726858615875244 lr:0.00014058257904057587 tokens_per_second_per_gpu:2193.831399537739 
Step 3011 | loss:2.1956067085266113 lr:0.00014054661322412325 tokens_per_second_per_gpu:2183.09404847786 
Step 3012 | loss:2.14066219329834 lr:0.0001405106411297869 tokens_per_second_per_gpu:2180.912107977293 
Step 3013 | loss:2.141223907470703 lr:0.00014047466276313642 tokens_per_second_per_gpu:2172.079101781139 
Step 3014 | loss:2.1277010440826416 lr:0.00014043867812974238 tokens_per_second_per_gpu:2193.0034118529607 
Step 3015 | loss:2.1142373085021973 lr:0.00014040268723517637 tokens_per_second_per_gpu:2159.238765586272 
Step 3016 | loss:2.1111278533935547 lr:0.0001403666900850109 tokens_per_second_per_gpu:2106.702378990798 
Step 3017 | loss:2.136819839477539 lr:0.0001403306866848194 tokens_per_second_per_gpu:2193.5232082176067 
Step 3018 | loss:2.1549625396728516 lr:0.00014029467704017637 tokens_per_second_per_gpu:2112.4961538238426 
Step 3019 | loss:2.160252094268799 lr:0.0001402586611566572 tokens_per_second_per_gpu:2117.795655694694 
Step 3020 | loss:2.206672191619873 lr:0.0001402226390398383 tokens_per_second_per_gpu:2117.309747388661 
Step 3021 | loss:2.1804308891296387 lr:0.00014018661069529706 tokens_per_second_per_gpu:2137.974961875883 
Step 3022 | loss:2.1595702171325684 lr:0.0001401505761286117 tokens_per_second_per_gpu:2186.481451302356 
Step 3023 | loss:2.177147388458252 lr:0.00014011453534536157 tokens_per_second_per_gpu:2187.715504317714 
Step 3024 | loss:2.159203052520752 lr:0.00014007848835112687 tokens_per_second_per_gpu:2145.4187741963437 
Step 3025 | loss:2.1361379623413086 lr:0.00014004243515148882 tokens_per_second_per_gpu:2192.2047815867236 
Step 3026 | loss:2.1194281578063965 lr:0.00014000637575202956 tokens_per_second_per_gpu:2174.480600555062 
Step 3027 | loss:2.148397445678711 lr:0.0001399703101583323 tokens_per_second_per_gpu:2191.931606399253 
Step 3028 | loss:2.185497760772705 lr:0.00013993423837598093 tokens_per_second_per_gpu:2167.6729764937 
Step 3029 | loss:2.077925682067871 lr:0.0001398981604105607 tokens_per_second_per_gpu:2161.5753330054085 
Step 3030 | loss:2.1354432106018066 lr:0.00013986207626765754 tokens_per_second_per_gpu:2159.3456445187876 
Step 3031 | loss:2.071056604385376 lr:0.00013982598595285833 tokens_per_second_per_gpu:2113.8764895286618 
Step 3032 | loss:2.0898358821868896 lr:0.00013978988947175108 tokens_per_second_per_gpu:2194.9691490202995 
Step 3033 | loss:2.1851794719696045 lr:0.00013975378682992457 tokens_per_second_per_gpu:2127.0579148642046 
Step 3034 | loss:2.1475274562835693 lr:0.00013971767803296867 tokens_per_second_per_gpu:2172.973934602401 
Step 3035 | loss:2.1284995079040527 lr:0.00013968156308647418 tokens_per_second_per_gpu:2119.4977419399083 
Step 3036 | loss:2.1422317028045654 lr:0.00013964544199603275 tokens_per_second_per_gpu:2170.64106105833 
Step 3037 | loss:2.164633274078369 lr:0.00013960931476723705 tokens_per_second_per_gpu:2180.5327834700356 
Step 3038 | loss:2.091376304626465 lr:0.00013957318140568077 tokens_per_second_per_gpu:2181.7805080537473 
Step 3039 | loss:2.150320529937744 lr:0.00013953704191695847 tokens_per_second_per_gpu:2169.567375894805 
Step 3040 | loss:2.1582584381103516 lr:0.00013950089630666564 tokens_per_second_per_gpu:2184.2140647427464 
Step 3041 | loss:2.128293991088867 lr:0.00013946474458039875 tokens_per_second_per_gpu:2148.4710835268743 
Step 3042 | loss:2.0788087844848633 lr:0.00013942858674375526 tokens_per_second_per_gpu:2095.445531122888 
Step 3043 | loss:2.187957286834717 lr:0.00013939242280233352 tokens_per_second_per_gpu:2190.6757867236256 
Step 3044 | loss:2.079326629638672 lr:0.00013935625276173278 tokens_per_second_per_gpu:2178.8734490652337 
Step 3045 | loss:2.1020424365997314 lr:0.00013932007662755338 tokens_per_second_per_gpu:2186.1179488404373 
Step 3046 | loss:2.144955635070801 lr:0.00013928389440539645 tokens_per_second_per_gpu:2162.069418548303 
Step 3047 | loss:2.1340231895446777 lr:0.00013924770610086422 tokens_per_second_per_gpu:2132.7009646032334 
Step 3048 | loss:2.0788161754608154 lr:0.0001392115117195597 tokens_per_second_per_gpu:2161.2723087240543 
Step 3049 | loss:2.1180434226989746 lr:0.00013917531126708688 tokens_per_second_per_gpu:2136.918180143082 
Step 3050 | loss:2.1857032775878906 lr:0.00013913910474905078 tokens_per_second_per_gpu:2177.9066662085693 
Step 3051 | loss:2.162947177886963 lr:0.0001391028921710573 tokens_per_second_per_gpu:2171.2269892916197 
Step 3052 | loss:2.0593221187591553 lr:0.00013906667353871322 tokens_per_second_per_gpu:2172.857366156733 
Step 3053 | loss:2.1265320777893066 lr:0.00013903044885762642 tokens_per_second_per_gpu:2138.314165978715 
Step 3054 | loss:2.1862239837646484 lr:0.00013899421813340552 tokens_per_second_per_gpu:2165.6866650107263 
Step 3055 | loss:2.090941905975342 lr:0.0001389579813716602 tokens_per_second_per_gpu:2078.5310453333745 
Step 3056 | loss:2.1208057403564453 lr:0.00013892173857800108 tokens_per_second_per_gpu:2161.954165736098 
Step 3057 | loss:2.137624502182007 lr:0.00013888548975803962 tokens_per_second_per_gpu:2167.560122870555 
Step 3058 | loss:2.195981025695801 lr:0.0001388492349173883 tokens_per_second_per_gpu:2117.597860998793 
Step 3059 | loss:2.1309914588928223 lr:0.00013881297406166053 tokens_per_second_per_gpu:2189.974612366197 
Step 3060 | loss:2.124052047729492 lr:0.00013877670719647056 tokens_per_second_per_gpu:2187.713380928978 
Step 3061 | loss:2.122823715209961 lr:0.00013874043432743368 tokens_per_second_per_gpu:2190.178462766105 
Step 3062 | loss:2.1333723068237305 lr:0.00013870415546016605 tokens_per_second_per_gpu:2205.0642689194556 
Step 3063 | loss:2.1991326808929443 lr:0.00013866787060028482 tokens_per_second_per_gpu:2129.5807489535664 
Step 3064 | loss:2.120405912399292 lr:0.00013863157975340791 tokens_per_second_per_gpu:2223.497769470285 
Step 3065 | loss:2.0837864875793457 lr:0.00013859528292515437 tokens_per_second_per_gpu:2169.9369080244373 
Step 3066 | loss:2.1256980895996094 lr:0.00013855898012114407 tokens_per_second_per_gpu:2176.1535012405243 
Step 3067 | loss:2.1336236000061035 lr:0.00013852267134699782 tokens_per_second_per_gpu:2223.64771271764 
Step 3068 | loss:2.2064738273620605 lr:0.00013848635660833734 tokens_per_second_per_gpu:2191.9413550256286 
Step 3069 | loss:2.133134365081787 lr:0.00013845003591078528 tokens_per_second_per_gpu:2223.9830346571516 
Step 3070 | loss:2.1722002029418945 lr:0.00013841370925996523 tokens_per_second_per_gpu:2231.0511237945097 
Step 3071 | loss:2.0451059341430664 lr:0.0001383773766615017 tokens_per_second_per_gpu:2217.8706730988965 
Step 3072 | loss:2.233525276184082 lr:0.00013834103812102012 tokens_per_second_per_gpu:2223.3132862345938 
Step 3073 | loss:2.114150047302246 lr:0.00013830469364414674 tokens_per_second_per_gpu:2174.835250322895 
Step 3074 | loss:2.090131998062134 lr:0.000138268343236509 tokens_per_second_per_gpu:2214.019786300106 
Step 3075 | loss:2.155155658721924 lr:0.00013823198690373492 tokens_per_second_per_gpu:2218.7090683081537 
Step 3076 | loss:2.1243896484375 lr:0.00013819562465145366 tokens_per_second_per_gpu:2222.309454097118 
Step 3077 | loss:2.13377046585083 lr:0.00013815925648529527 tokens_per_second_per_gpu:2196.8817030172595 
Step 3078 | loss:2.2152557373046875 lr:0.00013812288241089063 tokens_per_second_per_gpu:2225.1702840769126 
Step 3079 | loss:2.118793487548828 lr:0.00013808650243387155 tokens_per_second_per_gpu:2148.166846079492 
Step 3080 | loss:2.17141056060791 lr:0.00013805011655987083 tokens_per_second_per_gpu:2229.005092473673 
Step 3081 | loss:2.1617069244384766 lr:0.00013801372479452218 tokens_per_second_per_gpu:2229.1445311642324 
Step 3082 | loss:2.1097097396850586 lr:0.00013797732714346012 tokens_per_second_per_gpu:2183.991972667001 
Step 3083 | loss:2.1685502529144287 lr:0.0001379409236123202 tokens_per_second_per_gpu:2224.283590813853 
Step 3084 | loss:2.121154308319092 lr:0.00013790451420673877 tokens_per_second_per_gpu:2222.0616079440483 
Step 3085 | loss:2.1227126121520996 lr:0.00013786809893235317 tokens_per_second_per_gpu:2231.2803110777595 
Step 3086 | loss:2.1725826263427734 lr:0.00013783167779480166 tokens_per_second_per_gpu:2131.8873217146997 
Step 3087 | loss:2.113729953765869 lr:0.0001377952507997233 tokens_per_second_per_gpu:2216.6762147008544 
Step 3088 | loss:2.110152244567871 lr:0.00013775881795275816 tokens_per_second_per_gpu:2147.7339739061636 
Step 3089 | loss:2.1199238300323486 lr:0.0001377223792595472 tokens_per_second_per_gpu:2121.999371963725 
Step 3090 | loss:2.1173343658447266 lr:0.00013768593472573225 tokens_per_second_per_gpu:2150.703520100297 
Step 3091 | loss:2.1686038970947266 lr:0.00013764948435695607 tokens_per_second_per_gpu:2146.1773946588432 
Step 3092 | loss:2.185616970062256 lr:0.0001376130281588623 tokens_per_second_per_gpu:2223.290907738369 
Step 3093 | loss:2.054577350616455 lr:0.00013757656613709558 tokens_per_second_per_gpu:2220.170263407078 
Step 3094 | loss:2.133054733276367 lr:0.00013754009829730122 tokens_per_second_per_gpu:2221.691150613342 
Step 3095 | loss:2.169384002685547 lr:0.00013750362464512575 tokens_per_second_per_gpu:2224.3684641205577 
Step 3096 | loss:2.1162915229797363 lr:0.0001374671451862163 tokens_per_second_per_gpu:2228.1492273332915 
Step 3097 | loss:2.1535348892211914 lr:0.00013743065992622108 tokens_per_second_per_gpu:2158.936734426523 
Step 3098 | loss:2.166360378265381 lr:0.00013739416887078917 tokens_per_second_per_gpu:2226.128855094816 
Step 3099 | loss:2.1429591178894043 lr:0.00013735767202557053 tokens_per_second_per_gpu:2177.136802264455 
Step 3100 | loss:2.174133777618408 lr:0.00013732116939621592 tokens_per_second_per_gpu:2150.8109780551385 
Step 3101 | loss:2.1359663009643555 lr:0.00013728466098837725 tokens_per_second_per_gpu:2204.1823666324626 
Step 3102 | loss:2.0916337966918945 lr:0.00013724814680770702 tokens_per_second_per_gpu:2172.4634454276384 
Step 3103 | loss:2.130434274673462 lr:0.0001372116268598588 tokens_per_second_per_gpu:2222.9783828620093 
Step 3104 | loss:2.1299777030944824 lr:0.0001371751011504871 tokens_per_second_per_gpu:2157.299321681389 
Step 3105 | loss:2.111414909362793 lr:0.00013713856968524714 tokens_per_second_per_gpu:2225.317457023814 
Step 3106 | loss:2.165834426879883 lr:0.0001371020324697952 tokens_per_second_per_gpu:2201.909609316497 
Step 3107 | loss:2.1248254776000977 lr:0.00013706548950978833 tokens_per_second_per_gpu:2213.348620932266 
Step 3108 | loss:2.137540340423584 lr:0.00013702894081088455 tokens_per_second_per_gpu:2069.2274476405714 
Step 3109 | loss:2.1319174766540527 lr:0.00013699238637874275 tokens_per_second_per_gpu:2150.3480482718146 
Step 3110 | loss:2.1198058128356934 lr:0.00013695582621902272 tokens_per_second_per_gpu:2195.250857064277 
Step 3111 | loss:2.140817642211914 lr:0.00013691926033738508 tokens_per_second_per_gpu:2199.3178243248763 
Step 3112 | loss:2.1993021965026855 lr:0.00013688268873949134 tokens_per_second_per_gpu:2143.7814400036596 
Step 3113 | loss:2.1311793327331543 lr:0.000136846111431004 tokens_per_second_per_gpu:2220.241797344451 
Step 3114 | loss:2.1534571647644043 lr:0.00013680952841758635 tokens_per_second_per_gpu:2226.1991039060426 
Step 3115 | loss:2.1529946327209473 lr:0.00013677293970490258 tokens_per_second_per_gpu:2158.2216213020606 
Step 3116 | loss:2.1414072513580322 lr:0.00013673634529861773 tokens_per_second_per_gpu:2208.125191886577 
Step 3117 | loss:2.142078399658203 lr:0.0001366997452043978 tokens_per_second_per_gpu:2218.544551414344 
Step 3118 | loss:2.1271629333496094 lr:0.0001366631394279096 tokens_per_second_per_gpu:2201.443555986383 
Step 3119 | loss:2.140936851501465 lr:0.0001366265279748209 tokens_per_second_per_gpu:2151.9920399124367 
Step 3120 | loss:2.1210060119628906 lr:0.00013658991085080025 tokens_per_second_per_gpu:2212.3063418111983 
Step 3121 | loss:2.051022529602051 lr:0.00013655328806151714 tokens_per_second_per_gpu:2205.9682633558473 
Step 3122 | loss:2.0999155044555664 lr:0.00013651665961264192 tokens_per_second_per_gpu:2202.944511089034 
Step 3123 | loss:2.1322364807128906 lr:0.00013648002550984583 tokens_per_second_per_gpu:2205.955382689775 
Step 3124 | loss:2.130248546600342 lr:0.00013644338575880097 tokens_per_second_per_gpu:2128.4712161081034 
Step 3125 | loss:2.127373218536377 lr:0.00013640674036518032 tokens_per_second_per_gpu:2176.121519845494 
Step 3126 | loss:2.1236820220947266 lr:0.00013637008933465772 tokens_per_second_per_gpu:2052.241268040824 
Step 3127 | loss:2.1062283515930176 lr:0.0001363334326729079 tokens_per_second_per_gpu:2189.8323830278923 
Step 3128 | loss:2.1106719970703125 lr:0.0001362967703856065 tokens_per_second_per_gpu:2213.1017113075377 
Step 3129 | loss:2.120380401611328 lr:0.00013626010247842988 tokens_per_second_per_gpu:2215.842601277221 
Step 3130 | loss:2.1124022006988525 lr:0.00013622342895705552 tokens_per_second_per_gpu:2214.8913263311356 
Step 3131 | loss:2.108381748199463 lr:0.00013618674982716154 tokens_per_second_per_gpu:2135.5177597879706 
Step 3132 | loss:2.139451503753662 lr:0.000136150065094427 tokens_per_second_per_gpu:2208.804185074741 
Step 3133 | loss:2.164916753768921 lr:0.00013611337476453192 tokens_per_second_per_gpu:2225.846544525465 
Step 3134 | loss:2.0821757316589355 lr:0.00013607667884315706 tokens_per_second_per_gpu:2112.1094616332816 
Step 3135 | loss:2.1637649536132812 lr:0.0001360399773359841 tokens_per_second_per_gpu:2221.4397216654343 
Step 3136 | loss:2.148348331451416 lr:0.0001360032702486956 tokens_per_second_per_gpu:2186.7240905839417 
Step 3137 | loss:2.0991878509521484 lr:0.00013596655758697494 tokens_per_second_per_gpu:2225.781874529399 
Step 3138 | loss:2.1581356525421143 lr:0.0001359298393565064 tokens_per_second_per_gpu:2208.0549199559164 
Step 3139 | loss:2.1397600173950195 lr:0.0001358931155629751 tokens_per_second_per_gpu:2220.1664794915 
Step 3140 | loss:2.100712299346924 lr:0.00013585638621206706 tokens_per_second_per_gpu:2214.9335401596327 
Step 3141 | loss:2.0979132652282715 lr:0.0001358196513094691 tokens_per_second_per_gpu:2222.1345232787507 
Step 3142 | loss:2.078622817993164 lr:0.00013578291086086897 tokens_per_second_per_gpu:2205.7381903967344 
Step 3143 | loss:2.1122536659240723 lr:0.00013574616487195518 tokens_per_second_per_gpu:2216.8349213074844 
Step 3144 | loss:2.1873860359191895 lr:0.00013570941334841723 tokens_per_second_per_gpu:2148.10677631654 
Step 3145 | loss:2.1343894004821777 lr:0.00013567265629594534 tokens_per_second_per_gpu:2195.257208403109 
Step 3146 | loss:2.1653695106506348 lr:0.00013563589372023069 tokens_per_second_per_gpu:2191.062116499425 
Step 3147 | loss:2.1408028602600098 lr:0.0001355991256269653 tokens_per_second_per_gpu:2183.5109552453946 
Step 3148 | loss:2.081543445587158 lr:0.00013556235202184192 tokens_per_second_per_gpu:2225.3556517433494 
Step 3149 | loss:2.0782887935638428 lr:0.00013552557291055437 tokens_per_second_per_gpu:2215.7022838216503 
Step 3150 | loss:2.1817541122436523 lr:0.00013548878829879716 tokens_per_second_per_gpu:2203.738412347264 
Step 3151 | loss:2.082853317260742 lr:0.00013545199819226566 tokens_per_second_per_gpu:2217.299259864608 
Step 3152 | loss:2.1681294441223145 lr:0.0001354152025966562 tokens_per_second_per_gpu:2167.8446473550935 
Step 3153 | loss:2.2086212635040283 lr:0.00013537840151766587 tokens_per_second_per_gpu:2170.410808346208 
Step 3154 | loss:2.1248598098754883 lr:0.00013534159496099256 tokens_per_second_per_gpu:2139.060660636509 
Step 3155 | loss:2.117105484008789 lr:0.00013530478293233517 tokens_per_second_per_gpu:2221.912919505985 
Step 3156 | loss:2.0850987434387207 lr:0.0001352679654373933 tokens_per_second_per_gpu:2223.1871334521493 
Step 3157 | loss:2.1123437881469727 lr:0.00013523114248186746 tokens_per_second_per_gpu:2142.3945669427076 
Step 3158 | loss:2.1258692741394043 lr:0.00013519431407145902 tokens_per_second_per_gpu:2179.929205985056 
Step 3159 | loss:2.1134650707244873 lr:0.0001351574802118701 tokens_per_second_per_gpu:2215.979170876357 
Step 3160 | loss:2.1063952445983887 lr:0.0001351206409088038 tokens_per_second_per_gpu:2221.3000532035085 
Step 3161 | loss:2.1078925132751465 lr:0.00013508379616796398 tokens_per_second_per_gpu:2183.5266914489875 
Step 3162 | loss:2.1494579315185547 lr:0.00013504694599505537 tokens_per_second_per_gpu:2226.1378533853867 
Step 3163 | loss:2.140994071960449 lr:0.00013501009039578347 tokens_per_second_per_gpu:2181.283777371403 
Step 3164 | loss:2.1797547340393066 lr:0.00013497322937585475 tokens_per_second_per_gpu:2219.734225324908 
Step 3165 | loss:2.160470962524414 lr:0.00013493636294097642 tokens_per_second_per_gpu:2160.8137080430865 
Step 3166 | loss:2.0983614921569824 lr:0.00013489949109685655 tokens_per_second_per_gpu:2199.4997319467434 
Step 3167 | loss:2.1211042404174805 lr:0.00013486261384920408 tokens_per_second_per_gpu:2215.567052209046 
Step 3168 | loss:2.0915544033050537 lr:0.00013482573120372873 tokens_per_second_per_gpu:2184.074964528864 
Step 3169 | loss:2.0958657264709473 lr:0.0001347888431661411 tokens_per_second_per_gpu:2191.2695452047324 
Step 3170 | loss:2.074923038482666 lr:0.00013475194974215258 tokens_per_second_per_gpu:2228.55215723759 
Step 3171 | loss:2.1289329528808594 lr:0.00013471505093747555 tokens_per_second_per_gpu:2210.2484433646523 
Step 3172 | loss:2.1375675201416016 lr:0.0001346781467578229 tokens_per_second_per_gpu:2228.8188327312255 
Step 3173 | loss:2.112654447555542 lr:0.0001346412372089087 tokens_per_second_per_gpu:2210.3755526469736 
Step 3174 | loss:2.096639633178711 lr:0.0001346043222964477 tokens_per_second_per_gpu:2209.7898684695188 
Step 3175 | loss:2.109285354614258 lr:0.00013456740202615538 tokens_per_second_per_gpu:2138.1590940636975 
Step 3176 | loss:2.192622423171997 lr:0.00013453047640374827 tokens_per_second_per_gpu:2230.0804275347737 
Step 3177 | loss:2.0742499828338623 lr:0.00013449354543494354 tokens_per_second_per_gpu:2219.9002643241515 
Step 3178 | loss:2.055295705795288 lr:0.00013445660912545925 tokens_per_second_per_gpu:2228.0288082442294 
Step 3179 | loss:2.0613856315612793 lr:0.00013441966748101435 tokens_per_second_per_gpu:2224.794561458718 
Step 3180 | loss:2.0896382331848145 lr:0.00013438272050732853 tokens_per_second_per_gpu:2208.790824050278 
Step 3181 | loss:2.0463497638702393 lr:0.00013434576821012232 tokens_per_second_per_gpu:2213.172565890131 
Step 3182 | loss:2.1091971397399902 lr:0.00013430881059511713 tokens_per_second_per_gpu:2187.983064843725 
Step 3183 | loss:2.130920886993408 lr:0.00013427184766803515 tokens_per_second_per_gpu:2157.5312248032797 
Step 3184 | loss:2.0478477478027344 lr:0.00013423487943459934 tokens_per_second_per_gpu:2223.094348279043 
Step 3185 | loss:2.0929319858551025 lr:0.00013419790590053364 tokens_per_second_per_gpu:2208.168629732273 
Step 3186 | loss:2.1362593173980713 lr:0.00013416092707156261 tokens_per_second_per_gpu:2199.6466821989566 
Step 3187 | loss:2.095121145248413 lr:0.00013412394295341174 tokens_per_second_per_gpu:2208.5044492752713 
Step 3188 | loss:2.112063407897949 lr:0.00013408695355180742 tokens_per_second_per_gpu:2227.27079144516 
Step 3189 | loss:2.0667190551757812 lr:0.0001340499588724767 tokens_per_second_per_gpu:2196.1296759780057 
Step 3190 | loss:2.1563587188720703 lr:0.0001340129589211475 tokens_per_second_per_gpu:2222.9523710641506 
Step 3191 | loss:2.1039013862609863 lr:0.00013397595370354855 tokens_per_second_per_gpu:2216.642374948777 
Step 3192 | loss:2.110055446624756 lr:0.0001339389432254095 tokens_per_second_per_gpu:2179.367523087819 
Step 3193 | loss:2.0997490882873535 lr:0.0001339019274924607 tokens_per_second_per_gpu:2145.234606888104 
Step 3194 | loss:2.0922069549560547 lr:0.00013386490651043326 tokens_per_second_per_gpu:2216.583356158585 
Step 3195 | loss:2.0875444412231445 lr:0.0001338278802850593 tokens_per_second_per_gpu:2198.195703463999 
Step 3196 | loss:2.1526131629943848 lr:0.00013379084882207158 tokens_per_second_per_gpu:2175.9526669976403 
Step 3197 | loss:2.1010942459106445 lr:0.00013375381212720372 tokens_per_second_per_gpu:2225.4249427466007 
Step 3198 | loss:2.1118383407592773 lr:0.0001337167702061902 tokens_per_second_per_gpu:2216.807028112912 
Step 3199 | loss:2.103503704071045 lr:0.0001336797230647662 tokens_per_second_per_gpu:2179.2520891139816 
Step 3200 | loss:2.156045913696289 lr:0.00013364267070866786 tokens_per_second_per_gpu:2198.9281848719165 
Step 3201 | loss:2.120786666870117 lr:0.00013360561314363202 tokens_per_second_per_gpu:2212.464693846033 
Step 3202 | loss:2.128357172012329 lr:0.00013356855037539625 tokens_per_second_per_gpu:2226.8034354308415 
Step 3203 | loss:2.127493143081665 lr:0.0001335314824096992 tokens_per_second_per_gpu:2196.1076292930256 
Step 3204 | loss:2.111262559890747 lr:0.00013349440925228002 tokens_per_second_per_gpu:2146.0560241260055 
Step 3205 | loss:2.0893216133117676 lr:0.00013345733090887882 tokens_per_second_per_gpu:2221.073364583679 
Step 3206 | loss:2.119943618774414 lr:0.00013342024738523652 tokens_per_second_per_gpu:2195.82492951343 
Step 3207 | loss:2.110499382019043 lr:0.00013338315868709476 tokens_per_second_per_gpu:2140.8175782677845 
Step 3208 | loss:2.0849132537841797 lr:0.00013334606482019607 tokens_per_second_per_gpu:2206.446893861571 
Step 3209 | loss:2.1834335327148438 lr:0.00013330896579028377 tokens_per_second_per_gpu:2209.0562544815625 
Step 3210 | loss:2.116334915161133 lr:0.00013327186160310184 tokens_per_second_per_gpu:2162.973880643647 
Step 3211 | loss:2.1229045391082764 lr:0.0001332347522643953 tokens_per_second_per_gpu:2174.1352252822558 
Step 3212 | loss:2.1796131134033203 lr:0.00013319763777990974 tokens_per_second_per_gpu:2172.512324660893 
Step 3213 | loss:2.0757265090942383 lr:0.0001331605181553917 tokens_per_second_per_gpu:2148.7355992420244 
Step 3214 | loss:2.1192800998687744 lr:0.0001331233933965884 tokens_per_second_per_gpu:2211.716441934383 
Step 3215 | loss:2.1029562950134277 lr:0.00013308626350924798 tokens_per_second_per_gpu:2232.6863564758883 
Step 3216 | loss:2.167618751525879 lr:0.00013304912849911927 tokens_per_second_per_gpu:2184.7762662635255 
Step 3217 | loss:2.104128837585449 lr:0.00013301198837195195 tokens_per_second_per_gpu:2231.165470394709 
Step 3218 | loss:2.1366710662841797 lr:0.00013297484313349643 tokens_per_second_per_gpu:2184.859991406549 
Step 3219 | loss:2.115891933441162 lr:0.00013293769278950403 tokens_per_second_per_gpu:2229.12115605261 
Step 3220 | loss:2.152928352355957 lr:0.0001329005373457267 tokens_per_second_per_gpu:2200.6407121709085 
Step 3221 | loss:2.085513114929199 lr:0.00013286337680791733 tokens_per_second_per_gpu:2226.0573118690654 
Step 3222 | loss:2.113292694091797 lr:0.00013282621118182952 tokens_per_second_per_gpu:2220.8148381973015 
Step 3223 | loss:2.057478904724121 lr:0.00013278904047321762 tokens_per_second_per_gpu:2226.246115955239 
Step 3224 | loss:2.148529291152954 lr:0.00013275186468783687 tokens_per_second_per_gpu:2219.916412795519 
Step 3225 | loss:2.09501314163208 lr:0.00013271468383144324 tokens_per_second_per_gpu:2183.5952606409255 
Step 3226 | loss:2.1631524562835693 lr:0.0001326774979097935 tokens_per_second_per_gpu:2221.291864167877 
Step 3227 | loss:2.1104462146759033 lr:0.00013264030692864513 tokens_per_second_per_gpu:2192.80607039785 
Step 3228 | loss:2.120002269744873 lr:0.00013260311089375657 tokens_per_second_per_gpu:2152.674126241946 
Step 3229 | loss:2.138580083847046 lr:0.00013256590981088677 tokens_per_second_per_gpu:2230.3904955504095 
Step 3230 | loss:2.1101748943328857 lr:0.0001325287036857958 tokens_per_second_per_gpu:2189.7927352388274 
Step 3231 | loss:2.1778724193573 lr:0.0001324914925242442 tokens_per_second_per_gpu:2212.9762530811277 
Step 3232 | loss:2.0757923126220703 lr:0.00013245427633199345 tokens_per_second_per_gpu:1946.0358811739122 
Step 3233 | loss:2.0953614711761475 lr:0.00013241705511480586 tokens_per_second_per_gpu:2196.5253407995897 
Step 3234 | loss:2.118623733520508 lr:0.0001323798288784443 tokens_per_second_per_gpu:2198.9890345831277 
Step 3235 | loss:2.117755651473999 lr:0.00013234259762867265 tokens_per_second_per_gpu:2146.51366570196 
Step 3236 | loss:2.0951356887817383 lr:0.0001323053613712555 tokens_per_second_per_gpu:2212.831339256246 
Step 3237 | loss:2.106182336807251 lr:0.0001322681201119581 tokens_per_second_per_gpu:2197.3428141269574 
Step 3238 | loss:2.1498420238494873 lr:0.00013223087385654659 tokens_per_second_per_gpu:2223.606574864127 
Step 3239 | loss:2.1488897800445557 lr:0.00013219362261078786 tokens_per_second_per_gpu:2231.6695706715573 
Step 3240 | loss:2.0953776836395264 lr:0.0001321563663804496 tokens_per_second_per_gpu:2197.261513877355 
Step 3241 | loss:2.160151958465576 lr:0.00013211910517130023 tokens_per_second_per_gpu:2207.162004120865 
Step 3242 | loss:2.185413360595703 lr:0.00013208183898910888 tokens_per_second_per_gpu:2217.584649582254 
Step 3243 | loss:2.111876964569092 lr:0.00013204456783964564 tokens_per_second_per_gpu:2213.2584902248354 
Step 3244 | loss:2.1355137825012207 lr:0.00013200729172868113 tokens_per_second_per_gpu:2194.9674010707067 
Step 3245 | loss:2.1633713245391846 lr:0.00013197001066198692 tokens_per_second_per_gpu:2166.621354706579 
Step 3246 | loss:2.1121530532836914 lr:0.0001319327246453353 tokens_per_second_per_gpu:2189.536606997546 
Step 3247 | loss:2.1664867401123047 lr:0.00013189543368449927 tokens_per_second_per_gpu:2201.472202954177 
Step 3248 | loss:2.1267430782318115 lr:0.00013185813778525263 tokens_per_second_per_gpu:2201.0172270271432 
Step 3249 | loss:2.13319730758667 lr:0.00013182083695337005 tokens_per_second_per_gpu:2154.043654583126 
Step 3250 | loss:2.1612656116485596 lr:0.00013178353119462673 tokens_per_second_per_gpu:2227.2104481391357 
Step 3251 | loss:2.109333038330078 lr:0.00013174622051479883 tokens_per_second_per_gpu:2178.115211617211 
Step 3252 | loss:2.130246162414551 lr:0.00013170890491966323 tokens_per_second_per_gpu:2215.3152908077122 
Step 3253 | loss:2.0931057929992676 lr:0.00013167158441499752 tokens_per_second_per_gpu:2075.645002260415 
Step 3254 | loss:2.104121208190918 lr:0.0001316342590065801 tokens_per_second_per_gpu:2005.135188971834 
Step 3255 | loss:2.1061153411865234 lr:0.0001315969287001901 tokens_per_second_per_gpu:2204.9032045878675 
Step 3256 | loss:2.1260008811950684 lr:0.00013155959350160738 tokens_per_second_per_gpu:2224.546390714171 
Step 3257 | loss:2.165316581726074 lr:0.0001315222534166127 tokens_per_second_per_gpu:2154.656629743694 
Step 3258 | loss:2.131338119506836 lr:0.00013148490845098736 tokens_per_second_per_gpu:2213.613600768728 
Step 3259 | loss:2.1556711196899414 lr:0.0001314475586105136 tokens_per_second_per_gpu:2204.3071530639995 
Step 3260 | loss:2.1159932613372803 lr:0.00013141020390097433 tokens_per_second_per_gpu:2206.782847236425 
Step 3261 | loss:2.1210269927978516 lr:0.00013137284432815323 tokens_per_second_per_gpu:2227.7862726316016 
Step 3262 | loss:2.1588892936706543 lr:0.0001313354798978347 tokens_per_second_per_gpu:2178.911608632051 
Step 3263 | loss:2.1395156383514404 lr:0.00013129811061580394 tokens_per_second_per_gpu:2160.4348216562717 
Step 3264 | loss:2.082219123840332 lr:0.00013126073648784688 tokens_per_second_per_gpu:2157.5906001145863 
Step 3265 | loss:2.1154024600982666 lr:0.00013122335751975021 tokens_per_second_per_gpu:2228.118168096422 
Step 3266 | loss:2.085373640060425 lr:0.00013118597371730137 tokens_per_second_per_gpu:2198.1768119848534 
Step 3267 | loss:2.1758203506469727 lr:0.00013114858508628857 tokens_per_second_per_gpu:2228.030116240602 
Step 3268 | loss:2.1327664852142334 lr:0.00013111119163250064 tokens_per_second_per_gpu:2223.593838912941 
Step 3269 | loss:2.223632335662842 lr:0.00013107379336172733 tokens_per_second_per_gpu:2204.675929898286 
Step 3270 | loss:2.1612253189086914 lr:0.0001310363902797591 tokens_per_second_per_gpu:2227.281408743706 
Step 3271 | loss:2.059906005859375 lr:0.00013099898239238704 tokens_per_second_per_gpu:2227.544751253951 
Step 3272 | loss:2.149695873260498 lr:0.00013096156970540305 tokens_per_second_per_gpu:2210.065653419412 
Step 3273 | loss:2.169299364089966 lr:0.00013092415222459988 tokens_per_second_per_gpu:2213.8817984224024 
Step 3274 | loss:2.1074304580688477 lr:0.00013088672995577086 tokens_per_second_per_gpu:2206.778568943042 
Step 3275 | loss:2.1494991779327393 lr:0.00013084930290471012 tokens_per_second_per_gpu:2175.2043965649805 
Step 3276 | loss:2.0781774520874023 lr:0.00013081187107721255 tokens_per_second_per_gpu:2204.6737847203026 
Step 3277 | loss:2.162928819656372 lr:0.0001307744344790738 tokens_per_second_per_gpu:2225.1255957863777 
Step 3278 | loss:2.144648313522339 lr:0.00013073699311609015 tokens_per_second_per_gpu:2215.5751318924895 
Step 3279 | loss:2.081240653991699 lr:0.00013069954699405876 tokens_per_second_per_gpu:2186.419777191344 
Step 3280 | loss:2.1012988090515137 lr:0.00013066209611877746 tokens_per_second_per_gpu:2224.819114612444 
Step 3281 | loss:2.1623058319091797 lr:0.0001306246404960448 tokens_per_second_per_gpu:2156.008966500056 
Step 3282 | loss:2.0793027877807617 lr:0.00013058718013166004 tokens_per_second_per_gpu:2224.087566581856 
Step 3283 | loss:2.166466236114502 lr:0.0001305497150314233 tokens_per_second_per_gpu:2211.9734916275333 
Step 3284 | loss:2.142030954360962 lr:0.0001305122452011353 tokens_per_second_per_gpu:2131.262726351729 
Step 3285 | loss:2.109567642211914 lr:0.00013047477064659753 tokens_per_second_per_gpu:2212.637702968871 
Step 3286 | loss:2.1329264640808105 lr:0.00013043729137361223 tokens_per_second_per_gpu:2172.5219337827857 
Step 3287 | loss:2.1244828701019287 lr:0.00013039980738798244 tokens_per_second_per_gpu:2130.8842926470174 
Step 3288 | loss:2.1435232162475586 lr:0.0001303623186955117 tokens_per_second_per_gpu:2213.4211181897867 
Step 3289 | loss:2.157349109649658 lr:0.00013032482530200457 tokens_per_second_per_gpu:2225.9079821113173 
Step 3290 | loss:2.1578240394592285 lr:0.00013028732721326612 tokens_per_second_per_gpu:2146.9258181266914 
Step 3291 | loss:2.101787805557251 lr:0.0001302498244351023 tokens_per_second_per_gpu:2210.5550866334393 
Step 3292 | loss:2.113114833831787 lr:0.00013021231697331963 tokens_per_second_per_gpu:2219.7796258397498 
Step 3293 | loss:2.140164852142334 lr:0.0001301748048337255 tokens_per_second_per_gpu:2225.183929546428 
Step 3294 | loss:2.148183584213257 lr:0.00013013728802212793 tokens_per_second_per_gpu:2100.5761938919736 
Step 3295 | loss:2.1398396492004395 lr:0.0001300997665443357 tokens_per_second_per_gpu:2203.715621502938 
Step 3296 | loss:2.167841911315918 lr:0.00013006224040615832 tokens_per_second_per_gpu:2227.984019718647 
Step 3297 | loss:2.1169815063476562 lr:0.000130024709613406 tokens_per_second_per_gpu:2213.5814192503863 
Step 3298 | loss:2.1163225173950195 lr:0.0001299871741718897 tokens_per_second_per_gpu:2231.7276401347217 
Step 3299 | loss:2.1342592239379883 lr:0.00012994963408742102 tokens_per_second_per_gpu:2226.7454049636094 
Step 3300 | loss:2.132143020629883 lr:0.00012991208936581242 tokens_per_second_per_gpu:2179.821866554738 
Step 3301 | loss:2.0646519660949707 lr:0.00012987454001287695 tokens_per_second_per_gpu:2136.5064551331147 
Step 3302 | loss:2.062530994415283 lr:0.00012983698603442843 tokens_per_second_per_gpu:2186.222239534625 
Step 3303 | loss:2.108006477355957 lr:0.0001297994274362814 tokens_per_second_per_gpu:2234.4990491624753 
Step 3304 | loss:2.177163600921631 lr:0.0001297618642242511 tokens_per_second_per_gpu:2170.4881662639978 
Step 3305 | loss:2.1085939407348633 lr:0.00012972429640415348 tokens_per_second_per_gpu:2226.673890393003 
Step 3306 | loss:2.1604228019714355 lr:0.0001296867239818052 tokens_per_second_per_gpu:2199.9390562129156 
Step 3307 | loss:2.1298012733459473 lr:0.0001296491469630237 tokens_per_second_per_gpu:2190.779943171092 
Step 3308 | loss:2.0492608547210693 lr:0.00012961156535362705 tokens_per_second_per_gpu:2163.591086288854 
Step 3309 | loss:2.139591693878174 lr:0.00012957397915943402 tokens_per_second_per_gpu:2124.881161480257 
Step 3310 | loss:2.0861639976501465 lr:0.00012953638838626418 tokens_per_second_per_gpu:2230.473950359024 
Step 3311 | loss:2.0353832244873047 lr:0.00012949879303993775 tokens_per_second_per_gpu:2222.2736454185815 
Step 3312 | loss:2.1204934120178223 lr:0.00012946119312627565 tokens_per_second_per_gpu:2166.608798743911 
Step 3313 | loss:2.1209747791290283 lr:0.0001294235886510995 tokens_per_second_per_gpu:2219.8654048018866 
Step 3314 | loss:2.1183221340179443 lr:0.00012938597962023173 tokens_per_second_per_gpu:2230.2189551701945 
Step 3315 | loss:2.120342969894409 lr:0.0001293483660394953 tokens_per_second_per_gpu:2206.3580712156117 
Step 3316 | loss:2.0824062824249268 lr:0.00012931074791471401 tokens_per_second_per_gpu:2179.433068023919 
Step 3317 | loss:2.042391538619995 lr:0.00012927312525171236 tokens_per_second_per_gpu:2168.137675108165 
Step 3318 | loss:2.0989904403686523 lr:0.00012923549805631546 tokens_per_second_per_gpu:2189.0947487951476 
Step 3319 | loss:2.0973806381225586 lr:0.00012919786633434915 tokens_per_second_per_gpu:2188.6222162688946 
Step 3320 | loss:2.13706111907959 lr:0.0001291602300916401 tokens_per_second_per_gpu:2232.3244756067447 
Step 3321 | loss:2.131519317626953 lr:0.0001291225893340155 tokens_per_second_per_gpu:2205.3180640671494 
Step 3322 | loss:2.180675983428955 lr:0.0001290849440673033 tokens_per_second_per_gpu:2220.6795223854424 
Step 3323 | loss:2.078331232070923 lr:0.00012904729429733222 tokens_per_second_per_gpu:2208.163652898705 
Step 3324 | loss:2.084484100341797 lr:0.0001290096400299316 tokens_per_second_per_gpu:2170.54569931514 
Step 3325 | loss:2.086747407913208 lr:0.0001289719812709315 tokens_per_second_per_gpu:2231.876827328062 
Step 3326 | loss:2.1184170246124268 lr:0.00012893431802616268 tokens_per_second_per_gpu:2182.1252075274506 
Step 3327 | loss:2.139439582824707 lr:0.0001288966503014566 tokens_per_second_per_gpu:2170.183068751537 
Step 3328 | loss:2.1214799880981445 lr:0.00012885897810264532 tokens_per_second_per_gpu:2167.860366841875 
Step 3329 | loss:2.118408203125 lr:0.00012882130143556178 tokens_per_second_per_gpu:2194.3298990522662 
Step 3330 | loss:2.1103715896606445 lr:0.00012878362030603946 tokens_per_second_per_gpu:2203.4094485681694 
Step 3331 | loss:2.0816478729248047 lr:0.00012874593471991257 tokens_per_second_per_gpu:2158.170263824246 
Step 3332 | loss:2.168890953063965 lr:0.000128708244683016 tokens_per_second_per_gpu:2225.759703841534 
Step 3333 | loss:2.0820696353912354 lr:0.00012867055020118542 tokens_per_second_per_gpu:2204.863050472068 
Step 3334 | loss:2.093790054321289 lr:0.00012863285128025703 tokens_per_second_per_gpu:2209.2386072867284 
Step 3335 | loss:2.0679712295532227 lr:0.00012859514792606786 tokens_per_second_per_gpu:2163.8975872298006 
Step 3336 | loss:2.1114463806152344 lr:0.00012855744014445553 tokens_per_second_per_gpu:2231.8254351591117 
Step 3337 | loss:2.076371192932129 lr:0.00012851972794125847 tokens_per_second_per_gpu:2236.749623954867 
Step 3338 | loss:2.156048536300659 lr:0.00012848201132231556 tokens_per_second_per_gpu:2231.852233052139 
Step 3339 | loss:2.0879855155944824 lr:0.00012844429029346664 tokens_per_second_per_gpu:2227.4274625214653 
Step 3340 | loss:2.1102213859558105 lr:0.000128406564860552 tokens_per_second_per_gpu:2178.694632735585 
Step 3341 | loss:2.1038107872009277 lr:0.00012836883502941282 tokens_per_second_per_gpu:2197.1690876210614 
Step 3342 | loss:2.1660401821136475 lr:0.00012833110080589082 tokens_per_second_per_gpu:2221.4860497012533 
Step 3343 | loss:2.0854673385620117 lr:0.00012829336219582842 tokens_per_second_per_gpu:2184.0382360496287 
Step 3344 | loss:2.1080193519592285 lr:0.00012825561920506873 tokens_per_second_per_gpu:2220.9886994409967 
Step 3345 | loss:2.1175427436828613 lr:0.0001282178718394556 tokens_per_second_per_gpu:2120.4506317909095 
Step 3346 | loss:2.1088690757751465 lr:0.00012818012010483342 tokens_per_second_per_gpu:2219.7446948589827 
Step 3347 | loss:2.1283822059631348 lr:0.00012814236400704738 tokens_per_second_per_gpu:2216.2122261444633 
Step 3348 | loss:2.158027172088623 lr:0.00012810460355194335 tokens_per_second_per_gpu:2211.415175420061 
Step 3349 | loss:2.1496191024780273 lr:0.00012806683874536776 tokens_per_second_per_gpu:2230.9712126005143 
Step 3350 | loss:2.046407461166382 lr:0.0001280290695931678 tokens_per_second_per_gpu:2207.0444809626974 
Step 3351 | loss:2.143282175064087 lr:0.00012799129610119138 tokens_per_second_per_gpu:2202.3025226407317 
Step 3352 | loss:2.076014280319214 lr:0.00012795351827528693 tokens_per_second_per_gpu:2195.49164427999 
Step 3353 | loss:2.061811923980713 lr:0.00012791573612130365 tokens_per_second_per_gpu:2212.9688770758034 
Step 3354 | loss:2.099285125732422 lr:0.00012787794964509147 tokens_per_second_per_gpu:2213.6929380973093 
Step 3355 | loss:2.086820363998413 lr:0.00012784015885250084 tokens_per_second_per_gpu:2178.5825970493115 
Step 3356 | loss:2.138989210128784 lr:0.00012780236374938298 tokens_per_second_per_gpu:2172.9708845649097 
Step 3357 | loss:2.1269218921661377 lr:0.00012776456434158978 tokens_per_second_per_gpu:2223.7077155805705 
Step 3358 | loss:2.075627326965332 lr:0.00012772676063497375 tokens_per_second_per_gpu:2232.854535550045 
Step 3359 | loss:2.1076126098632812 lr:0.00012768895263538807 tokens_per_second_per_gpu:2221.984582935897 
Step 3360 | loss:2.069700241088867 lr:0.00012765114034868664 tokens_per_second_per_gpu:2130.0237997448603 
Step 3361 | loss:2.1230416297912598 lr:0.00012761332378072397 tokens_per_second_per_gpu:2216.234731383122 
Step 3362 | loss:2.148420810699463 lr:0.0001275755029373552 tokens_per_second_per_gpu:2234.62662024322 
Step 3363 | loss:2.1405739784240723 lr:0.00012753767782443625 tokens_per_second_per_gpu:2203.5015716939206 
Step 3364 | loss:2.060805320739746 lr:0.0001274998484478236 tokens_per_second_per_gpu:2197.845730268506 
Step 3365 | loss:2.0500905513763428 lr:0.0001274620148133744 tokens_per_second_per_gpu:2107.6238814751055 
Step 3366 | loss:2.2043681144714355 lr:0.00012742417692694651 tokens_per_second_per_gpu:2166.5297263246675 
Step 3367 | loss:2.11373233795166 lr:0.0001273863347943984 tokens_per_second_per_gpu:2168.474383762997 
Step 3368 | loss:2.076366424560547 lr:0.00012734848842158925 tokens_per_second_per_gpu:2213.9872782363323 
Step 3369 | loss:2.100161552429199 lr:0.0001273106378143788 tokens_per_second_per_gpu:2168.231663835008 
Step 3370 | loss:2.104975938796997 lr:0.00012727278297862757 tokens_per_second_per_gpu:2211.8711935456995 
Step 3371 | loss:2.0426697731018066 lr:0.00012723492392019664 tokens_per_second_per_gpu:2185.677622579421 
Step 3372 | loss:2.058128833770752 lr:0.00012719706064494779 tokens_per_second_per_gpu:2230.716714186352 
Step 3373 | loss:2.1335604190826416 lr:0.00012715919315874343 tokens_per_second_per_gpu:2198.8721066620656 
Step 3374 | loss:2.1532654762268066 lr:0.0001271213214674466 tokens_per_second_per_gpu:2201.862492722913 
Step 3375 | loss:2.15073299407959 lr:0.0001270834455769211 tokens_per_second_per_gpu:2214.93623400021 
Step 3376 | loss:2.1473934650421143 lr:0.00012704556549303123 tokens_per_second_per_gpu:2236.5987096375375 
Step 3377 | loss:2.1481378078460693 lr:0.00012700768122164203 tokens_per_second_per_gpu:2222.768743502784 
Step 3378 | loss:2.1427440643310547 lr:0.0001269697927686192 tokens_per_second_per_gpu:2197.4247471278827 
Step 3379 | loss:2.1543591022491455 lr:0.00012693190013982904 tokens_per_second_per_gpu:2157.896356410592 
Step 3380 | loss:2.112976551055908 lr:0.0001268940033411385 tokens_per_second_per_gpu:2175.7088330170263 
Step 3381 | loss:2.130882978439331 lr:0.0001268561023784152 tokens_per_second_per_gpu:2209.137831309452 
Step 3382 | loss:2.107581615447998 lr:0.00012681819725752735 tokens_per_second_per_gpu:2168.315100871976 
Step 3383 | loss:2.110797882080078 lr:0.00012678028798434395 tokens_per_second_per_gpu:2206.5392386925164 
Step 3384 | loss:2.1723194122314453 lr:0.00012674237456473443 tokens_per_second_per_gpu:2210.363628296133 
Step 3385 | loss:2.133641242980957 lr:0.0001267044570045691 tokens_per_second_per_gpu:2186.613613977156 
Step 3386 | loss:2.1167197227478027 lr:0.00012666653530971864 tokens_per_second_per_gpu:2127.4298759026756 
Step 3387 | loss:2.0843143463134766 lr:0.00012662860948605458 tokens_per_second_per_gpu:2174.4927704374672 
Step 3388 | loss:2.1308298110961914 lr:0.0001265906795394491 tokens_per_second_per_gpu:2138.7886639087237 
Step 3389 | loss:2.1080777645111084 lr:0.0001265527454757748 tokens_per_second_per_gpu:2213.489811900823 
Step 3390 | loss:2.1070916652679443 lr:0.00012651480730090518 tokens_per_second_per_gpu:2174.3198587619327 
Step 3391 | loss:2.0834784507751465 lr:0.00012647686502071417 tokens_per_second_per_gpu:2214.159732327222 
Step 3392 | loss:2.0757014751434326 lr:0.00012643891864107644 tokens_per_second_per_gpu:2203.9952585089823 
Step 3393 | loss:2.1063318252563477 lr:0.00012640096816786734 tokens_per_second_per_gpu:2180.535324392289 
Step 3394 | loss:2.2065248489379883 lr:0.0001263630136069627 tokens_per_second_per_gpu:2137.567500135929 
Step 3395 | loss:2.1048426628112793 lr:0.00012632505496423913 tokens_per_second_per_gpu:2213.8850319931503 
Step 3396 | loss:2.121438503265381 lr:0.0001262870922455738 tokens_per_second_per_gpu:2229.1895449388912 
Step 3397 | loss:2.151285409927368 lr:0.00012624912545684453 tokens_per_second_per_gpu:2151.3474920181425 
Step 3398 | loss:2.1335902214050293 lr:0.00012621115460392977 tokens_per_second_per_gpu:2237.2256961589615 
Step 3399 | loss:2.1139888763427734 lr:0.0001261731796927086 tokens_per_second_per_gpu:2219.3062397183808 
Step 3400 | loss:2.0631775856018066 lr:0.0001261352007290607 tokens_per_second_per_gpu:2233.6642749410667 
Step 3401 | loss:2.192201852798462 lr:0.00012609721771886638 tokens_per_second_per_gpu:2233.5993423781424 
Step 3402 | loss:2.1998276710510254 lr:0.00012605923066800668 tokens_per_second_per_gpu:2192.8807785834006 
Step 3403 | loss:2.174248218536377 lr:0.0001260212395823631 tokens_per_second_per_gpu:2207.260668976273 
Step 3404 | loss:2.144772529602051 lr:0.00012598324446781787 tokens_per_second_per_gpu:2211.6530624579323 
Step 3405 | loss:2.1267685890197754 lr:0.00012594524533025386 tokens_per_second_per_gpu:2140.1843791861825 
Step 3406 | loss:2.1297292709350586 lr:0.00012590724217555448 tokens_per_second_per_gpu:2181.204290945147 
Step 3407 | loss:2.0816140174865723 lr:0.00012586923500960387 tokens_per_second_per_gpu:2213.9598692697123 
Step 3408 | loss:2.136143207550049 lr:0.00012583122383828666 tokens_per_second_per_gpu:2156.4208082485725 
Step 3409 | loss:2.0714306831359863 lr:0.00012579320866748818 tokens_per_second_per_gpu:2214.2118925747363 
Step 3410 | loss:2.195950508117676 lr:0.00012575518950309436 tokens_per_second_per_gpu:2198.258397097113 
Step 3411 | loss:2.0988173484802246 lr:0.0001257171663509918 tokens_per_second_per_gpu:2191.3354454117957 
Step 3412 | loss:2.070138454437256 lr:0.00012567913921706766 tokens_per_second_per_gpu:2230.1355391844813 
Step 3413 | loss:2.1607043743133545 lr:0.0001256411081072097 tokens_per_second_per_gpu:2235.8798192285317 
Step 3414 | loss:2.0938668251037598 lr:0.00012560307302730635 tokens_per_second_per_gpu:2198.1757696164486 
Step 3415 | loss:2.1806936264038086 lr:0.00012556503398324664 tokens_per_second_per_gpu:2227.9153049081942 
Step 3416 | loss:2.167099952697754 lr:0.00012552699098092014 tokens_per_second_per_gpu:2131.4506737984207 
Step 3417 | loss:2.0946617126464844 lr:0.00012548894402621719 tokens_per_second_per_gpu:2197.503518008933 
Step 3418 | loss:2.086897373199463 lr:0.0001254508931250286 tokens_per_second_per_gpu:2215.4754798482413 
Step 3419 | loss:2.0335946083068848 lr:0.00012541283828324578 tokens_per_second_per_gpu:2202.8260947979397 
Step 3420 | loss:2.162501335144043 lr:0.00012537477950676093 tokens_per_second_per_gpu:2219.252316092749 
Step 3421 | loss:2.090087413787842 lr:0.00012533671680146666 tokens_per_second_per_gpu:2070.6378291282545 
Step 3422 | loss:2.1568007469177246 lr:0.00012529865017325625 tokens_per_second_per_gpu:2186.15267287551 
Step 3423 | loss:2.1574366092681885 lr:0.0001252605796280237 tokens_per_second_per_gpu:2210.0231494021973 
Step 3424 | loss:2.1449975967407227 lr:0.00012522250517166343 tokens_per_second_per_gpu:2220.993439116704 
Step 3425 | loss:2.084404945373535 lr:0.00012518442681007058 tokens_per_second_per_gpu:2225.2937792255893 
Step 3426 | loss:2.0850610733032227 lr:0.00012514634454914092 tokens_per_second_per_gpu:2229.704238748394 
Step 3427 | loss:2.0615177154541016 lr:0.0001251082583947707 tokens_per_second_per_gpu:2204.545072211984 
Step 3428 | loss:2.0691888332366943 lr:0.00012507016835285688 tokens_per_second_per_gpu:2228.5875639645637 
Step 3429 | loss:2.0789670944213867 lr:0.00012503207442929697 tokens_per_second_per_gpu:2202.2899472525414 
Step 3430 | loss:2.121757745742798 lr:0.00012499397662998917 tokens_per_second_per_gpu:2188.1234480813378 
Step 3431 | loss:2.136605739593506 lr:0.0001249558749608321 tokens_per_second_per_gpu:2168.032759380768 
Step 3432 | loss:2.1350009441375732 lr:0.00012491776942772525 tokens_per_second_per_gpu:2204.800011711948 
Step 3433 | loss:2.1407928466796875 lr:0.00012487966003656836 tokens_per_second_per_gpu:2233.75900663295 
Step 3434 | loss:2.107449531555176 lr:0.0001248415467932621 tokens_per_second_per_gpu:2191.918355095998 
Step 3435 | loss:2.1618752479553223 lr:0.0001248034297037075 tokens_per_second_per_gpu:2229.4793014026295 
Step 3436 | loss:2.190218210220337 lr:0.00012476530877380634 tokens_per_second_per_gpu:2195.969115495333 
Step 3437 | loss:2.1466641426086426 lr:0.0001247271840094609 tokens_per_second_per_gpu:2204.4768285671553 
Step 3438 | loss:2.157622814178467 lr:0.0001246890554165741 tokens_per_second_per_gpu:2235.1816869544627 
Step 3439 | loss:2.072923183441162 lr:0.00012465092300104945 tokens_per_second_per_gpu:2223.6486998680075 
Step 3440 | loss:2.147730827331543 lr:0.00012461278676879098 tokens_per_second_per_gpu:2182.9555759153322 
Step 3441 | loss:2.0805792808532715 lr:0.00012457464672570342 tokens_per_second_per_gpu:2232.160783245935 
Step 3442 | loss:2.1051368713378906 lr:0.00012453650287769209 tokens_per_second_per_gpu:2217.9097970489183 
Step 3443 | loss:2.093687057495117 lr:0.00012449835523066272 tokens_per_second_per_gpu:2200.7572548328512 
Step 3444 | loss:2.0961780548095703 lr:0.00012446020379052185 tokens_per_second_per_gpu:2185.2600136188835 
Step 3445 | loss:2.124131679534912 lr:0.00012442204856317655 tokens_per_second_per_gpu:2224.953935486085 
Step 3446 | loss:2.071502685546875 lr:0.00012438388955453433 tokens_per_second_per_gpu:2174.364807364297 
Step 3447 | loss:2.061983823776245 lr:0.00012434572677050352 tokens_per_second_per_gpu:2168.6365003267533 
Step 3448 | loss:2.0732030868530273 lr:0.00012430756021699282 tokens_per_second_per_gpu:2205.936498104229 
Step 3449 | loss:2.0781912803649902 lr:0.0001242693898999116 tokens_per_second_per_gpu:2234.8035982853767 
Step 3450 | loss:2.0809426307678223 lr:0.00012423121582516995 tokens_per_second_per_gpu:2238.254103282903 
Step 3451 | loss:2.172492027282715 lr:0.00012419303799867824 tokens_per_second_per_gpu:2130.599780869597 
Step 3452 | loss:2.073978900909424 lr:0.00012415485642634772 tokens_per_second_per_gpu:2200.7778691153644 
Step 3453 | loss:2.1229429244995117 lr:0.00012411667111409002 tokens_per_second_per_gpu:2233.072281357092 
Step 3454 | loss:2.0856595039367676 lr:0.00012407848206781745 tokens_per_second_per_gpu:2226.9819654319026 
Step 3455 | loss:2.114412784576416 lr:0.00012404028929344284 tokens_per_second_per_gpu:2213.112443694408 
Step 3456 | loss:2.1034319400787354 lr:0.0001240020927968797 tokens_per_second_per_gpu:2210.4758259091795 
Step 3457 | loss:2.0754642486572266 lr:0.00012396389258404194 tokens_per_second_per_gpu:2155.991455422085 
Step 3458 | loss:2.1476922035217285 lr:0.0001239256886608442 tokens_per_second_per_gpu:2196.765700950573 
Step 3459 | loss:2.0891103744506836 lr:0.00012388748103320162 tokens_per_second_per_gpu:2189.399038511147 
Step 3460 | loss:2.075382709503174 lr:0.00012384926970703 tokens_per_second_per_gpu:2131.091650486795 
Step 3461 | loss:2.178790330886841 lr:0.00012381105468824556 tokens_per_second_per_gpu:2189.9420338827867 
Step 3462 | loss:2.152420997619629 lr:0.00012377283598276524 tokens_per_second_per_gpu:2195.5346269207557 
Step 3463 | loss:2.0976579189300537 lr:0.0001237346135965065 tokens_per_second_per_gpu:2190.6127378919587 
Step 3464 | loss:2.1519994735717773 lr:0.0001236963875353873 tokens_per_second_per_gpu:2184.756902692993 
Step 3465 | loss:2.1149346828460693 lr:0.00012365815780532625 tokens_per_second_per_gpu:2184.487826918298 
Step 3466 | loss:2.166752815246582 lr:0.00012361992441224258 tokens_per_second_per_gpu:2116.8820019633745 
Step 3467 | loss:2.1246838569641113 lr:0.00012358168736205589 tokens_per_second_per_gpu:2174.854765640317 
Step 3468 | loss:2.1181979179382324 lr:0.0001235434466606866 tokens_per_second_per_gpu:2190.2289132709666 
Step 3469 | loss:2.1553099155426025 lr:0.00012350520231405545 tokens_per_second_per_gpu:2050.0910065481226 
Step 3470 | loss:2.135136127471924 lr:0.0001234669543280839 tokens_per_second_per_gpu:2193.226881557129 
Step 3471 | loss:2.066716194152832 lr:0.000123428702708694 tokens_per_second_per_gpu:2186.934451185297 
Step 3472 | loss:2.108978271484375 lr:0.00012339044746180824 tokens_per_second_per_gpu:2172.7255895476187 
Step 3473 | loss:2.1280951499938965 lr:0.0001233521885933497 tokens_per_second_per_gpu:2181.575389656485 
Step 3474 | loss:2.158389091491699 lr:0.00012331392610924214 tokens_per_second_per_gpu:2115.937821620823 
Step 3475 | loss:2.1285758018493652 lr:0.00012327566001540968 tokens_per_second_per_gpu:2158.3608687828128 
Step 3476 | loss:2.113213539123535 lr:0.00012323739031777718 tokens_per_second_per_gpu:2172.1004907995343 
Step 3477 | loss:2.1504759788513184 lr:0.00012319911702226996 tokens_per_second_per_gpu:2158.5645447764296 
Step 3478 | loss:2.0801315307617188 lr:0.00012316084013481394 tokens_per_second_per_gpu:2190.0321121435477 
Step 3479 | loss:2.0596117973327637 lr:0.00012312255966133554 tokens_per_second_per_gpu:2191.296237452839 
Step 3480 | loss:2.0516927242279053 lr:0.00012308427560776185 tokens_per_second_per_gpu:2165.457685893604 
Step 3481 | loss:2.0610551834106445 lr:0.00012304598798002037 tokens_per_second_per_gpu:2160.9809008734424 
Step 3482 | loss:2.143690347671509 lr:0.00012300769678403922 tokens_per_second_per_gpu:2144.7006729705317 
Step 3483 | loss:2.100379228591919 lr:0.00012296940202574715 tokens_per_second_per_gpu:2188.9929663298794 
Step 3484 | loss:2.182002067565918 lr:0.0001229311037110733 tokens_per_second_per_gpu:2112.028928644556 
Step 3485 | loss:2.12017822265625 lr:0.00012289280184594746 tokens_per_second_per_gpu:2194.1172427385313 
Step 3486 | loss:2.106712579727173 lr:0.0001228544964363 tokens_per_second_per_gpu:2171.7558412283392 
Step 3487 | loss:2.099247694015503 lr:0.00012281618748806182 tokens_per_second_per_gpu:2193.393641792622 
Step 3488 | loss:2.1355953216552734 lr:0.00012277787500716424 tokens_per_second_per_gpu:2177.4013624664058 
Step 3489 | loss:2.038226366043091 lr:0.0001227395589995393 tokens_per_second_per_gpu:2178.448172350076 
Step 3490 | loss:2.124016284942627 lr:0.00012270123947111952 tokens_per_second_per_gpu:2196.9223550238853 
Step 3491 | loss:2.082202911376953 lr:0.0001226629164278379 tokens_per_second_per_gpu:2146.0022885164967 
Step 3492 | loss:2.13975191116333 lr:0.00012262458987562813 tokens_per_second_per_gpu:2159.8342142568545 
Step 3493 | loss:2.08259916305542 lr:0.00012258625982042434 tokens_per_second_per_gpu:2156.5530260604996 
Step 3494 | loss:2.074583053588867 lr:0.0001225479262681611 tokens_per_second_per_gpu:2170.9179024091977 
Step 3495 | loss:2.127140522003174 lr:0.00012250958922477385 tokens_per_second_per_gpu:2127.350407848038 
Step 3496 | loss:2.0960543155670166 lr:0.00012247124869619824 tokens_per_second_per_gpu:2156.926842991116 
Step 3497 | loss:2.086033582687378 lr:0.00012243290468837053 tokens_per_second_per_gpu:2067.3422918319225 
Step 3498 | loss:2.1767208576202393 lr:0.0001223945572072277 tokens_per_second_per_gpu:2192.425227529807 
Step 3499 | loss:2.101898431777954 lr:0.0001223562062587071 tokens_per_second_per_gpu:2123.377791957843 
Step 3500 | loss:2.0911145210266113 lr:0.00012231785184874659 tokens_per_second_per_gpu:2190.460836822467 
Step 3501 | loss:2.090973377227783 lr:0.00012227949398328468 tokens_per_second_per_gpu:2186.740455100449 
Step 3502 | loss:2.154262065887451 lr:0.0001222411326682604 tokens_per_second_per_gpu:2145.839992768978 
Step 3503 | loss:2.060945510864258 lr:0.00012220276790961317 tokens_per_second_per_gpu:2182.6832641553556 
Step 3504 | loss:2.1299219131469727 lr:0.00012216439971328322 tokens_per_second_per_gpu:2189.727479472229 
Step 3505 | loss:2.1265265941619873 lr:0.000122126028085211 tokens_per_second_per_gpu:2136.2386713758347 
Step 3506 | loss:2.075860023498535 lr:0.00012208765303133772 tokens_per_second_per_gpu:2184.2827796125175 
Step 3507 | loss:2.158740997314453 lr:0.00012204927455760501 tokens_per_second_per_gpu:2196.2375722093084 
Step 3508 | loss:2.081078290939331 lr:0.00012201089266995506 tokens_per_second_per_gpu:2186.990099685781 
Step 3509 | loss:2.12766170501709 lr:0.00012197250737433057 tokens_per_second_per_gpu:2181.268416467101 
Step 3510 | loss:2.135570526123047 lr:0.00012193411867667484 tokens_per_second_per_gpu:2192.526701767448 
Step 3511 | loss:2.0754342079162598 lr:0.00012189572658293158 tokens_per_second_per_gpu:2116.6820166337716 
Step 3512 | loss:2.1012516021728516 lr:0.00012185733109904511 tokens_per_second_per_gpu:2118.5433794480064 
Step 3513 | loss:2.1740853786468506 lr:0.00012181893223096024 tokens_per_second_per_gpu:2176.477030361177 
Step 3514 | loss:2.1301817893981934 lr:0.00012178052998462237 tokens_per_second_per_gpu:2104.678644602354 
Step 3515 | loss:2.070195198059082 lr:0.00012174212436597727 tokens_per_second_per_gpu:2182.966757940464 
Step 3516 | loss:2.1420834064483643 lr:0.00012170371538097143 tokens_per_second_per_gpu:2166.8790498069434 
Step 3517 | loss:2.101945400238037 lr:0.0001216653030355517 tokens_per_second_per_gpu:2171.4120437508673 
Step 3518 | loss:2.14475154876709 lr:0.00012162688733566553 tokens_per_second_per_gpu:2178.2649460221587 
Step 3519 | loss:2.078037738800049 lr:0.00012158846828726087 tokens_per_second_per_gpu:2096.763363542206 
Step 3520 | loss:2.0766592025756836 lr:0.00012155004589628623 tokens_per_second_per_gpu:2169.370846208752 
Step 3521 | loss:2.1042346954345703 lr:0.00012151162016869049 tokens_per_second_per_gpu:2159.5075085612525 
Step 3522 | loss:2.073511838912964 lr:0.00012147319111042328 tokens_per_second_per_gpu:2163.0042449443836 
Step 3523 | loss:2.1642513275146484 lr:0.00012143475872743458 tokens_per_second_per_gpu:2185.9682284071023 
Step 3524 | loss:2.1537671089172363 lr:0.00012139632302567483 tokens_per_second_per_gpu:2178.5983915944735 
Step 3525 | loss:2.105365037918091 lr:0.00012135788401109523 tokens_per_second_per_gpu:2193.886192794572 
Step 3526 | loss:2.073298454284668 lr:0.00012131944168964727 tokens_per_second_per_gpu:2160.241182368161 
Step 3527 | loss:2.141706943511963 lr:0.00012128099606728295 tokens_per_second_per_gpu:2191.114657771476 
Step 3528 | loss:2.163924217224121 lr:0.000121242547149955 tokens_per_second_per_gpu:2151.9088210529776 
Step 3529 | loss:2.097306728363037 lr:0.00012120409494361642 tokens_per_second_per_gpu:2151.5954641874555 
Step 3530 | loss:2.0973055362701416 lr:0.00012116563945422084 tokens_per_second_per_gpu:2179.054147110983 
Step 3531 | loss:2.157257556915283 lr:0.00012112718068772237 tokens_per_second_per_gpu:2193.6150076419844 
Step 3532 | loss:2.0683863162994385 lr:0.00012108871865007562 tokens_per_second_per_gpu:2171.6456138159633 
Step 3533 | loss:2.1298577785491943 lr:0.00012105025334723572 tokens_per_second_per_gpu:2179.9247465449953 
Step 3534 | loss:2.10042405128479 lr:0.00012101178478515834 tokens_per_second_per_gpu:2165.6405366700187 
Step 3535 | loss:2.129664897918701 lr:0.00012097331296979954 tokens_per_second_per_gpu:2167.424923938246 
Step 3536 | loss:2.1371312141418457 lr:0.00012093483790711604 tokens_per_second_per_gpu:2190.5274952629447 
Step 3537 | loss:2.1260411739349365 lr:0.00012089635960306491 tokens_per_second_per_gpu:2181.6886062965723 
Step 3538 | loss:2.1053733825683594 lr:0.00012085787806360387 tokens_per_second_per_gpu:2184.478028159439 
Step 3539 | loss:2.150137424468994 lr:0.00012081939329469101 tokens_per_second_per_gpu:2135.695373641842 
Step 3540 | loss:2.024226188659668 lr:0.00012078090530228498 tokens_per_second_per_gpu:2165.283466934674 
Step 3541 | loss:2.1037561893463135 lr:0.00012074241409234497 tokens_per_second_per_gpu:2179.357035923526 
Step 3542 | loss:2.0781726837158203 lr:0.00012070391967083057 tokens_per_second_per_gpu:2152.851072728959 
Step 3543 | loss:2.10477876663208 lr:0.00012066542204370193 tokens_per_second_per_gpu:2112.1427766334555 
Step 3544 | loss:2.0917277336120605 lr:0.00012062692121691972 tokens_per_second_per_gpu:2150.3188471369403 
Step 3545 | loss:2.1000795364379883 lr:0.000120588417196445 tokens_per_second_per_gpu:2184.1338577165557 
Step 3546 | loss:2.124211549758911 lr:0.00012054990998823949 tokens_per_second_per_gpu:2135.8043566528168 
Step 3547 | loss:2.094311237335205 lr:0.0001205113995982653 tokens_per_second_per_gpu:2148.8557589822512 
Step 3548 | loss:2.0662293434143066 lr:0.00012047288603248492 tokens_per_second_per_gpu:2194.9052820328607 
Step 3549 | loss:2.116340160369873 lr:0.00012043436929686161 tokens_per_second_per_gpu:2129.120020916145 
Step 3550 | loss:2.062901496887207 lr:0.00012039584939735889 tokens_per_second_per_gpu:2191.7846097665342 
Step 3551 | loss:2.0819129943847656 lr:0.00012035732633994082 tokens_per_second_per_gpu:2152.5379980258035 
Step 3552 | loss:2.10441255569458 lr:0.00012031880013057204 tokens_per_second_per_gpu:2194.142891649334 
Step 3553 | loss:2.182234764099121 lr:0.00012028027077521758 tokens_per_second_per_gpu:2181.6604847064577 
Step 3554 | loss:2.1022348403930664 lr:0.00012024173827984296 tokens_per_second_per_gpu:2144.5789453458506 
Step 3555 | loss:2.1383118629455566 lr:0.00012020320265041427 tokens_per_second_per_gpu:2182.5934480337955 
Step 3556 | loss:2.022916316986084 lr:0.00012016466389289798 tokens_per_second_per_gpu:2126.525809029741 
Step 3557 | loss:2.1037988662719727 lr:0.00012012612201326114 tokens_per_second_per_gpu:2134.5214643442746 
Step 3558 | loss:2.067009449005127 lr:0.00012008757701747122 tokens_per_second_per_gpu:2135.20163828864 
Step 3559 | loss:2.153933048248291 lr:0.00012004902891149616 tokens_per_second_per_gpu:2173.4471501203407 
Step 3560 | loss:2.129826068878174 lr:0.00012001047770130447 tokens_per_second_per_gpu:2152.834896465289 
Step 3561 | loss:2.1795897483825684 lr:0.00011997192339286503 tokens_per_second_per_gpu:2173.920468180878 
Step 3562 | loss:2.0980966091156006 lr:0.0001199333659921473 tokens_per_second_per_gpu:2186.6381837604704 
Step 3563 | loss:2.112457275390625 lr:0.00011989480550512113 tokens_per_second_per_gpu:2121.939147608975 
Step 3564 | loss:2.1089909076690674 lr:0.00011985624193775691 tokens_per_second_per_gpu:2126.0768102823913 
Step 3565 | loss:2.1175146102905273 lr:0.0001198176752960255 tokens_per_second_per_gpu:2192.5046966728937 
Step 3566 | loss:2.129779577255249 lr:0.00011977910558589817 tokens_per_second_per_gpu:2155.3157389964595 
Step 3567 | loss:2.149508476257324 lr:0.00011974053281334679 tokens_per_second_per_gpu:2180.1582181379285 
Step 3568 | loss:2.1439452171325684 lr:0.00011970195698434359 tokens_per_second_per_gpu:2110.2993999995697 
Step 3569 | loss:2.070265769958496 lr:0.00011966337810486127 tokens_per_second_per_gpu:2195.100919149609 
Step 3570 | loss:2.1322879791259766 lr:0.00011962479618087315 tokens_per_second_per_gpu:2194.4519375714744 
Step 3571 | loss:2.1415586471557617 lr:0.00011958621121835286 tokens_per_second_per_gpu:2186.978827011374 
Step 3572 | loss:2.0842885971069336 lr:0.00011954762322327451 tokens_per_second_per_gpu:2162.611777756975 
Step 3573 | loss:2.1437079906463623 lr:0.00011950903220161285 tokens_per_second_per_gpu:2147.020990116961 
Step 3574 | loss:2.111372470855713 lr:0.00011947043815934287 tokens_per_second_per_gpu:2187.651437211069 
Step 3575 | loss:2.1177310943603516 lr:0.00011943184110244017 tokens_per_second_per_gpu:2180.6454489467983 
Step 3576 | loss:2.119779109954834 lr:0.0001193932410368808 tokens_per_second_per_gpu:2164.3018343273097 
Step 3577 | loss:2.182356119155884 lr:0.00011935463796864126 tokens_per_second_per_gpu:2179.009254944412 
Step 3578 | loss:2.1074118614196777 lr:0.00011931603190369843 tokens_per_second_per_gpu:2178.198176834236 
Step 3579 | loss:2.1178553104400635 lr:0.00011927742284802986 tokens_per_second_per_gpu:2109.3743198426737 
Step 3580 | loss:2.0754055976867676 lr:0.00011923881080761335 tokens_per_second_per_gpu:2170.1426814529314 
Step 3581 | loss:2.0681638717651367 lr:0.00011920019578842727 tokens_per_second_per_gpu:2146.9499274918608 
Step 3582 | loss:2.1319432258605957 lr:0.0001191615777964505 tokens_per_second_per_gpu:2185.692259063757 
Step 3583 | loss:2.104210376739502 lr:0.00011912295683766219 tokens_per_second_per_gpu:2179.5927618532874 
Step 3584 | loss:2.1139755249023438 lr:0.00011908433291804217 tokens_per_second_per_gpu:2151.308836258621 
Step 3585 | loss:2.1449673175811768 lr:0.00011904570604357061 tokens_per_second_per_gpu:2147.0402475999094 
Step 3586 | loss:2.0858805179595947 lr:0.00011900707622022813 tokens_per_second_per_gpu:2155.0681281307693 
Step 3587 | loss:2.119884490966797 lr:0.00011896844345399584 tokens_per_second_per_gpu:2191.8505225787662 
Step 3588 | loss:2.0335049629211426 lr:0.00011892980775085531 tokens_per_second_per_gpu:2190.6844937051596 
Step 3589 | loss:2.1440036296844482 lr:0.00011889116911678859 tokens_per_second_per_gpu:2198.270679794674 
Step 3590 | loss:2.1129961013793945 lr:0.0001188525275577781 tokens_per_second_per_gpu:2149.967991534969 
Step 3591 | loss:2.154047966003418 lr:0.00011881388307980676 tokens_per_second_per_gpu:2168.8703610257116 
Step 3592 | loss:2.168795585632324 lr:0.000118775235688858 tokens_per_second_per_gpu:2149.242373943753 
Step 3593 | loss:2.123863697052002 lr:0.00011873658539091556 tokens_per_second_per_gpu:2196.5582380172696 
Step 3594 | loss:2.1026527881622314 lr:0.00011869793219196379 tokens_per_second_per_gpu:2176.581382443878 
Step 3595 | loss:2.1592178344726562 lr:0.0001186592760979874 tokens_per_second_per_gpu:2043.0211497185885 
Step 3596 | loss:2.148707628250122 lr:0.00011862061711497148 tokens_per_second_per_gpu:2194.00924298212 
Step 3597 | loss:2.1108107566833496 lr:0.00011858195524890178 tokens_per_second_per_gpu:2128.2019240639684 
Step 3598 | loss:2.1250064373016357 lr:0.0001185432905057643 tokens_per_second_per_gpu:2199.419467400147 
Step 3599 | loss:2.0465965270996094 lr:0.00011850462289154552 tokens_per_second_per_gpu:2191.9407265379455 
Step 3600 | loss:2.1707730293273926 lr:0.00011846595241223247 tokens_per_second_per_gpu:2195.119928864011 
Step 3601 | loss:2.088290214538574 lr:0.00011842727907381248 tokens_per_second_per_gpu:2178.076618401808 
Step 3602 | loss:2.089367389678955 lr:0.0001183886028822734 tokens_per_second_per_gpu:2182.8483783017464 
Step 3603 | loss:2.148501396179199 lr:0.00011834992384360357 tokens_per_second_per_gpu:2149.00802963396 
Step 3604 | loss:1.990275263786316 lr:0.00011831124196379168 tokens_per_second_per_gpu:2120.64824136259 
Step 3605 | loss:2.107663154602051 lr:0.00011827255724882688 tokens_per_second_per_gpu:2133.3553487739955 
Step 3606 | loss:2.109757423400879 lr:0.0001182338697046988 tokens_per_second_per_gpu:2136.581349612877 
Step 3607 | loss:2.0675177574157715 lr:0.00011819517933739747 tokens_per_second_per_gpu:2159.8618264410757 
Step 3608 | loss:2.11677622795105 lr:0.00011815648615291338 tokens_per_second_per_gpu:2149.975896036622 
Step 3609 | loss:2.0385727882385254 lr:0.00011811779015723743 tokens_per_second_per_gpu:2152.262066840474 
Step 3610 | loss:2.1306064128875732 lr:0.00011807909135636094 tokens_per_second_per_gpu:2196.3974892454808 
Step 3611 | loss:2.1213185787200928 lr:0.00011804038975627576 tokens_per_second_per_gpu:2162.606469453276 
Step 3612 | loss:2.167069435119629 lr:0.00011800168536297407 tokens_per_second_per_gpu:2180.018250370278 
Step 3613 | loss:2.1028990745544434 lr:0.00011796297818244854 tokens_per_second_per_gpu:2169.5893518359335 
Step 3614 | loss:2.1064348220825195 lr:0.00011792426822069223 tokens_per_second_per_gpu:2128.532374359615 
Step 3615 | loss:2.16060733795166 lr:0.00011788555548369864 tokens_per_second_per_gpu:2136.5979090598935 
Step 3616 | loss:2.1300108432769775 lr:0.00011784683997746178 tokens_per_second_per_gpu:2161.952538499056 
Step 3617 | loss:2.103364944458008 lr:0.00011780812170797593 tokens_per_second_per_gpu:2153.3263222536425 
Step 3618 | loss:2.134791135787964 lr:0.00011776940068123594 tokens_per_second_per_gpu:2135.5093623584085 
Step 3619 | loss:2.02720308303833 lr:0.00011773067690323708 tokens_per_second_per_gpu:2177.08852076209 
Step 3620 | loss:2.1116085052490234 lr:0.00011769195037997487 tokens_per_second_per_gpu:2167.454299156181 
Step 3621 | loss:2.100491523742676 lr:0.00011765322111744554 tokens_per_second_per_gpu:2182.9935749832603 
Step 3622 | loss:2.047931671142578 lr:0.0001176144891216455 tokens_per_second_per_gpu:2172.536803591037 
Step 3623 | loss:2.097820281982422 lr:0.00011757575439857167 tokens_per_second_per_gpu:2170.5554783824405 
Step 3624 | loss:2.0664236545562744 lr:0.00011753701695422146 tokens_per_second_per_gpu:2134.84426013888 
Step 3625 | loss:2.1676278114318848 lr:0.00011749827679459258 tokens_per_second_per_gpu:2158.434203672152 
Step 3626 | loss:2.102236747741699 lr:0.00011745953392568321 tokens_per_second_per_gpu:2165.893151874426 
Step 3627 | loss:2.135200023651123 lr:0.00011742078835349202 tokens_per_second_per_gpu:2198.1911463670885 
Step 3628 | loss:2.147761344909668 lr:0.00011738204008401798 tokens_per_second_per_gpu:2157.646883672642 
Step 3629 | loss:2.0388927459716797 lr:0.00011734328912326056 tokens_per_second_per_gpu:2173.426744676249 
Step 3630 | loss:2.146247148513794 lr:0.00011730453547721964 tokens_per_second_per_gpu:2167.3588088438523 
Step 3631 | loss:2.077953338623047 lr:0.00011726577915189545 tokens_per_second_per_gpu:2136.5326904504236 
Step 3632 | loss:2.0667953491210938 lr:0.00011722702015328869 tokens_per_second_per_gpu:2195.015886326592 
Step 3633 | loss:2.103710412979126 lr:0.00011718825848740049 tokens_per_second_per_gpu:2182.9253179435423 
Step 3634 | loss:2.129464864730835 lr:0.00011714949416023236 tokens_per_second_per_gpu:2182.9636764432553 
Step 3635 | loss:2.171937942504883 lr:0.00011711072717778622 tokens_per_second_per_gpu:2193.1653342506897 
Step 3636 | loss:2.0544772148132324 lr:0.00011707195754606443 tokens_per_second_per_gpu:2194.2910138344455 
Step 3637 | loss:2.0763473510742188 lr:0.0001170331852710697 tokens_per_second_per_gpu:2128.9089634711804 
Step 3638 | loss:2.1207830905914307 lr:0.00011699441035880526 tokens_per_second_per_gpu:2180.6423376095904 
Step 3639 | loss:2.1589462757110596 lr:0.0001169556328152746 tokens_per_second_per_gpu:2198.0363690414933 
Step 3640 | loss:2.1573128700256348 lr:0.00011691685264648176 tokens_per_second_per_gpu:2184.545684809239 
Step 3641 | loss:2.088454246520996 lr:0.00011687806985843107 tokens_per_second_per_gpu:2193.032589791623 
Step 3642 | loss:2.07643985748291 lr:0.00011683928445712735 tokens_per_second_per_gpu:2144.9088474383257 
Step 3643 | loss:2.1492505073547363 lr:0.00011680049644857582 tokens_per_second_per_gpu:2168.770663380655 
Step 3644 | loss:2.1457138061523438 lr:0.00011676170583878201 tokens_per_second_per_gpu:2185.1583465874864 
Step 3645 | loss:2.108044385910034 lr:0.00011672291263375198 tokens_per_second_per_gpu:2050.462490065744 
Step 3646 | loss:2.107400894165039 lr:0.0001166841168394921 tokens_per_second_per_gpu:2146.4349088199006 
Step 3647 | loss:2.085313320159912 lr:0.00011664531846200914 tokens_per_second_per_gpu:2186.119690676946 
Step 3648 | loss:2.1020476818084717 lr:0.0001166065175073104 tokens_per_second_per_gpu:2068.000240795063 
Step 3649 | loss:2.132249355316162 lr:0.00011656771398140343 tokens_per_second_per_gpu:2186.250937699352 
Step 3650 | loss:2.1516809463500977 lr:0.00011652890789029615 tokens_per_second_per_gpu:2200.3295270683316 
Step 3651 | loss:2.1466550827026367 lr:0.00011649009923999707 tokens_per_second_per_gpu:2134.971860544249 
Step 3652 | loss:2.0886776447296143 lr:0.00011645128803651495 tokens_per_second_per_gpu:2172.7121500158137 
Step 3653 | loss:2.0833120346069336 lr:0.00011641247428585893 tokens_per_second_per_gpu:2175.71956485736 
Step 3654 | loss:2.1154565811157227 lr:0.00011637365799403868 tokens_per_second_per_gpu:2166.408772690061 
Step 3655 | loss:2.0616283416748047 lr:0.00011633483916706409 tokens_per_second_per_gpu:2176.742056900573 
Step 3656 | loss:2.146145820617676 lr:0.00011629601781094556 tokens_per_second_per_gpu:2196.6078749235235 
Step 3657 | loss:2.111009359359741 lr:0.0001162571939316939 tokens_per_second_per_gpu:2193.973660272631 
Step 3658 | loss:2.1315038204193115 lr:0.00011621836753532019 tokens_per_second_per_gpu:2195.3964450286235 
Step 3659 | loss:2.1153564453125 lr:0.00011617953862783598 tokens_per_second_per_gpu:2196.5949798158745 
Step 3660 | loss:2.1330604553222656 lr:0.00011614070721525325 tokens_per_second_per_gpu:2176.1689965004553 
Step 3661 | loss:2.1058316230773926 lr:0.00011610187330358427 tokens_per_second_per_gpu:2192.91992851064 
Step 3662 | loss:2.1199615001678467 lr:0.00011606303689884173 tokens_per_second_per_gpu:2167.999633586521 
Step 3663 | loss:2.1077983379364014 lr:0.00011602419800703874 tokens_per_second_per_gpu:2133.569941264477 
Step 3664 | loss:2.0961179733276367 lr:0.00011598535663418884 tokens_per_second_per_gpu:2195.414397588121 
Step 3665 | loss:2.0786614418029785 lr:0.00011594651278630577 tokens_per_second_per_gpu:2153.698692600868 
Step 3666 | loss:2.1364808082580566 lr:0.00011590766646940385 tokens_per_second_per_gpu:2190.4777768704394 
Step 3667 | loss:2.065953254699707 lr:0.0001158688176894977 tokens_per_second_per_gpu:2160.505737068418 
Step 3668 | loss:2.073730707168579 lr:0.00011582996645260232 tokens_per_second_per_gpu:2150.053455467413 
Step 3669 | loss:2.1244049072265625 lr:0.00011579111276473306 tokens_per_second_per_gpu:2194.7452362496224 
Step 3670 | loss:2.1349401473999023 lr:0.00011575225663190576 tokens_per_second_per_gpu:2196.514802924957 
Step 3671 | loss:2.1000921726226807 lr:0.00011571339806013646 tokens_per_second_per_gpu:2187.140834898905 
Step 3672 | loss:2.086318254470825 lr:0.0001156745370554418 tokens_per_second_per_gpu:2198.176609113592 
Step 3673 | loss:2.0554561614990234 lr:0.00011563567362383861 tokens_per_second_per_gpu:2177.0942890275974 
Step 3674 | loss:2.128080368041992 lr:0.00011559680777134414 tokens_per_second_per_gpu:2150.5733123758214 
Step 3675 | loss:2.1040449142456055 lr:0.00011555793950397611 tokens_per_second_per_gpu:2187.4677953398364 
Step 3676 | loss:2.0857129096984863 lr:0.00011551906882775251 tokens_per_second_per_gpu:2185.2780531229755 
Step 3677 | loss:2.064164161682129 lr:0.00011548019574869168 tokens_per_second_per_gpu:2064.821232968491 
Step 3678 | loss:2.123459815979004 lr:0.00011544132027281251 tokens_per_second_per_gpu:2147.6498261414504 
Step 3679 | loss:2.069819450378418 lr:0.00011540244240613404 tokens_per_second_per_gpu:2175.152471411166 
Step 3680 | loss:2.116825580596924 lr:0.00011536356215467581 tokens_per_second_per_gpu:2198.935271704016 
Step 3681 | loss:2.1072473526000977 lr:0.00011532467952445774 tokens_per_second_per_gpu:2191.144080996838 
Step 3682 | loss:2.0864815711975098 lr:0.00011528579452149999 tokens_per_second_per_gpu:2196.720322569811 
Step 3683 | loss:2.0850868225097656 lr:0.00011524690715182325 tokens_per_second_per_gpu:2182.6581223573085 
Step 3684 | loss:2.077972888946533 lr:0.00011520801742144847 tokens_per_second_per_gpu:2191.4175019818317 
Step 3685 | loss:2.094094753265381 lr:0.00011516912533639699 tokens_per_second_per_gpu:2157.457729841723 
Step 3686 | loss:2.0965569019317627 lr:0.00011513023090269053 tokens_per_second_per_gpu:2108.151377642064 
Step 3687 | loss:2.1186089515686035 lr:0.00011509133412635118 tokens_per_second_per_gpu:2125.3637094736278 
Step 3688 | loss:2.152904510498047 lr:0.00011505243501340135 tokens_per_second_per_gpu:2149.729743063839 
Step 3689 | loss:2.135200262069702 lr:0.00011501353356986383 tokens_per_second_per_gpu:2197.379974259902 
Step 3690 | loss:2.017787456512451 lr:0.00011497462980176184 tokens_per_second_per_gpu:2179.7374282618066 
Step 3691 | loss:2.137681245803833 lr:0.00011493572371511888 tokens_per_second_per_gpu:2197.729652050982 
Step 3692 | loss:2.0968499183654785 lr:0.00011489681531595875 tokens_per_second_per_gpu:2158.4713790932065 
Step 3693 | loss:2.088685989379883 lr:0.00011485790461030577 tokens_per_second_per_gpu:2150.406004548206 
Step 3694 | loss:2.0742616653442383 lr:0.00011481899160418454 tokens_per_second_per_gpu:2160.1705903954276 
Step 3695 | loss:2.08050274848938 lr:0.00011478007630361995 tokens_per_second_per_gpu:2172.600505310632 
Step 3696 | loss:2.149263858795166 lr:0.00011474115871463736 tokens_per_second_per_gpu:2194.291203592672 
Step 3697 | loss:2.1098575592041016 lr:0.00011470223884326239 tokens_per_second_per_gpu:2173.824665367929 
Step 3698 | loss:2.0753204822540283 lr:0.00011466331669552108 tokens_per_second_per_gpu:2085.3673322506147 
Step 3699 | loss:2.0667247772216797 lr:0.00011462439227743977 tokens_per_second_per_gpu:2167.1684040039986 
Step 3700 | loss:2.150082588195801 lr:0.00011458546559504521 tokens_per_second_per_gpu:2159.1761592702665 
Step 3701 | loss:2.1423723697662354 lr:0.00011454653665436443 tokens_per_second_per_gpu:2196.113842353378 
Step 3702 | loss:2.1180553436279297 lr:0.00011450760546142491 tokens_per_second_per_gpu:2165.137766967938 
Step 3703 | loss:2.126654624938965 lr:0.00011446867202225438 tokens_per_second_per_gpu:2200.278984356219 
Step 3704 | loss:2.0660805702209473 lr:0.00011442973634288087 tokens_per_second_per_gpu:2054.713583262104 
Step 3705 | loss:2.096573829650879 lr:0.000114390798429333 tokens_per_second_per_gpu:2120.9510679741875 
Step 3706 | loss:2.04142427444458 lr:0.00011435185828763946 tokens_per_second_per_gpu:2184.637431330197 
Step 3707 | loss:2.1296348571777344 lr:0.00011431291592382943 tokens_per_second_per_gpu:2117.2888702218197 
Step 3708 | loss:2.0712509155273438 lr:0.00011427397134393245 tokens_per_second_per_gpu:2105.0348806381094 
Step 3709 | loss:2.091062545776367 lr:0.0001142350245539783 tokens_per_second_per_gpu:2178.792480771318 
Step 3710 | loss:2.0828428268432617 lr:0.00011419607555999716 tokens_per_second_per_gpu:2183.9924523860977 
Step 3711 | loss:2.1283035278320312 lr:0.00011415712436801962 tokens_per_second_per_gpu:2181.6106602353675 
Step 3712 | loss:2.1188411712646484 lr:0.00011411817098407646 tokens_per_second_per_gpu:2196.4715541619944 
Step 3713 | loss:2.097550868988037 lr:0.00011407921541419895 tokens_per_second_per_gpu:2066.9281930268635 
Step 3714 | loss:2.163043975830078 lr:0.0001140402576644186 tokens_per_second_per_gpu:2186.4139354342747 
Step 3715 | loss:2.1395926475524902 lr:0.00011400129774076728 tokens_per_second_per_gpu:2177.8225676814736 
Step 3716 | loss:2.0406405925750732 lr:0.0001139623356492772 tokens_per_second_per_gpu:2086.769814560374 
Step 3717 | loss:2.1129140853881836 lr:0.00011392337139598093 tokens_per_second_per_gpu:2140.4803347778425 
Step 3718 | loss:2.123850107192993 lr:0.00011388440498691138 tokens_per_second_per_gpu:2170.37225252609 
Step 3719 | loss:2.0972604751586914 lr:0.0001138454364281017 tokens_per_second_per_gpu:2171.463419124223 
Step 3720 | loss:2.1383070945739746 lr:0.00011380646572558548 tokens_per_second_per_gpu:2180.2362745877194 
Step 3721 | loss:2.1649928092956543 lr:0.00011376749288539664 tokens_per_second_per_gpu:2141.5202071640315 
Step 3722 | loss:2.1047303676605225 lr:0.00011372851791356934 tokens_per_second_per_gpu:2170.0102541099373 
Step 3723 | loss:2.0987143516540527 lr:0.00011368954081613812 tokens_per_second_per_gpu:2154.8525989488408 
Step 3724 | loss:2.1026434898376465 lr:0.00011365056159913789 tokens_per_second_per_gpu:2161.777181067733 
Step 3725 | loss:2.1223435401916504 lr:0.00011361158026860383 tokens_per_second_per_gpu:2152.1713118515836 
Step 3726 | loss:2.075417995452881 lr:0.00011357259683057147 tokens_per_second_per_gpu:2168.6750169639963 
Step 3727 | loss:2.1067376136779785 lr:0.00011353361129107669 tokens_per_second_per_gpu:2197.695192858626 
Step 3728 | loss:2.0816588401794434 lr:0.00011349462365615562 tokens_per_second_per_gpu:2150.1636619222236 
Step 3729 | loss:2.1260781288146973 lr:0.00011345563393184483 tokens_per_second_per_gpu:2147.2764264405364 
Step 3730 | loss:2.043944835662842 lr:0.00011341664212418111 tokens_per_second_per_gpu:2189.2506096691504 
Step 3731 | loss:2.0981006622314453 lr:0.00011337764823920161 tokens_per_second_per_gpu:2159.8092403043674 
Step 3732 | loss:2.1229875087738037 lr:0.00011333865228294382 tokens_per_second_per_gpu:2188.8097061015433 
Step 3733 | loss:2.115328788757324 lr:0.0001132996542614455 tokens_per_second_per_gpu:2189.047324480031 
Step 3734 | loss:2.0509114265441895 lr:0.00011326065418074478 tokens_per_second_per_gpu:2144.7303512314575 
Step 3735 | loss:2.195080280303955 lr:0.00011322165204688016 tokens_per_second_per_gpu:2005.5652090573246 
Step 3736 | loss:2.0962066650390625 lr:0.00011318264786589028 tokens_per_second_per_gpu:2163.6399243294068 
Step 3737 | loss:2.0415775775909424 lr:0.00011314364164381426 tokens_per_second_per_gpu:2170.158203510146 
Step 3738 | loss:2.0341358184814453 lr:0.00011310463338669146 tokens_per_second_per_gpu:2174.7149308607086 
Step 3739 | loss:2.071082353591919 lr:0.00011306562310056163 tokens_per_second_per_gpu:2014.927000598485 
Step 3740 | loss:2.0950350761413574 lr:0.00011302661079146473 tokens_per_second_per_gpu:2124.5996805752775 
Step 3741 | loss:2.1546223163604736 lr:0.0001129875964654411 tokens_per_second_per_gpu:2133.9367722661095 
Step 3742 | loss:2.0632519721984863 lr:0.00011294858012853143 tokens_per_second_per_gpu:2105.876344193517 
Step 3743 | loss:2.123249053955078 lr:0.00011290956178677656 tokens_per_second_per_gpu:2176.5284547414185 
Step 3744 | loss:2.096440553665161 lr:0.00011287054144621783 tokens_per_second_per_gpu:2192.793648039116 
Step 3745 | loss:2.084688186645508 lr:0.0001128315191128968 tokens_per_second_per_gpu:2155.9776031422075 
Step 3746 | loss:2.128715991973877 lr:0.00011279249479285534 tokens_per_second_per_gpu:2187.725482394254 
Step 3747 | loss:2.1230649948120117 lr:0.00011275346849213561 tokens_per_second_per_gpu:2191.0147960830286 
Step 3748 | loss:2.039083480834961 lr:0.00011271444021678015 tokens_per_second_per_gpu:2153.185892491006 
Step 3749 | loss:2.1693811416625977 lr:0.00011267540997283173 tokens_per_second_per_gpu:2192.4787454741595 
Step 3750 | loss:2.0688834190368652 lr:0.00011263637776633342 tokens_per_second_per_gpu:2185.720779284974 
Step 3751 | loss:2.1228461265563965 lr:0.0001125973436033287 tokens_per_second_per_gpu:2107.5478182562056 
Step 3752 | loss:2.1545581817626953 lr:0.00011255830748986123 tokens_per_second_per_gpu:2142.918689503023 
Step 3753 | loss:2.10349702835083 lr:0.00011251926943197499 tokens_per_second_per_gpu:2187.053092493068 
Step 3754 | loss:2.173318386077881 lr:0.00011248022943571439 tokens_per_second_per_gpu:2193.596382873406 
Step 3755 | loss:2.121267080307007 lr:0.00011244118750712394 tokens_per_second_per_gpu:2168.892840741252 
Step 3756 | loss:2.117180347442627 lr:0.00011240214365224861 tokens_per_second_per_gpu:2188.3508175615507 
Step 3757 | loss:2.069497585296631 lr:0.00011236309787713361 tokens_per_second_per_gpu:2158.276496412146 
Step 3758 | loss:2.128894805908203 lr:0.00011232405018782441 tokens_per_second_per_gpu:2190.088832849279 
Step 3759 | loss:2.095472812652588 lr:0.00011228500059036688 tokens_per_second_per_gpu:2187.4044390173312 
Step 3760 | loss:2.1207103729248047 lr:0.00011224594909080704 tokens_per_second_per_gpu:2170.6527516481724 
Step 3761 | loss:2.1117749214172363 lr:0.00011220689569519132 tokens_per_second_per_gpu:2164.706458557669 
Step 3762 | loss:2.104396343231201 lr:0.00011216784040956643 tokens_per_second_per_gpu:2115.1409807398736 
Step 3763 | loss:2.023068904876709 lr:0.00011212878323997928 tokens_per_second_per_gpu:2191.798652642455 
Step 3764 | loss:2.096954345703125 lr:0.00011208972419247723 tokens_per_second_per_gpu:2135.614378566044 
Step 3765 | loss:2.1238293647766113 lr:0.00011205066327310776 tokens_per_second_per_gpu:2113.359579883165 
Step 3766 | loss:2.151819944381714 lr:0.00011201160048791881 tokens_per_second_per_gpu:2163.277440078665 
Step 3767 | loss:2.10245418548584 lr:0.00011197253584295844 tokens_per_second_per_gpu:2169.6562455502253 
Step 3768 | loss:2.117338180541992 lr:0.00011193346934427512 tokens_per_second_per_gpu:2189.657886040512 
Step 3769 | loss:2.091914653778076 lr:0.00011189440099791755 tokens_per_second_per_gpu:2142.2274326993665 
Step 3770 | loss:2.155949354171753 lr:0.00011185533080993474 tokens_per_second_per_gpu:2191.018333206876 
Step 3771 | loss:2.1611549854278564 lr:0.00011181625878637596 tokens_per_second_per_gpu:2182.212712085393 
Step 3772 | loss:2.1271021366119385 lr:0.00011177718493329082 tokens_per_second_per_gpu:2114.156957169875 
Step 3773 | loss:2.135432720184326 lr:0.00011173810925672912 tokens_per_second_per_gpu:2133.9534286802195 
Step 3774 | loss:2.127023458480835 lr:0.00011169903176274104 tokens_per_second_per_gpu:2115.490729570682 
Step 3775 | loss:2.177285671234131 lr:0.00011165995245737699 tokens_per_second_per_gpu:2186.319723436728 
Step 3776 | loss:2.0774874687194824 lr:0.00011162087134668767 tokens_per_second_per_gpu:2187.6426819454923 
Step 3777 | loss:2.1606316566467285 lr:0.00011158178843672402 tokens_per_second_per_gpu:2191.221375532747 
Step 3778 | loss:2.1019551753997803 lr:0.00011154270373353737 tokens_per_second_per_gpu:2165.5121309175274 
Step 3779 | loss:2.1377944946289062 lr:0.0001115036172431792 tokens_per_second_per_gpu:2164.7849867035516 
Step 3780 | loss:2.0589582920074463 lr:0.00011146452897170132 tokens_per_second_per_gpu:2165.1852960044353 
Step 3781 | loss:2.079540252685547 lr:0.00011142543892515582 tokens_per_second_per_gpu:2112.8814968476236 
Step 3782 | loss:2.050895929336548 lr:0.00011138634710959508 tokens_per_second_per_gpu:2158.2981761103715 
Step 3783 | loss:2.1085381507873535 lr:0.00011134725353107176 tokens_per_second_per_gpu:2169.9720716080046 
Step 3784 | loss:2.0811333656311035 lr:0.00011130815819563869 tokens_per_second_per_gpu:2192.1260325428057 
Step 3785 | loss:2.062584400177002 lr:0.00011126906110934912 tokens_per_second_per_gpu:2181.5565269512385 
Step 3786 | loss:2.1235733032226562 lr:0.00011122996227825648 tokens_per_second_per_gpu:2181.1838993409197 
Step 3787 | loss:2.119358539581299 lr:0.00011119086170841449 tokens_per_second_per_gpu:2150.2753000306375 
Step 3788 | loss:2.161663770675659 lr:0.00011115175940587712 tokens_per_second_per_gpu:2181.2869771015858 
Step 3789 | loss:2.0390591621398926 lr:0.00011111265537669866 tokens_per_second_per_gpu:2164.4296065076264 
Step 3790 | loss:2.070556163787842 lr:0.00011107354962693366 tokens_per_second_per_gpu:2149.102924962647 
Step 3791 | loss:2.1860837936401367 lr:0.00011103444216263685 tokens_per_second_per_gpu:2146.3845493904023 
Step 3792 | loss:2.124330520629883 lr:0.00011099533298986331 tokens_per_second_per_gpu:2140.3480201678617 
Step 3793 | loss:2.0899758338928223 lr:0.0001109562221146684 tokens_per_second_per_gpu:2166.08025783497 
Step 3794 | loss:2.168018341064453 lr:0.00011091710954310765 tokens_per_second_per_gpu:2182.616824555181 
Step 3795 | loss:2.080784320831299 lr:0.00011087799528123695 tokens_per_second_per_gpu:2151.280461030972 
Step 3796 | loss:2.06516695022583 lr:0.00011083887933511241 tokens_per_second_per_gpu:2081.4806475256864 
Step 3797 | loss:2.114628314971924 lr:0.00011079976171079036 tokens_per_second_per_gpu:2127.1820833477454 
Step 3798 | loss:2.067474842071533 lr:0.00011076064241432747 tokens_per_second_per_gpu:2194.567799523011 
Step 3799 | loss:2.084305763244629 lr:0.00011072152145178063 tokens_per_second_per_gpu:2168.489765178192 
Step 3800 | loss:2.0707480907440186 lr:0.00011068239882920699 tokens_per_second_per_gpu:2182.866126401493 
Step 3801 | loss:2.0739126205444336 lr:0.00011064327455266392 tokens_per_second_per_gpu:2183.879705893871 
Step 3802 | loss:2.1689181327819824 lr:0.00011060414862820913 tokens_per_second_per_gpu:2155.6267552971117 
Step 3803 | loss:2.0584731101989746 lr:0.0001105650210619005 tokens_per_second_per_gpu:2192.4326843028175 
Step 3804 | loss:2.167600631713867 lr:0.00011052589185979621 tokens_per_second_per_gpu:2136.331586224158 
Step 3805 | loss:2.0459651947021484 lr:0.00011048676102795472 tokens_per_second_per_gpu:2145.681090137122 
Step 3806 | loss:2.108401298522949 lr:0.00011044762857243464 tokens_per_second_per_gpu:2165.1605827281865 
Step 3807 | loss:2.048456907272339 lr:0.00011040849449929494 tokens_per_second_per_gpu:2186.425195607403 
Step 3808 | loss:2.0735325813293457 lr:0.00011036935881459478 tokens_per_second_per_gpu:2157.374160714069 
Step 3809 | loss:2.1357016563415527 lr:0.0001103302215243936 tokens_per_second_per_gpu:2128.5361214994796 
Step 3810 | loss:2.113313913345337 lr:0.00011029108263475112 tokens_per_second_per_gpu:2176.5425341997643 
Step 3811 | loss:2.182621479034424 lr:0.00011025194215172718 tokens_per_second_per_gpu:2171.586252097282 
Step 3812 | loss:2.0668044090270996 lr:0.000110212800081382 tokens_per_second_per_gpu:2148.982160716233 
Step 3813 | loss:2.1458559036254883 lr:0.00011017365642977599 tokens_per_second_per_gpu:2119.1998837035335 
Step 3814 | loss:2.1058759689331055 lr:0.00011013451120296982 tokens_per_second_per_gpu:2168.659049668902 
Step 3815 | loss:2.1461472511291504 lr:0.00011009536440702437 tokens_per_second_per_gpu:2182.7987162817785 
Step 3816 | loss:2.087507963180542 lr:0.00011005621604800078 tokens_per_second_per_gpu:2107.3922395736054 
Step 3817 | loss:2.047980785369873 lr:0.0001100170661319605 tokens_per_second_per_gpu:2164.701939337175 
Step 3818 | loss:2.1855509281158447 lr:0.00010997791466496511 tokens_per_second_per_gpu:2155.4468170040614 
Step 3819 | loss:2.0948081016540527 lr:0.00010993876165307648 tokens_per_second_per_gpu:2031.9246896426787 
Step 3820 | loss:2.1393816471099854 lr:0.00010989960710235679 tokens_per_second_per_gpu:2100.7136405898887 
Step 3821 | loss:2.1131491661071777 lr:0.00010986045101886828 tokens_per_second_per_gpu:2185.811712046937 
Step 3822 | loss:2.053647756576538 lr:0.0001098212934086736 tokens_per_second_per_gpu:2194.489315167582 
Step 3823 | loss:2.0704102516174316 lr:0.00010978213427783557 tokens_per_second_per_gpu:2175.292727915019 
Step 3824 | loss:2.081035614013672 lr:0.00010974297363241724 tokens_per_second_per_gpu:2141.6388106709956 
Step 3825 | loss:2.129030227661133 lr:0.0001097038114784819 tokens_per_second_per_gpu:2180.0357942032147 
Step 3826 | loss:2.0992889404296875 lr:0.00010966464782209311 tokens_per_second_per_gpu:2162.8243680293963 
Step 3827 | loss:2.0991129875183105 lr:0.00010962548266931456 tokens_per_second_per_gpu:2161.59684262177 
Step 3828 | loss:2.14630126953125 lr:0.00010958631602621028 tokens_per_second_per_gpu:2189.6837125202824 
Step 3829 | loss:2.01011323928833 lr:0.00010954714789884452 tokens_per_second_per_gpu:2175.304042839172 
Step 3830 | loss:2.0949912071228027 lr:0.0001095079782932817 tokens_per_second_per_gpu:2134.170346322372 
Step 3831 | loss:2.1327342987060547 lr:0.00010946880721558648 tokens_per_second_per_gpu:2179.5394052493602 
Step 3832 | loss:2.0673067569732666 lr:0.00010942963467182379 tokens_per_second_per_gpu:2192.3901690268544 
Step 3833 | loss:2.0765531063079834 lr:0.00010939046066805877 tokens_per_second_per_gpu:2165.517928895214 
Step 3834 | loss:2.0824108123779297 lr:0.00010935128521035677 tokens_per_second_per_gpu:2187.1710144301073 
Step 3835 | loss:2.085439682006836 lr:0.00010931210830478338 tokens_per_second_per_gpu:2129.3319052832035 
Step 3836 | loss:2.131330728530884 lr:0.00010927292995740444 tokens_per_second_per_gpu:2193.5590352793247 
Step 3837 | loss:2.1235573291778564 lr:0.00010923375017428592 tokens_per_second_per_gpu:2162.9956633415054 
Step 3838 | loss:2.1700265407562256 lr:0.00010919456896149411 tokens_per_second_per_gpu:2145.0239030917214 
Step 3839 | loss:2.074859619140625 lr:0.0001091553863250955 tokens_per_second_per_gpu:2117.4347360963257 
Step 3840 | loss:2.141720771789551 lr:0.00010911620227115678 tokens_per_second_per_gpu:2046.5525499594173 
Step 3841 | loss:2.074709892272949 lr:0.00010907701680574486 tokens_per_second_per_gpu:2163.395665339811 
Step 3842 | loss:2.1012954711914062 lr:0.00010903782993492689 tokens_per_second_per_gpu:2156.9143606986345 
Step 3843 | loss:2.1458492279052734 lr:0.00010899864166477019 tokens_per_second_per_gpu:2175.0644738752612 
Step 3844 | loss:2.0706064701080322 lr:0.00010895945200134235 tokens_per_second_per_gpu:2118.3663564597114 
Step 3845 | loss:2.0370943546295166 lr:0.00010892026095071115 tokens_per_second_per_gpu:2189.2047505431033 
Step 3846 | loss:2.1121559143066406 lr:0.00010888106851894459 tokens_per_second_per_gpu:2136.21144651744 
Step 3847 | loss:2.033003091812134 lr:0.00010884187471211094 tokens_per_second_per_gpu:2077.4618292205164 
Step 3848 | loss:2.125018358230591 lr:0.00010880267953627852 tokens_per_second_per_gpu:2188.6066488608203 
Step 3849 | loss:2.0735092163085938 lr:0.00010876348299751604 tokens_per_second_per_gpu:2173.2935557658448 
Step 3850 | loss:2.1919503211975098 lr:0.00010872428510189237 tokens_per_second_per_gpu:2139.9276695935773 
Step 3851 | loss:2.1189398765563965 lr:0.0001086850858554765 tokens_per_second_per_gpu:2088.8914089585046 
Step 3852 | loss:2.152036666870117 lr:0.00010864588526433772 tokens_per_second_per_gpu:2126.1838398495393 
Step 3853 | loss:2.117281675338745 lr:0.00010860668333454557 tokens_per_second_per_gpu:2143.812933834661 
Step 3854 | loss:2.085954189300537 lr:0.00010856748007216966 tokens_per_second_per_gpu:2186.502021966962 
Step 3855 | loss:2.0708627700805664 lr:0.00010852827548327991 tokens_per_second_per_gpu:2178.2046098490027 
Step 3856 | loss:2.114189386367798 lr:0.00010848906957394643 tokens_per_second_per_gpu:2192.565031817019 
Step 3857 | loss:2.1097123622894287 lr:0.00010844986235023948 tokens_per_second_per_gpu:2136.5932549569015 
Step 3858 | loss:2.1069412231445312 lr:0.00010841065381822959 tokens_per_second_per_gpu:2134.044477951737 
Step 3859 | loss:2.1275792121887207 lr:0.00010837144398398747 tokens_per_second_per_gpu:2074.723148138468 
Step 3860 | loss:2.0691933631896973 lr:0.00010833223285358405 tokens_per_second_per_gpu:2146.5895872244555 
Step 3861 | loss:2.0905041694641113 lr:0.00010829302043309037 tokens_per_second_per_gpu:2143.0610855487544 
Step 3862 | loss:2.1112594604492188 lr:0.00010825380672857782 tokens_per_second_per_gpu:2161.9349174044314 
Step 3863 | loss:2.036078691482544 lr:0.00010821459174611785 tokens_per_second_per_gpu:2130.918991469533 
Step 3864 | loss:2.1159286499023438 lr:0.0001081753754917822 tokens_per_second_per_gpu:2170.564409757189 
Step 3865 | loss:2.1207761764526367 lr:0.00010813615797164276 tokens_per_second_per_gpu:2166.2518931047057 
Step 3866 | loss:2.1386823654174805 lr:0.0001080969391917716 tokens_per_second_per_gpu:2190.2777976398474 
Step 3867 | loss:2.0652990341186523 lr:0.00010805771915824105 tokens_per_second_per_gpu:2105.920203600482 
Step 3868 | loss:2.170186996459961 lr:0.00010801849787712364 tokens_per_second_per_gpu:2160.390529295944 
Step 3869 | loss:2.0324325561523438 lr:0.00010797927535449195 tokens_per_second_per_gpu:2139.2877235691176 
Step 3870 | loss:2.1485891342163086 lr:0.0001079400515964189 tokens_per_second_per_gpu:2175.8812090155334 
Step 3871 | loss:2.0849928855895996 lr:0.00010790082660897758 tokens_per_second_per_gpu:2171.984872059284 
Step 3872 | loss:2.082343578338623 lr:0.00010786160039824123 tokens_per_second_per_gpu:2137.634269489123 
Step 3873 | loss:2.1474385261535645 lr:0.00010782237297028326 tokens_per_second_per_gpu:2150.3656192255294 
Step 3874 | loss:2.0678484439849854 lr:0.00010778314433117733 tokens_per_second_per_gpu:2134.972621301148 
Step 3875 | loss:2.049509286880493 lr:0.00010774391448699728 tokens_per_second_per_gpu:2180.8807541945134 
Step 3876 | loss:2.1246519088745117 lr:0.00010770468344381708 tokens_per_second_per_gpu:2174.323938401476 
Step 3877 | loss:2.124776840209961 lr:0.00010766545120771094 tokens_per_second_per_gpu:2172.168724891297 
Step 3878 | loss:2.092672348022461 lr:0.00010762621778475323 tokens_per_second_per_gpu:2173.051314396549 
Step 3879 | loss:2.080549716949463 lr:0.00010758698318101852 tokens_per_second_per_gpu:2172.7610843953203 
Step 3880 | loss:2.0677337646484375 lr:0.00010754774740258158 tokens_per_second_per_gpu:2165.89340146128 
Step 3881 | loss:2.155323028564453 lr:0.00010750851045551727 tokens_per_second_per_gpu:2149.5152891990642 
Step 3882 | loss:2.1539151668548584 lr:0.00010746927234590071 tokens_per_second_per_gpu:2172.111341485879 
Step 3883 | loss:2.0836222171783447 lr:0.00010743003307980724 tokens_per_second_per_gpu:2184.043549521386 
Step 3884 | loss:2.104649782180786 lr:0.0001073907926633123 tokens_per_second_per_gpu:2192.2901009014013 
Step 3885 | loss:2.1216683387756348 lr:0.0001073515511024915 tokens_per_second_per_gpu:2118.1412383214038 
Step 3886 | loss:2.1936187744140625 lr:0.0001073123084034207 tokens_per_second_per_gpu:2130.2988412392065 
Step 3887 | loss:2.1166553497314453 lr:0.0001072730645721759 tokens_per_second_per_gpu:2188.261393639543 
Step 3888 | loss:2.066742420196533 lr:0.00010723381961483326 tokens_per_second_per_gpu:2170.533029558723 
Step 3889 | loss:2.099307060241699 lr:0.0001071945735374691 tokens_per_second_per_gpu:2156.977975649949 
Step 3890 | loss:2.1085801124572754 lr:0.00010715532634615996 tokens_per_second_per_gpu:2191.030640075786 
Step 3891 | loss:2.129937171936035 lr:0.00010711607804698254 tokens_per_second_per_gpu:2178.5966466982777 
Step 3892 | loss:2.162616014480591 lr:0.00010707682864601372 tokens_per_second_per_gpu:2186.2915290674737 
Step 3893 | loss:2.05598783493042 lr:0.00010703757814933049 tokens_per_second_per_gpu:2098.7623815609973 
Step 3894 | loss:2.1242241859436035 lr:0.00010699832656301008 tokens_per_second_per_gpu:2188.1717998797244 
Step 3895 | loss:2.062699794769287 lr:0.00010695907389312989 tokens_per_second_per_gpu:2186.512754963184 
Step 3896 | loss:2.118396282196045 lr:0.00010691982014576742 tokens_per_second_per_gpu:2137.491408401071 
Step 3897 | loss:2.1379475593566895 lr:0.00010688056532700039 tokens_per_second_per_gpu:2168.4318618085836 
Step 3898 | loss:2.098872184753418 lr:0.00010684130944290669 tokens_per_second_per_gpu:2182.124733062847 
Step 3899 | loss:2.129160165786743 lr:0.00010680205249956432 tokens_per_second_per_gpu:2194.3269270140495 
Step 3900 | loss:2.1498947143554688 lr:0.00010676279450305152 tokens_per_second_per_gpu:2191.74655349694 
Step 3901 | loss:2.1095733642578125 lr:0.00010672353545944663 tokens_per_second_per_gpu:2183.3840522474925 
Step 3902 | loss:2.0482280254364014 lr:0.00010668427537482819 tokens_per_second_per_gpu:2158.653167759607 
Step 3903 | loss:2.044769763946533 lr:0.00010664501425527489 tokens_per_second_per_gpu:2190.8295205223344 
Step 3904 | loss:2.1246497631073 lr:0.00010660575210686558 tokens_per_second_per_gpu:2133.5103649748066 
Step 3905 | loss:2.149883270263672 lr:0.00010656648893567927 tokens_per_second_per_gpu:2174.372812771343 
Step 3906 | loss:2.173679828643799 lr:0.0001065272247477951 tokens_per_second_per_gpu:2165.0424879873162 
Step 3907 | loss:2.141111373901367 lr:0.00010648795954929245 tokens_per_second_per_gpu:2166.4949699242943 
Step 3908 | loss:2.1273913383483887 lr:0.00010644869334625074 tokens_per_second_per_gpu:2189.6177061225294 
Step 3909 | loss:2.103093385696411 lr:0.00010640942614474962 tokens_per_second_per_gpu:2181.3859286302436 
Step 3910 | loss:2.056605815887451 lr:0.00010637015795086894 tokens_per_second_per_gpu:2144.1230320929503 
Step 3911 | loss:2.088113307952881 lr:0.00010633088877068858 tokens_per_second_per_gpu:2106.7200849235046 
Step 3912 | loss:2.093090057373047 lr:0.00010629161861028862 tokens_per_second_per_gpu:2182.9071868961123 
Step 3913 | loss:2.097158908843994 lr:0.00010625234747574937 tokens_per_second_per_gpu:2191.954246718813 
Step 3914 | loss:2.1875782012939453 lr:0.00010621307537315124 tokens_per_second_per_gpu:2015.8547903711171 
Step 3915 | loss:2.078049659729004 lr:0.0001061738023085747 tokens_per_second_per_gpu:2094.741728463735 
Step 3916 | loss:2.1562557220458984 lr:0.00010613452828810049 tokens_per_second_per_gpu:2141.916102125358 
Step 3917 | loss:2.083688497543335 lr:0.00010609525331780947 tokens_per_second_per_gpu:2193.48992120477 
Step 3918 | loss:2.0528345108032227 lr:0.00010605597740378261 tokens_per_second_per_gpu:2096.6896881759335 
Step 3919 | loss:2.1418190002441406 lr:0.0001060167005521011 tokens_per_second_per_gpu:2165.6134601922163 
Step 3920 | loss:2.1285436153411865 lr:0.00010597742276884614 tokens_per_second_per_gpu:2177.050596895814 
Step 3921 | loss:2.092526912689209 lr:0.00010593814406009923 tokens_per_second_per_gpu:2189.2224742776098 
Step 3922 | loss:2.0821049213409424 lr:0.00010589886443194193 tokens_per_second_per_gpu:2193.2235828791145 
Step 3923 | loss:2.2052853107452393 lr:0.00010585958389045591 tokens_per_second_per_gpu:2194.6480216983846 
Step 3924 | loss:2.101132392883301 lr:0.0001058203024417231 tokens_per_second_per_gpu:2144.376557985587 
Step 3925 | loss:2.0105702877044678 lr:0.00010578102009182544 tokens_per_second_per_gpu:2151.7792351895646 
Step 3926 | loss:2.148728370666504 lr:0.00010574173684684507 tokens_per_second_per_gpu:2144.356825778263 
Step 3927 | loss:2.133241653442383 lr:0.00010570245271286428 tokens_per_second_per_gpu:2124.2333795194836 
Step 3928 | loss:2.0813217163085938 lr:0.0001056631676959655 tokens_per_second_per_gpu:2160.4396904538708 
Step 3929 | loss:2.078773021697998 lr:0.00010562388180223124 tokens_per_second_per_gpu:2183.7026314713835 
Step 3930 | loss:2.067187786102295 lr:0.0001055845950377442 tokens_per_second_per_gpu:2190.0333919096533 
Step 3931 | loss:2.063638687133789 lr:0.00010554530740858724 tokens_per_second_per_gpu:2136.811210584923 
Step 3932 | loss:2.0993309020996094 lr:0.00010550601892084325 tokens_per_second_per_gpu:2165.078031783986 
Step 3933 | loss:2.092369318008423 lr:0.00010546672958059532 tokens_per_second_per_gpu:2172.014549775038 
Step 3934 | loss:2.0947458744049072 lr:0.00010542743939392673 tokens_per_second_per_gpu:2071.611286445663 
Step 3935 | loss:2.065925121307373 lr:0.00010538814836692077 tokens_per_second_per_gpu:2195.2371809623287 
Step 3936 | loss:2.1019108295440674 lr:0.00010534885650566096 tokens_per_second_per_gpu:2162.5551020421294 
Step 3937 | loss:2.0893478393554688 lr:0.00010530956381623088 tokens_per_second_per_gpu:2127.917448782702 
Step 3938 | loss:2.1217167377471924 lr:0.00010527027030471428 tokens_per_second_per_gpu:2134.8958133106285 
Step 3939 | loss:2.086854934692383 lr:0.000105230975977195 tokens_per_second_per_gpu:2148.98886868568 
Step 3940 | loss:2.0570759773254395 lr:0.00010519168083975708 tokens_per_second_per_gpu:2174.9770802422886 
Step 3941 | loss:2.1198325157165527 lr:0.00010515238489848462 tokens_per_second_per_gpu:2173.334165279103 
Step 3942 | loss:2.1093595027923584 lr:0.0001051130881594618 tokens_per_second_per_gpu:2192.6595906138873 
Step 3943 | loss:2.1019442081451416 lr:0.00010507379062877308 tokens_per_second_per_gpu:2098.6489345852733 
Step 3944 | loss:2.1038784980773926 lr:0.00010503449231250291 tokens_per_second_per_gpu:2154.3159222058343 
Step 3945 | loss:2.1314878463745117 lr:0.00010499519321673583 tokens_per_second_per_gpu:2145.5866535524906 
Step 3946 | loss:2.121791362762451 lr:0.00010495589334755667 tokens_per_second_per_gpu:2151.8413639743403 
Step 3947 | loss:2.0853967666625977 lr:0.00010491659271105023 tokens_per_second_per_gpu:2195.879780450293 
Step 3948 | loss:2.1153221130371094 lr:0.00010487729131330146 tokens_per_second_per_gpu:2172.2661223439513 
Step 3949 | loss:2.074709892272949 lr:0.0001048379891603955 tokens_per_second_per_gpu:2033.4132584675858 
Step 3950 | loss:2.0855515003204346 lr:0.00010479868625841753 tokens_per_second_per_gpu:2207.2124488171103 
Step 3951 | loss:2.043067455291748 lr:0.00010475938261345283 tokens_per_second_per_gpu:2226.6533287647785 
Step 3952 | loss:2.077016830444336 lr:0.0001047200782315869 tokens_per_second_per_gpu:2205.368928382281 
Step 3953 | loss:2.1073405742645264 lr:0.0001046807731189052 tokens_per_second_per_gpu:2179.0239562617803 
Step 3954 | loss:2.042302370071411 lr:0.00010464146728149349 tokens_per_second_per_gpu:2147.677743540617 
Step 3955 | loss:2.0553982257843018 lr:0.00010460216072543747 tokens_per_second_per_gpu:2221.7546110134463 
Step 3956 | loss:2.0068182945251465 lr:0.00010456285345682307 tokens_per_second_per_gpu:2218.2187619720025 
Step 3957 | loss:2.135007381439209 lr:0.00010452354548173621 tokens_per_second_per_gpu:2197.7689789648243 
Step 3958 | loss:2.0988075733184814 lr:0.00010448423680626309 tokens_per_second_per_gpu:2216.913217799939 
Step 3959 | loss:2.0644655227661133 lr:0.00010444492743648987 tokens_per_second_per_gpu:2225.8911318655755 
Step 3960 | loss:2.128753662109375 lr:0.0001044056173785029 tokens_per_second_per_gpu:2167.261188848414 
Step 3961 | loss:2.1132328510284424 lr:0.00010436630663838856 tokens_per_second_per_gpu:2215.865385399721 
Step 3962 | loss:2.114704132080078 lr:0.00010432699522223342 tokens_per_second_per_gpu:2231.98323738727 
Step 3963 | loss:2.1023106575012207 lr:0.00010428768313612407 tokens_per_second_per_gpu:2103.700652916223 
Step 3964 | loss:2.198610305786133 lr:0.00010424837038614733 tokens_per_second_per_gpu:2226.0832985168904 
Step 3965 | loss:2.131713390350342 lr:0.00010420905697838996 tokens_per_second_per_gpu:2227.0295311308423 
Step 3966 | loss:2.0890026092529297 lr:0.00010416974291893897 tokens_per_second_per_gpu:2124.9257725008756 
Step 3967 | loss:2.090531826019287 lr:0.00010413042821388135 tokens_per_second_per_gpu:2174.09062562805 
Step 3968 | loss:2.049551010131836 lr:0.0001040911128693043 tokens_per_second_per_gpu:2209.057170804296 
Step 3969 | loss:2.0945544242858887 lr:0.000104051796891295 tokens_per_second_per_gpu:2230.24507934313 
Step 3970 | loss:2.073230743408203 lr:0.00010401248028594088 tokens_per_second_per_gpu:2221.9177631196853 
Step 3971 | loss:2.049062728881836 lr:0.00010397316305932932 tokens_per_second_per_gpu:2207.1892337582067 
Step 3972 | loss:2.1370091438293457 lr:0.00010393384521754783 tokens_per_second_per_gpu:2178.6569765087515 
Step 3973 | loss:2.1059508323669434 lr:0.00010389452676668412 tokens_per_second_per_gpu:2215.955789799224 
Step 3974 | loss:2.0972371101379395 lr:0.00010385520771282589 tokens_per_second_per_gpu:2131.0969893977235 
Step 3975 | loss:2.1215052604675293 lr:0.00010381588806206087 tokens_per_second_per_gpu:2207.5371331067045 
Step 3976 | loss:2.0076723098754883 lr:0.00010377656782047711 tokens_per_second_per_gpu:2205.8617275687884 
Step 3977 | loss:2.087792158126831 lr:0.00010373724699416252 tokens_per_second_per_gpu:2186.9061140632125 
Step 3978 | loss:2.1458234786987305 lr:0.00010369792558920521 tokens_per_second_per_gpu:2228.2985422935644 
Step 3979 | loss:2.154712677001953 lr:0.00010365860361169341 tokens_per_second_per_gpu:2203.945368824262 
Step 3980 | loss:2.0849196910858154 lr:0.00010361928106771535 tokens_per_second_per_gpu:2205.887846756575 
Step 3981 | loss:2.124560832977295 lr:0.00010357995796335937 tokens_per_second_per_gpu:2232.054660201022 
Step 3982 | loss:2.0919408798217773 lr:0.00010354063430471399 tokens_per_second_per_gpu:2188.114362694462 
Step 3983 | loss:2.103670120239258 lr:0.00010350131009786766 tokens_per_second_per_gpu:2221.366243538067 
Step 3984 | loss:2.0826549530029297 lr:0.00010346198534890902 tokens_per_second_per_gpu:2219.0488301488185 
Step 3985 | loss:2.072661876678467 lr:0.0001034226600639268 tokens_per_second_per_gpu:2229.5400249827007 
Step 3986 | loss:2.089275360107422 lr:0.00010338333424900979 tokens_per_second_per_gpu:2212.0309508946143 
Step 3987 | loss:2.1059975624084473 lr:0.0001033440079102468 tokens_per_second_per_gpu:2212.187944562074 
Step 3988 | loss:2.1004204750061035 lr:0.00010330468105372681 tokens_per_second_per_gpu:2219.1309641110565 
Step 3989 | loss:2.0750837326049805 lr:0.00010326535368553889 tokens_per_second_per_gpu:2231.0730471064658 
Step 3990 | loss:2.066985607147217 lr:0.00010322602581177205 tokens_per_second_per_gpu:2218.9573862977186 
Step 3991 | loss:2.0435571670532227 lr:0.00010318669743851556 tokens_per_second_per_gpu:2141.117457052744 
Step 3992 | loss:2.039461851119995 lr:0.00010314736857185865 tokens_per_second_per_gpu:2196.00254067208 
Step 3993 | loss:2.047945976257324 lr:0.00010310803921789063 tokens_per_second_per_gpu:2213.661865704517 
Step 3994 | loss:2.0818138122558594 lr:0.00010306870938270097 tokens_per_second_per_gpu:2226.4803650990902 
Step 3995 | loss:2.135471820831299 lr:0.00010302937907237915 tokens_per_second_per_gpu:2219.8763174991527 
Step 3996 | loss:2.1186094284057617 lr:0.00010299004829301466 tokens_per_second_per_gpu:2208.3926559003326 
Step 3997 | loss:2.171483039855957 lr:0.00010295071705069723 tokens_per_second_per_gpu:2229.3302149107494 
Step 3998 | loss:2.0642189979553223 lr:0.00010291138535151652 tokens_per_second_per_gpu:2228.596956556521 
Step 3999 | loss:2.1360483169555664 lr:0.00010287205320156226 tokens_per_second_per_gpu:2208.536402549528 
Step 4000 | loss:2.161865711212158 lr:0.00010283272060692441 tokens_per_second_per_gpu:2131.944943608795 
Step 4001 | loss:2.122640609741211 lr:0.00010279338757369279 tokens_per_second_per_gpu:2247.765458888061 
Step 4002 | loss:2.1182143688201904 lr:0.00010275405410795743 tokens_per_second_per_gpu:2231.54757683864 
Step 4003 | loss:2.0477869510650635 lr:0.00010271472021580838 tokens_per_second_per_gpu:2235.0156063642025 
Step 4004 | loss:2.192291498184204 lr:0.00010267538590333572 tokens_per_second_per_gpu:2240.2557511396485 
Step 4005 | loss:2.08480167388916 lr:0.00010263605117662966 tokens_per_second_per_gpu:2227.6465213722936 
Step 4006 | loss:2.1462221145629883 lr:0.00010259671604178047 tokens_per_second_per_gpu:2226.880584458473 
Step 4007 | loss:2.0724987983703613 lr:0.00010255738050487839 tokens_per_second_per_gpu:2202.4880903999447 
Step 4008 | loss:2.1470935344696045 lr:0.00010251804457201386 tokens_per_second_per_gpu:2207.852048441835 
Step 4009 | loss:2.1131041049957275 lr:0.00010247870824927728 tokens_per_second_per_gpu:2199.362959716196 
Step 4010 | loss:2.1080398559570312 lr:0.00010243937154275915 tokens_per_second_per_gpu:2221.3949297062713 
Step 4011 | loss:2.0847105979919434 lr:0.00010240003445855 tokens_per_second_per_gpu:2223.4847620630126 
Step 4012 | loss:2.1184897422790527 lr:0.00010236069700274047 tokens_per_second_per_gpu:2217.2355394772035 
Step 4013 | loss:2.112626791000366 lr:0.00010232135918142124 tokens_per_second_per_gpu:2212.8816920806335 
Step 4014 | loss:2.1792609691619873 lr:0.000102282021000683 tokens_per_second_per_gpu:2218.517060299282 
Step 4015 | loss:2.0886330604553223 lr:0.00010224268246661652 tokens_per_second_per_gpu:2225.0215652223087 
Step 4016 | loss:2.082900047302246 lr:0.00010220334358531272 tokens_per_second_per_gpu:2228.574792718465 
Step 4017 | loss:2.13598370552063 lr:0.00010216400436286237 tokens_per_second_per_gpu:2202.8551365283697 
Step 4018 | loss:2.156583309173584 lr:0.00010212466480535649 tokens_per_second_per_gpu:2203.0495362328325 
Step 4019 | loss:2.089181423187256 lr:0.00010208532491888608 tokens_per_second_per_gpu:2217.06327944566 
Step 4020 | loss:2.0991058349609375 lr:0.0001020459847095421 tokens_per_second_per_gpu:2229.910749185087 
Step 4021 | loss:2.103093147277832 lr:0.00010200664418341574 tokens_per_second_per_gpu:2159.724194552706 
Step 4022 | loss:2.0728282928466797 lr:0.00010196730334659812 tokens_per_second_per_gpu:2222.2669340714056 
Step 4023 | loss:2.0948243141174316 lr:0.00010192796220518039 tokens_per_second_per_gpu:2192.158766688292 
Step 4024 | loss:2.059246778488159 lr:0.00010188862076525385 tokens_per_second_per_gpu:2214.1176275778057 
Step 4025 | loss:2.0668911933898926 lr:0.00010184927903290975 tokens_per_second_per_gpu:2160.925677499594 
Step 4026 | loss:2.103226661682129 lr:0.00010180993701423938 tokens_per_second_per_gpu:2125.6296453569394 
Step 4027 | loss:2.0798239707946777 lr:0.00010177059471533421 tokens_per_second_per_gpu:2232.538652637263 
Step 4028 | loss:2.1137237548828125 lr:0.00010173125214228559 tokens_per_second_per_gpu:2225.8659660528233 
Step 4029 | loss:2.0178933143615723 lr:0.00010169190930118498 tokens_per_second_per_gpu:2167.8575298118294 
Step 4030 | loss:2.1309657096862793 lr:0.00010165256619812393 tokens_per_second_per_gpu:2216.602468648246 
Step 4031 | loss:2.098116159439087 lr:0.00010161322283919392 tokens_per_second_per_gpu:2193.5952935943806 
Step 4032 | loss:2.153265953063965 lr:0.00010157387923048658 tokens_per_second_per_gpu:2184.1576290797148 
Step 4033 | loss:2.123399019241333 lr:0.00010153453537809354 tokens_per_second_per_gpu:2230.2076067319763 
Step 4034 | loss:2.113537311553955 lr:0.00010149519128810641 tokens_per_second_per_gpu:2187.4653991208666 
Step 4035 | loss:2.130852222442627 lr:0.0001014558469666169 tokens_per_second_per_gpu:2178.5837148003875 
Step 4036 | loss:2.092331886291504 lr:0.00010141650241971676 tokens_per_second_per_gpu:2177.425240375596 
Step 4037 | loss:2.162109851837158 lr:0.00010137715765349778 tokens_per_second_per_gpu:2189.678790187171 
Step 4038 | loss:2.132205009460449 lr:0.00010133781267405169 tokens_per_second_per_gpu:2190.027872387871 
Step 4039 | loss:2.1930603981018066 lr:0.00010129846748747036 tokens_per_second_per_gpu:2221.7459170836105 
Step 4040 | loss:2.071613073348999 lr:0.0001012591220998457 tokens_per_second_per_gpu:2234.0778338958166 
Step 4041 | loss:2.069365978240967 lr:0.0001012197765172695 tokens_per_second_per_gpu:2215.6129774378105 
Step 4042 | loss:2.0329418182373047 lr:0.0001011804307458338 tokens_per_second_per_gpu:2212.93552180124 
Step 4043 | loss:2.0856761932373047 lr:0.00010114108479163049 tokens_per_second_per_gpu:2193.1423420899523 
Step 4044 | loss:2.0803401470184326 lr:0.00010110173866075152 tokens_per_second_per_gpu:2232.279600680996 
Step 4045 | loss:2.0754799842834473 lr:0.00010106239235928902 tokens_per_second_per_gpu:2138.487202737301 
Step 4046 | loss:2.073047637939453 lr:0.00010102304589333496 tokens_per_second_per_gpu:2207.910024113801 
Step 4047 | loss:2.084030866622925 lr:0.00010098369926898135 tokens_per_second_per_gpu:2176.2230869752275 
Step 4048 | loss:2.073653221130371 lr:0.00010094435249232037 tokens_per_second_per_gpu:2222.5935264113873 
Step 4049 | loss:2.0821032524108887 lr:0.00010090500556944409 tokens_per_second_per_gpu:2226.548919088268 
Step 4050 | loss:2.0912272930145264 lr:0.00010086565850644462 tokens_per_second_per_gpu:2098.4279545594873 
Step 4051 | loss:2.0638656616210938 lr:0.00010082631130941417 tokens_per_second_per_gpu:2216.113797529456 
Step 4052 | loss:2.065706968307495 lr:0.00010078696398444487 tokens_per_second_per_gpu:2173.9685770743563 
Step 4053 | loss:2.080420732498169 lr:0.00010074761653762894 tokens_per_second_per_gpu:2200.2320671217035 
Step 4054 | loss:2.1117589473724365 lr:0.0001007082689750586 tokens_per_second_per_gpu:2180.4525530718056 
Step 4055 | loss:2.0870189666748047 lr:0.00010066892130282605 tokens_per_second_per_gpu:2184.0141171303853 
Step 4056 | loss:2.1144614219665527 lr:0.00010062957352702358 tokens_per_second_per_gpu:2132.1283868345013 
Step 4057 | loss:2.058713436126709 lr:0.00010059022565374345 tokens_per_second_per_gpu:2196.6140726304548 
Step 4058 | loss:2.04734468460083 lr:0.00010055087768907791 tokens_per_second_per_gpu:2226.9305800830066 
Step 4059 | loss:2.131758213043213 lr:0.00010051152963911929 tokens_per_second_per_gpu:2214.8586252956984 
Step 4060 | loss:2.1146936416625977 lr:0.00010047218150995988 tokens_per_second_per_gpu:2183.9187611451757 
Step 4061 | loss:2.0606932640075684 lr:0.00010043283330769202 tokens_per_second_per_gpu:2215.3052843942432 
Step 4062 | loss:2.0843119621276855 lr:0.00010039348503840802 tokens_per_second_per_gpu:2226.597903270574 
Step 4063 | loss:2.1014652252197266 lr:0.00010035413670820022 tokens_per_second_per_gpu:2155.504422841208 
Step 4064 | loss:2.1260664463043213 lr:0.000100314788323161 tokens_per_second_per_gpu:2237.2262550420037 
Step 4065 | loss:2.1113593578338623 lr:0.00010027543988938269 tokens_per_second_per_gpu:2204.137575028746 
Step 4066 | loss:2.109060287475586 lr:0.00010023609141295767 tokens_per_second_per_gpu:2221.222066816802 
Step 4067 | loss:2.037851572036743 lr:0.00010019674289997834 tokens_per_second_per_gpu:2182.360627379706 
Step 4068 | loss:2.0470199584960938 lr:0.00010015739435653699 tokens_per_second_per_gpu:2202.6273546424522 
Step 4069 | loss:2.141944169998169 lr:0.00010011804578872614 tokens_per_second_per_gpu:2195.765248391888 
Step 4070 | loss:2.0909500122070312 lr:0.0001000786972026381 tokens_per_second_per_gpu:2173.618212761445 
Step 4071 | loss:2.102411985397339 lr:0.00010003934860436523 tokens_per_second_per_gpu:2218.1310063454234 
Step 4072 | loss:2.0983848571777344 lr:0.0001 tokens_per_second_per_gpu:2228.437904263614 
Step 4073 | loss:2.1099233627319336 lr:9.996065139563479e-05 tokens_per_second_per_gpu:2228.710573287473 
Step 4074 | loss:2.0805511474609375 lr:9.992130279736195e-05 tokens_per_second_per_gpu:2215.3324087217693 
Step 4075 | loss:2.0701804161071777 lr:9.988195421127387e-05 tokens_per_second_per_gpu:2223.3033908281773 
Step 4076 | loss:2.135819673538208 lr:9.9842605643463e-05 tokens_per_second_per_gpu:2230.910159079555 
Step 4077 | loss:2.105563163757324 lr:9.98032571000217e-05 tokens_per_second_per_gpu:2219.7446155755288 
Step 4078 | loss:2.082993268966675 lr:9.976390858704237e-05 tokens_per_second_per_gpu:2222.609212491668 
Step 4079 | loss:2.097524642944336 lr:9.972456011061736e-05 tokens_per_second_per_gpu:2182.7243387616227 
Step 4080 | loss:2.1225314140319824 lr:9.968521167683905e-05 tokens_per_second_per_gpu:2199.1406253556943 
Step 4081 | loss:2.11757755279541 lr:9.96458632917998e-05 tokens_per_second_per_gpu:2173.5758107829747 
Step 4082 | loss:2.0632801055908203 lr:9.960651496159201e-05 tokens_per_second_per_gpu:2228.429501619308 
Step 4083 | loss:2.1210665702819824 lr:9.9567166692308e-05 tokens_per_second_per_gpu:2172.8005485993294 
Step 4084 | loss:2.141206741333008 lr:9.952781849004013e-05 tokens_per_second_per_gpu:2216.198782680864 
Step 4085 | loss:2.055701732635498 lr:9.948847036088073e-05 tokens_per_second_per_gpu:2211.4540927747694 
Step 4086 | loss:2.0596635341644287 lr:9.94491223109221e-05 tokens_per_second_per_gpu:2161.055134334754 
Step 4087 | loss:2.119546890258789 lr:9.940977434625656e-05 tokens_per_second_per_gpu:2182.124430532269 
Step 4088 | loss:2.0303564071655273 lr:9.937042647297643e-05 tokens_per_second_per_gpu:2212.8801233580907 
Step 4089 | loss:2.124757766723633 lr:9.933107869717396e-05 tokens_per_second_per_gpu:2230.7892625989516 
Step 4090 | loss:2.0483388900756836 lr:9.929173102494144e-05 tokens_per_second_per_gpu:2216.7486313249638 
Step 4091 | loss:2.063338279724121 lr:9.925238346237106e-05 tokens_per_second_per_gpu:2128.079835721115 
Step 4092 | loss:2.08894681930542 lr:9.921303601555512e-05 tokens_per_second_per_gpu:2220.3669161504163 
Step 4093 | loss:2.1054649353027344 lr:9.917368869058585e-05 tokens_per_second_per_gpu:2170.633025671614 
Step 4094 | loss:2.0655527114868164 lr:9.91343414935554e-05 tokens_per_second_per_gpu:2116.222803073457 
Step 4095 | loss:2.058573007583618 lr:9.909499443055594e-05 tokens_per_second_per_gpu:2217.9549998793614 
Step 4096 | loss:2.0786869525909424 lr:9.905564750767967e-05 tokens_per_second_per_gpu:2228.6171491739924 
Step 4097 | loss:2.1430678367614746 lr:9.901630073101865e-05 tokens_per_second_per_gpu:2174.3094136492277 
Step 4098 | loss:2.07035493850708 lr:9.897695410666506e-05 tokens_per_second_per_gpu:2230.522881319802 
Step 4099 | loss:2.126255750656128 lr:9.8937607640711e-05 tokens_per_second_per_gpu:2190.1796380223814 
Step 4100 | loss:2.0682926177978516 lr:9.889826133924849e-05 tokens_per_second_per_gpu:2149.2822312185003 
Step 4101 | loss:2.0382089614868164 lr:9.885891520836956e-05 tokens_per_second_per_gpu:2202.089984460185 
Step 4102 | loss:2.1074025630950928 lr:9.881956925416622e-05 tokens_per_second_per_gpu:2198.394798464485 
Step 4103 | loss:2.1203317642211914 lr:9.878022348273052e-05 tokens_per_second_per_gpu:2197.35291283495 
Step 4104 | loss:2.024552822113037 lr:9.874087790015434e-05 tokens_per_second_per_gpu:2190.972692046976 
Step 4105 | loss:2.1236255168914795 lr:9.870153251252967e-05 tokens_per_second_per_gpu:2191.8115604911445 
Step 4106 | loss:2.081367254257202 lr:9.866218732594836e-05 tokens_per_second_per_gpu:2220.928790613034 
Step 4107 | loss:2.1293320655822754 lr:9.862284234650225e-05 tokens_per_second_per_gpu:2219.725754840567 
Step 4108 | loss:2.03786039352417 lr:9.858349758028324e-05 tokens_per_second_per_gpu:2223.038478464828 
Step 4109 | loss:2.0398287773132324 lr:9.854415303338311e-05 tokens_per_second_per_gpu:2193.405340122963 
Step 4110 | loss:2.1134841442108154 lr:9.850480871189361e-05 tokens_per_second_per_gpu:2173.0733171749152 
Step 4111 | loss:2.140516757965088 lr:9.84654646219065e-05 tokens_per_second_per_gpu:2226.737427490997 
Step 4112 | loss:2.060657501220703 lr:9.842612076951343e-05 tokens_per_second_per_gpu:2188.84736151035 
Step 4113 | loss:2.1752052307128906 lr:9.838677716080609e-05 tokens_per_second_per_gpu:2160.974574473616 
Step 4114 | loss:2.1044178009033203 lr:9.834743380187609e-05 tokens_per_second_per_gpu:2224.7037278838056 
Step 4115 | loss:2.1240768432617188 lr:9.830809069881504e-05 tokens_per_second_per_gpu:2115.124586059036 
Step 4116 | loss:2.063831329345703 lr:9.826874785771444e-05 tokens_per_second_per_gpu:2203.518062625886 
Step 4117 | loss:2.097837448120117 lr:9.822940528466584e-05 tokens_per_second_per_gpu:2167.3376977770527 
Step 4118 | loss:2.0487024784088135 lr:9.819006298576062e-05 tokens_per_second_per_gpu:2233.523545804654 
Step 4119 | loss:2.111830234527588 lr:9.815072096709027e-05 tokens_per_second_per_gpu:2156.839393881547 
Step 4120 | loss:2.100121259689331 lr:9.811137923474617e-05 tokens_per_second_per_gpu:2193.388990301351 
Step 4121 | loss:2.1309099197387695 lr:9.807203779481963e-05 tokens_per_second_per_gpu:2229.482363425706 
Step 4122 | loss:2.1054697036743164 lr:9.803269665340192e-05 tokens_per_second_per_gpu:2174.2169327343845 
Step 4123 | loss:2.1631357669830322 lr:9.799335581658425e-05 tokens_per_second_per_gpu:2215.08479609711 
Step 4124 | loss:2.0813727378845215 lr:9.79540152904579e-05 tokens_per_second_per_gpu:2202.579069733291 
Step 4125 | loss:2.063445568084717 lr:9.791467508111395e-05 tokens_per_second_per_gpu:2182.3621932452947 
Step 4126 | loss:2.120306968688965 lr:9.787533519464353e-05 tokens_per_second_per_gpu:2207.148313918296 
Step 4127 | loss:2.1225123405456543 lr:9.783599563713766e-05 tokens_per_second_per_gpu:2239.51352307148 
Step 4128 | loss:2.0845320224761963 lr:9.779665641468733e-05 tokens_per_second_per_gpu:2211.774530207795 
Step 4129 | loss:2.0441267490386963 lr:9.775731753338346e-05 tokens_per_second_per_gpu:2189.8130088534426 
Step 4130 | loss:2.0635344982147217 lr:9.771797899931702e-05 tokens_per_second_per_gpu:2194.793291983701 
Step 4131 | loss:2.1268396377563477 lr:9.767864081857878e-05 tokens_per_second_per_gpu:2233.6081901909765 
Step 4132 | loss:2.0677595138549805 lr:9.763930299725956e-05 tokens_per_second_per_gpu:2223.9977323469757 
Step 4133 | loss:2.129981517791748 lr:9.759996554145003e-05 tokens_per_second_per_gpu:2173.9696108532316 
Step 4134 | loss:2.119039535522461 lr:9.756062845724087e-05 tokens_per_second_per_gpu:2225.0426794346076 
Step 4135 | loss:2.035372257232666 lr:9.752129175072273e-05 tokens_per_second_per_gpu:2207.8066330926963 
Step 4136 | loss:2.0538878440856934 lr:9.748195542798615e-05 tokens_per_second_per_gpu:2231.054403586451 
Step 4137 | loss:2.127725839614868 lr:9.744261949512162e-05 tokens_per_second_per_gpu:2174.837660213635 
Step 4138 | loss:2.003631830215454 lr:9.740328395821957e-05 tokens_per_second_per_gpu:2233.0709230716016 
Step 4139 | loss:2.0978713035583496 lr:9.736394882337037e-05 tokens_per_second_per_gpu:2206.336891778544 
Step 4140 | loss:2.1432313919067383 lr:9.732461409666429e-05 tokens_per_second_per_gpu:2226.822195188723 
Step 4141 | loss:2.143827438354492 lr:9.728527978419164e-05 tokens_per_second_per_gpu:2221.129161144063 
Step 4142 | loss:2.055015802383423 lr:9.724594589204258e-05 tokens_per_second_per_gpu:2174.6517678830874 
Step 4143 | loss:2.1321070194244385 lr:9.720661242630722e-05 tokens_per_second_per_gpu:2135.790235682398 
Step 4144 | loss:2.105271816253662 lr:9.716727939307562e-05 tokens_per_second_per_gpu:2188.315244357859 
Step 4145 | loss:2.1327571868896484 lr:9.712794679843773e-05 tokens_per_second_per_gpu:2137.818514049341 
Step 4146 | loss:2.061896324157715 lr:9.70886146484835e-05 tokens_per_second_per_gpu:2233.7552465249255 
Step 4147 | loss:2.0353100299835205 lr:9.70492829493028e-05 tokens_per_second_per_gpu:2190.7949883117226 
Step 4148 | loss:2.130272626876831 lr:9.700995170698537e-05 tokens_per_second_per_gpu:2234.826822678399 
Step 4149 | loss:2.080333709716797 lr:9.69706209276209e-05 tokens_per_second_per_gpu:2234.0628483371133 
Step 4150 | loss:2.1352672576904297 lr:9.693129061729904e-05 tokens_per_second_per_gpu:2159.158043230908 
Step 4151 | loss:2.1069517135620117 lr:9.689196078210937e-05 tokens_per_second_per_gpu:2214.864169744558 
Step 4152 | loss:2.0704421997070312 lr:9.685263142814137e-05 tokens_per_second_per_gpu:2224.415918227199 
Step 4153 | loss:2.135309934616089 lr:9.681330256148446e-05 tokens_per_second_per_gpu:2227.965116062151 
Step 4154 | loss:2.113800525665283 lr:9.677397418822797e-05 tokens_per_second_per_gpu:2181.0980092351556 
Step 4155 | loss:2.117981433868408 lr:9.673464631446115e-05 tokens_per_second_per_gpu:2174.710964134148 
Step 4156 | loss:2.1211516857147217 lr:9.669531894627317e-05 tokens_per_second_per_gpu:2224.0781424103693 
Step 4157 | loss:2.067162275314331 lr:9.66559920897532e-05 tokens_per_second_per_gpu:2204.571618733039 
Step 4158 | loss:2.074235439300537 lr:9.661666575099024e-05 tokens_per_second_per_gpu:2223.7510420667354 
Step 4159 | loss:2.096378803253174 lr:9.657733993607321e-05 tokens_per_second_per_gpu:2222.6963086982405 
Step 4160 | loss:2.1275739669799805 lr:9.653801465109101e-05 tokens_per_second_per_gpu:2235.1883693954496 
Step 4161 | loss:2.113879442214966 lr:9.649868990213235e-05 tokens_per_second_per_gpu:2163.8489622887246 
Step 4162 | loss:2.017435073852539 lr:9.645936569528603e-05 tokens_per_second_per_gpu:2187.4389580696507 
Step 4163 | loss:2.1308350563049316 lr:9.642004203664064e-05 tokens_per_second_per_gpu:2201.308413911965 
Step 4164 | loss:2.018608331680298 lr:9.638071893228467e-05 tokens_per_second_per_gpu:2224.099043873002 
Step 4165 | loss:2.0336999893188477 lr:9.634139638830661e-05 tokens_per_second_per_gpu:2177.789410842596 
Step 4166 | loss:2.1046602725982666 lr:9.630207441079477e-05 tokens_per_second_per_gpu:2196.880945301859 
Step 4167 | loss:2.1071279048919678 lr:9.62627530058375e-05 tokens_per_second_per_gpu:2237.490127772304 
Step 4168 | loss:2.1110267639160156 lr:9.622343217952291e-05 tokens_per_second_per_gpu:2199.354532149041 
Step 4169 | loss:2.1292214393615723 lr:9.618411193793914e-05 tokens_per_second_per_gpu:2224.152466835295 
Step 4170 | loss:2.026844024658203 lr:9.614479228717417e-05 tokens_per_second_per_gpu:2219.91166314774 
Step 4171 | loss:2.079054594039917 lr:9.610547323331593e-05 tokens_per_second_per_gpu:2205.8645782770886 
Step 4172 | loss:2.160689353942871 lr:9.606615478245217e-05 tokens_per_second_per_gpu:2155.128958562535 
Step 4173 | loss:2.150075912475586 lr:9.602683694067069e-05 tokens_per_second_per_gpu:2197.594985014705 
Step 4174 | loss:2.0667641162872314 lr:9.598751971405914e-05 tokens_per_second_per_gpu:2204.48652632731 
Step 4175 | loss:2.0520572662353516 lr:9.594820310870501e-05 tokens_per_second_per_gpu:2176.5839670998066 
Step 4176 | loss:2.0949270725250244 lr:9.590888713069573e-05 tokens_per_second_per_gpu:2171.0001362206485 
Step 4177 | loss:2.051262378692627 lr:9.586957178611866e-05 tokens_per_second_per_gpu:2232.600680143139 
Step 4178 | loss:2.0965404510498047 lr:9.583025708106107e-05 tokens_per_second_per_gpu:2201.1638521347036 
Step 4179 | loss:2.160524368286133 lr:9.579094302161005e-05 tokens_per_second_per_gpu:2211.5646523073387 
Step 4180 | loss:2.0842456817626953 lr:9.575162961385271e-05 tokens_per_second_per_gpu:2219.775633308968 
Step 4181 | loss:2.092395782470703 lr:9.571231686387597e-05 tokens_per_second_per_gpu:2172.300699231933 
Step 4182 | loss:2.1056673526763916 lr:9.56730047777666e-05 tokens_per_second_per_gpu:2207.5440632155432 
Step 4183 | loss:2.0652427673339844 lr:9.563369336161145e-05 tokens_per_second_per_gpu:2174.2737965712076 
Step 4184 | loss:2.0338034629821777 lr:9.559438262149714e-05 tokens_per_second_per_gpu:2212.8804088630036 
Step 4185 | loss:2.148159980773926 lr:9.555507256351013e-05 tokens_per_second_per_gpu:2223.409174602824 
Step 4186 | loss:2.135995864868164 lr:9.551576319373692e-05 tokens_per_second_per_gpu:2231.829349024486 
Step 4187 | loss:2.058166742324829 lr:9.547645451826382e-05 tokens_per_second_per_gpu:2223.5288622573403 
Step 4188 | loss:2.1031322479248047 lr:9.543714654317697e-05 tokens_per_second_per_gpu:2230.3904995692405 
Step 4189 | loss:2.10361385345459 lr:9.539783927456253e-05 tokens_per_second_per_gpu:2214.4518601576865 
Step 4190 | loss:2.0287716388702393 lr:9.535853271850655e-05 tokens_per_second_per_gpu:2213.302486973558 
Step 4191 | loss:2.0642035007476807 lr:9.53192268810948e-05 tokens_per_second_per_gpu:2223.366730345902 
Step 4192 | loss:2.080747365951538 lr:9.527992176841315e-05 tokens_per_second_per_gpu:2197.298819764506 
Step 4193 | loss:2.1146152019500732 lr:9.524061738654718e-05 tokens_per_second_per_gpu:2205.632968159244 
Step 4194 | loss:2.109919548034668 lr:9.52013137415825e-05 tokens_per_second_per_gpu:2223.987757044654 
Step 4195 | loss:2.1347455978393555 lr:9.51620108396045e-05 tokens_per_second_per_gpu:2230.4494619556017 
Step 4196 | loss:2.0766143798828125 lr:9.512270868669855e-05 tokens_per_second_per_gpu:2234.875453754702 
Step 4197 | loss:2.1001944541931152 lr:9.50834072889498e-05 tokens_per_second_per_gpu:2213.627055803067 
Step 4198 | loss:2.146308422088623 lr:9.504410665244337e-05 tokens_per_second_per_gpu:2186.7038495326947 
Step 4199 | loss:2.0462799072265625 lr:9.500480678326418e-05 tokens_per_second_per_gpu:2231.5788138887538 
Step 4200 | loss:2.0637032985687256 lr:9.496550768749713e-05 tokens_per_second_per_gpu:2173.090162133053 
Step 4201 | loss:2.05905818939209 lr:9.492620937122693e-05 tokens_per_second_per_gpu:2218.7112397138844 
Step 4202 | loss:2.138537883758545 lr:9.488691184053823e-05 tokens_per_second_per_gpu:2203.2824694743745 
Step 4203 | loss:2.0277116298675537 lr:9.484761510151543e-05 tokens_per_second_per_gpu:2203.680564804764 
Step 4204 | loss:2.0817058086395264 lr:9.480831916024292e-05 tokens_per_second_per_gpu:2237.4311922192187 
Step 4205 | loss:2.075984477996826 lr:9.476902402280501e-05 tokens_per_second_per_gpu:2113.3852728808683 
Step 4206 | loss:2.0885186195373535 lr:9.472972969528574e-05 tokens_per_second_per_gpu:2171.121515608863 
Step 4207 | loss:2.036716938018799 lr:9.469043618376916e-05 tokens_per_second_per_gpu:2215.426352689673 
Step 4208 | loss:2.13515305519104 lr:9.465114349433909e-05 tokens_per_second_per_gpu:2234.9178798175726 
Step 4209 | loss:2.1358888149261475 lr:9.461185163307924e-05 tokens_per_second_per_gpu:2219.2717806334376 
Step 4210 | loss:2.1225500106811523 lr:9.457256060607328e-05 tokens_per_second_per_gpu:2226.2806159581955 
Step 4211 | loss:2.103175163269043 lr:9.45332704194047e-05 tokens_per_second_per_gpu:2169.065458854123 
Step 4212 | loss:2.1278200149536133 lr:9.449398107915679e-05 tokens_per_second_per_gpu:2148.8245471427726 
Step 4213 | loss:2.134772777557373 lr:9.445469259141281e-05 tokens_per_second_per_gpu:2186.970065132588 
Step 4214 | loss:2.1068880558013916 lr:9.441540496225584e-05 tokens_per_second_per_gpu:2230.8098950111344 
Step 4215 | loss:2.1229257583618164 lr:9.437611819776878e-05 tokens_per_second_per_gpu:2160.9110017538524 
Step 4216 | loss:2.1057066917419434 lr:9.433683230403452e-05 tokens_per_second_per_gpu:2205.7461953256093 
Step 4217 | loss:2.107555389404297 lr:9.429754728713574e-05 tokens_per_second_per_gpu:2235.4818543969677 
Step 4218 | loss:2.0701546669006348 lr:9.425826315315495e-05 tokens_per_second_per_gpu:2233.3882077910157 
Step 4219 | loss:2.115971088409424 lr:9.421897990817461e-05 tokens_per_second_per_gpu:2188.725668512076 
Step 4220 | loss:2.089730739593506 lr:9.417969755827691e-05 tokens_per_second_per_gpu:2154.4219102376505 
Step 4221 | loss:2.086789846420288 lr:9.414041610954411e-05 tokens_per_second_per_gpu:2196.7880641770735 
Step 4222 | loss:2.085076332092285 lr:9.41011355680581e-05 tokens_per_second_per_gpu:2195.2098219129357 
Step 4223 | loss:2.0512852668762207 lr:9.40618559399008e-05 tokens_per_second_per_gpu:2226.9907764550408 
Step 4224 | loss:2.098578453063965 lr:9.402257723115387e-05 tokens_per_second_per_gpu:2219.753566282 
Step 4225 | loss:2.101724147796631 lr:9.398329944789892e-05 tokens_per_second_per_gpu:2234.180472712237 
Step 4226 | loss:2.093160629272461 lr:9.39440225962174e-05 tokens_per_second_per_gpu:2140.0222025522244 
Step 4227 | loss:2.120290517807007 lr:9.390474668219054e-05 tokens_per_second_per_gpu:2230.8468241117225 
Step 4228 | loss:2.043700933456421 lr:9.386547171189953e-05 tokens_per_second_per_gpu:2204.1783603128397 
Step 4229 | loss:2.066056251525879 lr:9.382619769142536e-05 tokens_per_second_per_gpu:2231.2210937839664 
Step 4230 | loss:2.1197009086608887 lr:9.378692462684881e-05 tokens_per_second_per_gpu:2209.439335976299 
Step 4231 | loss:2.1058108806610107 lr:9.374765252425061e-05 tokens_per_second_per_gpu:2208.0918291031835 
Step 4232 | loss:2.1536855697631836 lr:9.370838138971139e-05 tokens_per_second_per_gpu:2231.677221204182 
Step 4233 | loss:2.132902145385742 lr:9.366911122931146e-05 tokens_per_second_per_gpu:2226.3012574050035 
Step 4234 | loss:2.0807175636291504 lr:9.36298420491311e-05 tokens_per_second_per_gpu:2220.0770943866687 
Step 4235 | loss:2.1194424629211426 lr:9.35905738552504e-05 tokens_per_second_per_gpu:2145.4938905391623 
Step 4236 | loss:2.0960540771484375 lr:9.355130665374928e-05 tokens_per_second_per_gpu:2204.992792136994 
Step 4237 | loss:2.1452865600585938 lr:9.351204045070757e-05 tokens_per_second_per_gpu:2189.9520430136035 
Step 4238 | loss:2.063599109649658 lr:9.347277525220492e-05 tokens_per_second_per_gpu:2175.17068655161 
Step 4239 | loss:2.1036598682403564 lr:9.343351106432076e-05 tokens_per_second_per_gpu:2172.944244107208 
Step 4240 | loss:2.0960240364074707 lr:9.339424789313445e-05 tokens_per_second_per_gpu:2118.863455719363 
Step 4241 | loss:2.0698113441467285 lr:9.335498574472516e-05 tokens_per_second_per_gpu:2171.211459726426 
Step 4242 | loss:2.0715768337249756 lr:9.331572462517183e-05 tokens_per_second_per_gpu:2234.4289506088235 
Step 4243 | loss:2.116701364517212 lr:9.327646454055338e-05 tokens_per_second_per_gpu:2192.5316912184394 
Step 4244 | loss:2.1129140853881836 lr:9.323720549694852e-05 tokens_per_second_per_gpu:2213.7704391138864 
Step 4245 | loss:2.067768096923828 lr:9.319794750043572e-05 tokens_per_second_per_gpu:2204.9831718386854 
Step 4246 | loss:2.156613826751709 lr:9.315869055709337e-05 tokens_per_second_per_gpu:2208.1050198839107 
Step 4247 | loss:2.057236909866333 lr:9.311943467299962e-05 tokens_per_second_per_gpu:2151.0058901458115 
Step 4248 | loss:2.1011929512023926 lr:9.30801798542326e-05 tokens_per_second_per_gpu:2181.7178063032084 
Step 4249 | loss:2.177696943283081 lr:9.304092610687012e-05 tokens_per_second_per_gpu:2206.590588767121 
Step 4250 | loss:2.0810232162475586 lr:9.300167343698993e-05 tokens_per_second_per_gpu:2223.113126431391 
Step 4251 | loss:2.0851945877075195 lr:9.296242185066953e-05 tokens_per_second_per_gpu:2183.857912805963 
Step 4252 | loss:2.07198429107666 lr:9.292317135398629e-05 tokens_per_second_per_gpu:2216.220722632189 
Step 4253 | loss:2.03201961517334 lr:9.288392195301747e-05 tokens_per_second_per_gpu:2193.825923103002 
Step 4254 | loss:2.132178783416748 lr:9.284467365384005e-05 tokens_per_second_per_gpu:2177.145044263977 
Step 4255 | loss:2.0774245262145996 lr:9.280542646253094e-05 tokens_per_second_per_gpu:2219.6992944746253 
Step 4256 | loss:2.067357063293457 lr:9.27661803851668e-05 tokens_per_second_per_gpu:2227.2532402506695 
Step 4257 | loss:2.105463981628418 lr:9.272693542782414e-05 tokens_per_second_per_gpu:2216.269375616366 
Step 4258 | loss:2.1178998947143555 lr:9.26876915965793e-05 tokens_per_second_per_gpu:2163.4435507052667 
Step 4259 | loss:2.0883841514587402 lr:9.264844889750852e-05 tokens_per_second_per_gpu:2234.4961247976726 
Step 4260 | loss:2.149247169494629 lr:9.260920733668772e-05 tokens_per_second_per_gpu:2187.961036951875 
Step 4261 | loss:2.103975296020508 lr:9.256996692019279e-05 tokens_per_second_per_gpu:2217.713791986642 
Step 4262 | loss:2.0964951515197754 lr:9.253072765409933e-05 tokens_per_second_per_gpu:2220.5075549064645 
Step 4263 | loss:2.0452027320861816 lr:9.249148954448277e-05 tokens_per_second_per_gpu:2212.596833583991 
Step 4264 | loss:2.0935888290405273 lr:9.245225259741845e-05 tokens_per_second_per_gpu:2236.009513977462 
Step 4265 | loss:2.1447391510009766 lr:9.241301681898151e-05 tokens_per_second_per_gpu:2167.076722598848 
Step 4266 | loss:2.110384941101074 lr:9.237378221524679e-05 tokens_per_second_per_gpu:2217.905314318716 
Step 4267 | loss:2.130460739135742 lr:9.23345487922891e-05 tokens_per_second_per_gpu:2211.234326722833 
Step 4268 | loss:2.0802042484283447 lr:9.229531655618293e-05 tokens_per_second_per_gpu:2183.626744906178 
Step 4269 | loss:2.165285110473633 lr:9.225608551300274e-05 tokens_per_second_per_gpu:2224.0772820516117 
Step 4270 | loss:2.0894813537597656 lr:9.221685566882268e-05 tokens_per_second_per_gpu:2235.383719297833 
Step 4271 | loss:2.1577038764953613 lr:9.217762702971677e-05 tokens_per_second_per_gpu:2171.6315202485216 
Step 4272 | loss:2.035322666168213 lr:9.21383996017588e-05 tokens_per_second_per_gpu:2066.7683876949027 
Step 4273 | loss:2.147895574569702 lr:9.209917339102245e-05 tokens_per_second_per_gpu:2213.746505647667 
Step 4274 | loss:2.1196165084838867 lr:9.20599484035811e-05 tokens_per_second_per_gpu:2203.956036180154 
Step 4275 | loss:2.1457362174987793 lr:9.202072464550809e-05 tokens_per_second_per_gpu:2188.8915753850615 
Step 4276 | loss:2.063478469848633 lr:9.19815021228764e-05 tokens_per_second_per_gpu:2118.9174580014023 
Step 4277 | loss:2.103398084640503 lr:9.194228084175897e-05 tokens_per_second_per_gpu:2101.7857390263116 
Step 4278 | loss:2.0867483615875244 lr:9.190306080822841e-05 tokens_per_second_per_gpu:2151.712524431338 
Step 4279 | loss:2.0880234241485596 lr:9.186384202835725e-05 tokens_per_second_per_gpu:2207.1314518600975 
Step 4280 | loss:2.113231897354126 lr:9.182462450821781e-05 tokens_per_second_per_gpu:2209.711286505491 
Step 4281 | loss:2.1474709510803223 lr:9.178540825388216e-05 tokens_per_second_per_gpu:2206.36821539417 
Step 4282 | loss:2.138920783996582 lr:9.174619327142221e-05 tokens_per_second_per_gpu:2206.350455739474 
Step 4283 | loss:2.1027584075927734 lr:9.170697956690966e-05 tokens_per_second_per_gpu:2234.587381450661 
Step 4284 | loss:2.1332621574401855 lr:9.166776714641599e-05 tokens_per_second_per_gpu:2215.8412624787375 
Step 4285 | loss:2.040203094482422 lr:9.162855601601254e-05 tokens_per_second_per_gpu:2195.9953499540447 
Step 4286 | loss:2.0825018882751465 lr:9.158934618177044e-05 tokens_per_second_per_gpu:2164.3876498882146 
Step 4287 | loss:2.1162514686584473 lr:9.155013764976054e-05 tokens_per_second_per_gpu:2235.5762342620005 
Step 4288 | loss:2.0800490379333496 lr:9.151093042605362e-05 tokens_per_second_per_gpu:2167.1020947020947 
Step 4289 | loss:2.0646185874938965 lr:9.147172451672014e-05 tokens_per_second_per_gpu:2220.764823459831 
Step 4290 | loss:2.1339292526245117 lr:9.143251992783036e-05 tokens_per_second_per_gpu:2185.603228007455 
Step 4291 | loss:2.046219825744629 lr:9.139331666545445e-05 tokens_per_second_per_gpu:2162.2820086414467 
Step 4292 | loss:2.0483131408691406 lr:9.135411473566229e-05 tokens_per_second_per_gpu:2199.230554917261 
Step 4293 | loss:2.1161794662475586 lr:9.131491414452352e-05 tokens_per_second_per_gpu:2106.865937721331 
Step 4294 | loss:2.0759758949279785 lr:9.127571489810768e-05 tokens_per_second_per_gpu:2228.993164675257 
Step 4295 | loss:2.043412446975708 lr:9.123651700248396e-05 tokens_per_second_per_gpu:2145.4788544979087 
Step 4296 | loss:2.141596794128418 lr:9.119732046372149e-05 tokens_per_second_per_gpu:2214.078135433939 
Step 4297 | loss:2.04654598236084 lr:9.115812528788908e-05 tokens_per_second_per_gpu:2168.89251574902 
Step 4298 | loss:2.0361645221710205 lr:9.111893148105542e-05 tokens_per_second_per_gpu:2198.2856705030435 
Step 4299 | loss:2.136618137359619 lr:9.107973904928888e-05 tokens_per_second_per_gpu:2227.2935410394994 
Step 4300 | loss:2.16532564163208 lr:9.104054799865769e-05 tokens_per_second_per_gpu:2231.4142394358714 
Step 4301 | loss:2.1110920906066895 lr:9.100135833522982e-05 tokens_per_second_per_gpu:2116.873933744165 
Step 4302 | loss:2.169848680496216 lr:9.096217006507315e-05 tokens_per_second_per_gpu:2186.3107201091393 
Step 4303 | loss:2.0505013465881348 lr:9.092298319425514e-05 tokens_per_second_per_gpu:2224.4932472503046 
Step 4304 | loss:2.0805530548095703 lr:9.088379772884325e-05 tokens_per_second_per_gpu:2165.1686932219764 
Step 4305 | loss:2.0528149604797363 lr:9.084461367490451e-05 tokens_per_second_per_gpu:2205.354635495575 
Step 4306 | loss:2.115199089050293 lr:9.080543103850587e-05 tokens_per_second_per_gpu:2227.1737634303036 
Step 4307 | loss:2.156460762023926 lr:9.076624982571409e-05 tokens_per_second_per_gpu:2162.189371418823 
Step 4308 | loss:2.117213249206543 lr:9.072707004259557e-05 tokens_per_second_per_gpu:2220.0182780580485 
Step 4309 | loss:2.1118054389953613 lr:9.068789169521663e-05 tokens_per_second_per_gpu:2216.8689875875307 
Step 4310 | loss:2.1089391708374023 lr:9.064871478964326e-05 tokens_per_second_per_gpu:2127.119435111124 
Step 4311 | loss:2.113734483718872 lr:9.060953933194123e-05 tokens_per_second_per_gpu:2136.4693849777323 
Step 4312 | loss:2.049400806427002 lr:9.057036532817622e-05 tokens_per_second_per_gpu:2197.432607181676 
Step 4313 | loss:2.09390926361084 lr:9.053119278441356e-05 tokens_per_second_per_gpu:2185.768996180986 
Step 4314 | loss:1.9972964525222778 lr:9.049202170671833e-05 tokens_per_second_per_gpu:2108.9893914613053 
Step 4315 | loss:2.0713651180267334 lr:9.045285210115551e-05 tokens_per_second_per_gpu:2228.3892846864055 
Step 4316 | loss:2.104152202606201 lr:9.041368397378976e-05 tokens_per_second_per_gpu:2196.6338588430294 
Step 4317 | loss:2.105975866317749 lr:9.037451733068546e-05 tokens_per_second_per_gpu:2212.1564897119038 
Step 4318 | loss:2.060253143310547 lr:9.033535217790692e-05 tokens_per_second_per_gpu:2209.70928106602 
Step 4319 | loss:2.037076473236084 lr:9.029618852151812e-05 tokens_per_second_per_gpu:2223.5119576198795 
Step 4320 | loss:2.0998692512512207 lr:9.025702636758277e-05 tokens_per_second_per_gpu:2194.379423235592 
Step 4321 | loss:2.0874271392822266 lr:9.021786572216447e-05 tokens_per_second_per_gpu:2223.3558686622764 
Step 4322 | loss:2.1177380084991455 lr:9.01787065913264e-05 tokens_per_second_per_gpu:2153.1944398613905 
Step 4323 | loss:2.0844905376434326 lr:9.013954898113175e-05 tokens_per_second_per_gpu:2217.829678926311 
Step 4324 | loss:2.046536445617676 lr:9.010039289764325e-05 tokens_per_second_per_gpu:2220.3601678373584 
Step 4325 | loss:2.0501089096069336 lr:9.006123834692353e-05 tokens_per_second_per_gpu:2154.4307777865433 
Step 4326 | loss:2.081265687942505 lr:9.002208533503491e-05 tokens_per_second_per_gpu:2213.894668133982 
Step 4327 | loss:2.0669105052948 lr:8.998293386803949e-05 tokens_per_second_per_gpu:2227.9310813589127 
Step 4328 | loss:2.0591368675231934 lr:8.99437839519992e-05 tokens_per_second_per_gpu:2228.2157447709947 
Step 4329 | loss:2.115662097930908 lr:8.990463559297566e-05 tokens_per_second_per_gpu:2161.5230956587206 
Step 4330 | loss:2.0326809883117676 lr:8.98654887970302e-05 tokens_per_second_per_gpu:2182.1872566154984 
Step 4331 | loss:2.1140971183776855 lr:8.982634357022403e-05 tokens_per_second_per_gpu:2201.5306686908993 
Step 4332 | loss:2.1041336059570312 lr:8.978719991861801e-05 tokens_per_second_per_gpu:2201.1603470435084 
Step 4333 | loss:2.0459887981414795 lr:8.974805784827281e-05 tokens_per_second_per_gpu:2211.851699776836 
Step 4334 | loss:2.097990036010742 lr:8.97089173652489e-05 tokens_per_second_per_gpu:2168.4213745576526 
Step 4335 | loss:2.048923969268799 lr:8.96697784756064e-05 tokens_per_second_per_gpu:2173.2704448241648 
Step 4336 | loss:2.0980260372161865 lr:8.963064118540523e-05 tokens_per_second_per_gpu:2187.3812067699823 
Step 4337 | loss:2.0473854541778564 lr:8.959150550070511e-05 tokens_per_second_per_gpu:2216.5450144077477 
Step 4338 | loss:2.0768749713897705 lr:8.955237142756538e-05 tokens_per_second_per_gpu:2226.2698350432374 
Step 4339 | loss:2.0917317867279053 lr:8.951323897204531e-05 tokens_per_second_per_gpu:2225.005847613607 
Step 4340 | loss:2.114755153656006 lr:8.94741081402038e-05 tokens_per_second_per_gpu:2165.7702735570765 
Step 4341 | loss:2.1196675300598145 lr:8.943497893809953e-05 tokens_per_second_per_gpu:2213.8914079624233 
Step 4342 | loss:2.083698034286499 lr:8.939585137179092e-05 tokens_per_second_per_gpu:2195.0718453086934 
Step 4343 | loss:2.087719440460205 lr:8.935672544733609e-05 tokens_per_second_per_gpu:2197.6453914652184 
Step 4344 | loss:2.100863218307495 lr:8.931760117079304e-05 tokens_per_second_per_gpu:2229.7300827212607 
Step 4345 | loss:2.095154047012329 lr:8.927847854821938e-05 tokens_per_second_per_gpu:2222.64455680066 
Step 4346 | loss:2.191615104675293 lr:8.923935758567256e-05 tokens_per_second_per_gpu:2167.6257441252983 
Step 4347 | loss:2.076284408569336 lr:8.920023828920965e-05 tokens_per_second_per_gpu:2203.7006588977133 
Step 4348 | loss:2.0820560455322266 lr:8.916112066488764e-05 tokens_per_second_per_gpu:2179.9601607222658 
Step 4349 | loss:2.0638015270233154 lr:8.912200471876306e-05 tokens_per_second_per_gpu:2183.9121599579084 
Step 4350 | loss:2.070009231567383 lr:8.908289045689237e-05 tokens_per_second_per_gpu:2136.891971588278 
Step 4351 | loss:2.1474661827087402 lr:8.904377788533162e-05 tokens_per_second_per_gpu:2154.5632891354667 
Step 4352 | loss:2.1559219360351562 lr:8.900466701013672e-05 tokens_per_second_per_gpu:2222.096361063977 
Step 4353 | loss:2.105553150177002 lr:8.896555783736317e-05 tokens_per_second_per_gpu:2219.3785533185783 
Step 4354 | loss:2.0854063034057617 lr:8.892645037306634e-05 tokens_per_second_per_gpu:2202.372089093239 
Step 4355 | loss:2.1622202396392822 lr:8.888734462330132e-05 tokens_per_second_per_gpu:2223.8368651382293 
Step 4356 | loss:2.0698132514953613 lr:8.884824059412289e-05 tokens_per_second_per_gpu:2214.5543282650992 
Step 4357 | loss:2.02640700340271 lr:8.880913829158554e-05 tokens_per_second_per_gpu:2152.724971908596 
Step 4358 | loss:2.123211145401001 lr:8.877003772174355e-05 tokens_per_second_per_gpu:2208.4830421784495 
Step 4359 | loss:2.166130304336548 lr:8.873093889065091e-05 tokens_per_second_per_gpu:2160.2078716492824 
Step 4360 | loss:2.1356163024902344 lr:8.869184180436129e-05 tokens_per_second_per_gpu:2197.288251691042 
Step 4361 | loss:2.088808059692383 lr:8.865274646892827e-05 tokens_per_second_per_gpu:2173.6282952005417 
Step 4362 | loss:2.139141082763672 lr:8.861365289040495e-05 tokens_per_second_per_gpu:2183.46784819246 
Step 4363 | loss:2.1657750606536865 lr:8.85745610748442e-05 tokens_per_second_per_gpu:2178.2659234574726 
Step 4364 | loss:2.061459541320801 lr:8.853547102829873e-05 tokens_per_second_per_gpu:2205.7811365146126 
Step 4365 | loss:2.0494580268859863 lr:8.849638275682083e-05 tokens_per_second_per_gpu:2197.8086959235934 
Step 4366 | loss:2.1295671463012695 lr:8.845729626646264e-05 tokens_per_second_per_gpu:2161.959893058216 
Step 4367 | loss:2.113816738128662 lr:8.841821156327599e-05 tokens_per_second_per_gpu:2215.933781066791 
Step 4368 | loss:2.079962968826294 lr:8.837912865331236e-05 tokens_per_second_per_gpu:2229.4448452389056 
Step 4369 | loss:2.0642781257629395 lr:8.834004754262303e-05 tokens_per_second_per_gpu:2193.85576163204 
Step 4370 | loss:2.1262059211730957 lr:8.830096823725897e-05 tokens_per_second_per_gpu:2227.722588497937 
Step 4371 | loss:2.0895516872406006 lr:8.82618907432709e-05 tokens_per_second_per_gpu:2215.964236571114 
Step 4372 | loss:2.1079726219177246 lr:8.82228150667092e-05 tokens_per_second_per_gpu:2181.1724039528767 
Step 4373 | loss:2.1004700660705566 lr:8.818374121362407e-05 tokens_per_second_per_gpu:2213.9489387851654 
Step 4374 | loss:2.146108865737915 lr:8.81446691900653e-05 tokens_per_second_per_gpu:2212.995208843822 
Step 4375 | loss:2.0742764472961426 lr:8.81055990020825e-05 tokens_per_second_per_gpu:2161.086866060495 
Step 4376 | loss:2.135634422302246 lr:8.80665306557249e-05 tokens_per_second_per_gpu:2128.459003524069 
Step 4377 | loss:2.0858330726623535 lr:8.802746415704158e-05 tokens_per_second_per_gpu:2214.5708845503027 
Step 4378 | loss:2.0594542026519775 lr:8.798839951208123e-05 tokens_per_second_per_gpu:2225.197155296395 
Step 4379 | loss:2.0908870697021484 lr:8.794933672689225e-05 tokens_per_second_per_gpu:2206.634372798151 
Step 4380 | loss:2.096414804458618 lr:8.79102758075228e-05 tokens_per_second_per_gpu:2218.6080604023437 
Step 4381 | loss:2.064413547515869 lr:8.78712167600207e-05 tokens_per_second_per_gpu:2156.0051903974577 
Step 4382 | loss:2.1457126140594482 lr:8.78321595904336e-05 tokens_per_second_per_gpu:2209.9207481622034 
Step 4383 | loss:2.0700392723083496 lr:8.77931043048087e-05 tokens_per_second_per_gpu:2223.109400114073 
Step 4384 | loss:2.074260711669922 lr:8.775405090919299e-05 tokens_per_second_per_gpu:2216.43507281343 
Step 4385 | loss:2.127371311187744 lr:8.771499940963317e-05 tokens_per_second_per_gpu:2213.658709385312 
Step 4386 | loss:2.1172995567321777 lr:8.767594981217558e-05 tokens_per_second_per_gpu:2203.8959906762198 
Step 4387 | loss:2.0622925758361816 lr:8.76369021228664e-05 tokens_per_second_per_gpu:2150.6351978263046 
Step 4388 | loss:2.1230111122131348 lr:8.75978563477514e-05 tokens_per_second_per_gpu:2200.4684597164473 
Step 4389 | loss:2.137185573577881 lr:8.755881249287608e-05 tokens_per_second_per_gpu:2212.1113009631863 
Step 4390 | loss:2.114121913909912 lr:8.751977056428565e-05 tokens_per_second_per_gpu:2196.361045172619 
Step 4391 | loss:2.087141275405884 lr:8.748073056802504e-05 tokens_per_second_per_gpu:2201.6902057578036 
Step 4392 | loss:2.1000118255615234 lr:8.744169251013881e-05 tokens_per_second_per_gpu:2137.6069119392255 
Step 4393 | loss:2.1480932235717773 lr:8.740265639667133e-05 tokens_per_second_per_gpu:2175.123105522492 
Step 4394 | loss:2.1055123805999756 lr:8.73636222336666e-05 tokens_per_second_per_gpu:2151.582711218042 
Step 4395 | loss:2.092489242553711 lr:8.732459002716831e-05 tokens_per_second_per_gpu:2131.811432602314 
Step 4396 | loss:2.1225080490112305 lr:8.728555978321989e-05 tokens_per_second_per_gpu:2221.736168375298 
Step 4397 | loss:2.095141887664795 lr:8.72465315078644e-05 tokens_per_second_per_gpu:2225.030436989911 
Step 4398 | loss:2.0950636863708496 lr:8.72075052071447e-05 tokens_per_second_per_gpu:2206.274410774116 
Step 4399 | loss:2.0918681621551514 lr:8.716848088710321e-05 tokens_per_second_per_gpu:2207.6488444709084 
Step 4400 | loss:2.1002635955810547 lr:8.712945855378218e-05 tokens_per_second_per_gpu:2148.5065891457507 
Step 4401 | loss:2.076671838760376 lr:8.709043821322346e-05 tokens_per_second_per_gpu:2216.250528909922 
Step 4402 | loss:2.0768346786499023 lr:8.705141987146858e-05 tokens_per_second_per_gpu:2226.3511482764006 
Step 4403 | loss:2.116102695465088 lr:8.701240353455889e-05 tokens_per_second_per_gpu:2158.206516019114 
Step 4404 | loss:2.021430492401123 lr:8.697338920853528e-05 tokens_per_second_per_gpu:2224.745745711725 
Step 4405 | loss:2.0481929779052734 lr:8.693437689943838e-05 tokens_per_second_per_gpu:2204.3151917656037 
Step 4406 | loss:2.07666015625 lr:8.689536661330856e-05 tokens_per_second_per_gpu:2222.2079582029314 
Step 4407 | loss:2.122893810272217 lr:8.685635835618577e-05 tokens_per_second_per_gpu:2220.499941219346 
Step 4408 | loss:2.0683071613311768 lr:8.681735213410973e-05 tokens_per_second_per_gpu:2159.0970565336434 
Step 4409 | loss:2.090181827545166 lr:8.677834795311988e-05 tokens_per_second_per_gpu:2116.723830457579 
Step 4410 | loss:2.0586674213409424 lr:8.673934581925523e-05 tokens_per_second_per_gpu:2188.091596614601 
Step 4411 | loss:2.1249496936798096 lr:8.670034573855452e-05 tokens_per_second_per_gpu:2197.232032115992 
Step 4412 | loss:2.1110830307006836 lr:8.666134771705623e-05 tokens_per_second_per_gpu:2190.958246751883 
Step 4413 | loss:2.116058111190796 lr:8.66223517607984e-05 tokens_per_second_per_gpu:2211.063041876482 
Step 4414 | loss:2.1037614345550537 lr:8.65833578758189e-05 tokens_per_second_per_gpu:2226.323430281594 
Step 4415 | loss:2.104954242706299 lr:8.654436606815519e-05 tokens_per_second_per_gpu:2187.5325499039827 
Step 4416 | loss:2.0486581325531006 lr:8.65053763438444e-05 tokens_per_second_per_gpu:2220.535049775988 
Step 4417 | loss:2.056364059448242 lr:8.646638870892333e-05 tokens_per_second_per_gpu:2223.889124453336 
Step 4418 | loss:2.0812506675720215 lr:8.642740316942857e-05 tokens_per_second_per_gpu:2217.2177743662737 
Step 4419 | loss:2.0446062088012695 lr:8.638841973139619e-05 tokens_per_second_per_gpu:2214.238069354471 
Step 4420 | loss:2.1251492500305176 lr:8.634943840086213e-05 tokens_per_second_per_gpu:2195.261736413193 
Step 4421 | loss:2.0816869735717773 lr:8.631045918386192e-05 tokens_per_second_per_gpu:2159.3644352448473 
Step 4422 | loss:2.1132636070251465 lr:8.62714820864307e-05 tokens_per_second_per_gpu:2222.2508285001873 
Step 4423 | loss:2.12825083732605 lr:8.62325071146034e-05 tokens_per_second_per_gpu:2217.0277714250224 
Step 4424 | loss:2.0538339614868164 lr:8.619353427441451e-05 tokens_per_second_per_gpu:2210.4251247590532 
Step 4425 | loss:2.105992317199707 lr:8.615456357189831e-05 tokens_per_second_per_gpu:2179.9789316168512 
Step 4426 | loss:2.1291961669921875 lr:8.611559501308864e-05 tokens_per_second_per_gpu:2184.391794375086 
Step 4427 | loss:2.117875576019287 lr:8.607662860401908e-05 tokens_per_second_per_gpu:2220.5499759974555 
Step 4428 | loss:2.0812132358551025 lr:8.603766435072281e-05 tokens_per_second_per_gpu:2218.8382043283345 
Step 4429 | loss:2.0827677249908447 lr:8.599870225923273e-05 tokens_per_second_per_gpu:2209.1435021445764 
Step 4430 | loss:2.169342517852783 lr:8.595974233558141e-05 tokens_per_second_per_gpu:2220.7490462303085 
Step 4431 | loss:2.1187782287597656 lr:8.592078458580108e-05 tokens_per_second_per_gpu:2222.9486900499383 
Step 4432 | loss:2.089956521987915 lr:8.588182901592355e-05 tokens_per_second_per_gpu:2177.980298120703 
Step 4433 | loss:2.096388339996338 lr:8.584287563198043e-05 tokens_per_second_per_gpu:2183.587426092567 
Step 4434 | loss:2.0689268112182617 lr:8.580392444000285e-05 tokens_per_second_per_gpu:2194.3091226379 
Step 4435 | loss:2.083860397338867 lr:8.576497544602171e-05 tokens_per_second_per_gpu:2184.592308314454 
Step 4436 | loss:2.0758614540100098 lr:8.572602865606758e-05 tokens_per_second_per_gpu:2231.522983715725 
Step 4437 | loss:2.0597047805786133 lr:8.568708407617058e-05 tokens_per_second_per_gpu:2211.1954556754463 
Step 4438 | loss:2.121009111404419 lr:8.564814171236057e-05 tokens_per_second_per_gpu:2177.3522645111098 
Step 4439 | loss:2.0500025749206543 lr:8.560920157066706e-05 tokens_per_second_per_gpu:2228.298566665235 
Step 4440 | loss:2.043961524963379 lr:8.557026365711912e-05 tokens_per_second_per_gpu:2185.504194369954 
Step 4441 | loss:2.0893425941467285 lr:8.553132797774566e-05 tokens_per_second_per_gpu:2204.9054741151203 
Step 4442 | loss:2.0584311485290527 lr:8.549239453857511e-05 tokens_per_second_per_gpu:2204.4237066935916 
Step 4443 | loss:2.074522018432617 lr:8.545346334563559e-05 tokens_per_second_per_gpu:2218.59382919946 
Step 4444 | loss:2.1014130115509033 lr:8.541453440495481e-05 tokens_per_second_per_gpu:2200.7307586929464 
Step 4445 | loss:2.0995407104492188 lr:8.537560772256022e-05 tokens_per_second_per_gpu:2183.757651728655 
Step 4446 | loss:2.0337862968444824 lr:8.533668330447894e-05 tokens_per_second_per_gpu:2204.3063423836124 
Step 4447 | loss:2.0338101387023926 lr:8.529776115673762e-05 tokens_per_second_per_gpu:2123.786676271771 
Step 4448 | loss:2.0541892051696777 lr:8.525884128536268e-05 tokens_per_second_per_gpu:2216.607955624468 
Step 4449 | loss:2.0758743286132812 lr:8.521992369638007e-05 tokens_per_second_per_gpu:2223.3157174969865 
Step 4450 | loss:2.1158149242401123 lr:8.51810083958155e-05 tokens_per_second_per_gpu:2174.994450742912 
Step 4451 | loss:2.103292942047119 lr:8.514209538969422e-05 tokens_per_second_per_gpu:2217.140533491975 
Step 4452 | loss:2.1491312980651855 lr:8.510318468404127e-05 tokens_per_second_per_gpu:2220.030991342148 
Step 4453 | loss:2.0949063301086426 lr:8.506427628488116e-05 tokens_per_second_per_gpu:2219.7994659759484 
Step 4454 | loss:2.120506763458252 lr:8.502537019823819e-05 tokens_per_second_per_gpu:2219.8756756210546 
Step 4455 | loss:2.0970568656921387 lr:8.498646643013618e-05 tokens_per_second_per_gpu:2224.9267426607535 
Step 4456 | loss:2.1037583351135254 lr:8.494756498659866e-05 tokens_per_second_per_gpu:2218.8744583261564 
Step 4457 | loss:2.085435152053833 lr:8.490866587364884e-05 tokens_per_second_per_gpu:2171.525016543017 
Step 4458 | loss:2.074171543121338 lr:8.48697690973095e-05 tokens_per_second_per_gpu:2167.935587579172 
Step 4459 | loss:2.0046439170837402 lr:8.483087466360303e-05 tokens_per_second_per_gpu:2226.379075018684 
Step 4460 | loss:2.0944347381591797 lr:8.479198257855157e-05 tokens_per_second_per_gpu:2217.8960304361485 
Step 4461 | loss:2.0496280193328857 lr:8.475309284817679e-05 tokens_per_second_per_gpu:2225.0792605342463 
Step 4462 | loss:2.030268669128418 lr:8.47142054785e-05 tokens_per_second_per_gpu:2155.6456860251383 
Step 4463 | loss:2.0976080894470215 lr:8.467532047554229e-05 tokens_per_second_per_gpu:2142.934073457396 
Step 4464 | loss:2.066950798034668 lr:8.46364378453242e-05 tokens_per_second_per_gpu:2197.1304790658587 
Step 4465 | loss:2.1268839836120605 lr:8.459755759386597e-05 tokens_per_second_per_gpu:2225.8183318665647 
Step 4466 | loss:2.0432333946228027 lr:8.455867972718753e-05 tokens_per_second_per_gpu:2206.82623101017 
Step 4467 | loss:2.0582542419433594 lr:8.45198042513083e-05 tokens_per_second_per_gpu:2196.652506010333 
Step 4468 | loss:2.1236538887023926 lr:8.448093117224751e-05 tokens_per_second_per_gpu:2216.439102250868 
Step 4469 | loss:2.1344680786132812 lr:8.444206049602391e-05 tokens_per_second_per_gpu:2221.419196086755 
Step 4470 | loss:2.0796360969543457 lr:8.44031922286559e-05 tokens_per_second_per_gpu:2165.688414039388 
Step 4471 | loss:2.072120189666748 lr:8.436432637616143e-05 tokens_per_second_per_gpu:2210.173103184613 
Step 4472 | loss:2.0353403091430664 lr:8.43254629445582e-05 tokens_per_second_per_gpu:2178.8844645186878 
Step 4473 | loss:2.1039061546325684 lr:8.428660193986353e-05 tokens_per_second_per_gpu:2221.6279497132186 
Step 4474 | loss:2.121968984603882 lr:8.424774336809426e-05 tokens_per_second_per_gpu:2060.923552647917 
Step 4475 | loss:2.061737060546875 lr:8.420888723526695e-05 tokens_per_second_per_gpu:2229.8706677636046 
Step 4476 | loss:2.1091854572296143 lr:8.417003354739769e-05 tokens_per_second_per_gpu:2167.051459347839 
Step 4477 | loss:2.0853192806243896 lr:8.413118231050232e-05 tokens_per_second_per_gpu:2151.488184831854 
Step 4478 | loss:2.1010875701904297 lr:8.409233353059615e-05 tokens_per_second_per_gpu:2212.195105453014 
Step 4479 | loss:2.105985641479492 lr:8.405348721369425e-05 tokens_per_second_per_gpu:2168.951954124386 
Step 4480 | loss:2.048905849456787 lr:8.40146433658112e-05 tokens_per_second_per_gpu:2221.352654813816 
Step 4481 | loss:2.0648443698883057 lr:8.397580199296127e-05 tokens_per_second_per_gpu:2192.5325334363574 
Step 4482 | loss:2.114102840423584 lr:8.39369631011583e-05 tokens_per_second_per_gpu:2221.6387526757176 
Step 4483 | loss:2.1033387184143066 lr:8.389812669641574e-05 tokens_per_second_per_gpu:2209.5007605476435 
Step 4484 | loss:2.0887503623962402 lr:8.385929278474678e-05 tokens_per_second_per_gpu:2226.2669675909833 
Step 4485 | loss:2.0398850440979004 lr:8.382046137216403e-05 tokens_per_second_per_gpu:2196.1080492633846 
Step 4486 | loss:2.0621607303619385 lr:8.378163246467983e-05 tokens_per_second_per_gpu:2150.8452274762185 
Step 4487 | loss:2.0943591594696045 lr:8.374280606830614e-05 tokens_per_second_per_gpu:2224.0288323064215 
Step 4488 | loss:2.044071674346924 lr:8.370398218905442e-05 tokens_per_second_per_gpu:2153.7751968409284 
Step 4489 | loss:2.0472328662872314 lr:8.366516083293591e-05 tokens_per_second_per_gpu:2201.350973186669 
Step 4490 | loss:2.1208484172821045 lr:8.362634200596134e-05 tokens_per_second_per_gpu:2194.7608400459703 
Step 4491 | loss:2.1053590774536133 lr:8.358752571414108e-05 tokens_per_second_per_gpu:2209.6792230706974 
Step 4492 | loss:2.126467704772949 lr:8.354871196348508e-05 tokens_per_second_per_gpu:2185.4876697531126 
Step 4493 | loss:2.036707878112793 lr:8.350990076000297e-05 tokens_per_second_per_gpu:2219.187340737269 
Step 4494 | loss:2.1372194290161133 lr:8.347109210970386e-05 tokens_per_second_per_gpu:2231.013146890731 
Step 4495 | loss:2.123232841491699 lr:8.343228601859661e-05 tokens_per_second_per_gpu:2138.9428138807993 
Step 4496 | loss:2.1006734371185303 lr:8.339348249268962e-05 tokens_per_second_per_gpu:2118.1398565486506 
Step 4497 | loss:2.111995220184326 lr:8.335468153799088e-05 tokens_per_second_per_gpu:2139.691703344614 
Step 4498 | loss:2.071453094482422 lr:8.331588316050794e-05 tokens_per_second_per_gpu:2221.986642301753 
Step 4499 | loss:2.0622236728668213 lr:8.327708736624803e-05 tokens_per_second_per_gpu:2202.1131287660055 
Step 4500 | loss:2.0701143741607666 lr:8.3238294161218e-05 tokens_per_second_per_gpu:2182.7596828081537 
Step 4501 | loss:2.0535101890563965 lr:8.31995035514242e-05 tokens_per_second_per_gpu:2174.884146716227 
Step 4502 | loss:2.145773410797119 lr:8.316071554287267e-05 tokens_per_second_per_gpu:2198.5034829380565 
Step 4503 | loss:2.071641445159912 lr:8.312193014156894e-05 tokens_per_second_per_gpu:2174.4743029744914 
Step 4504 | loss:2.0352396965026855 lr:8.308314735351825e-05 tokens_per_second_per_gpu:2225.0274060778643 
Step 4505 | loss:2.058554172515869 lr:8.304436718472541e-05 tokens_per_second_per_gpu:2202.130094209031 
Step 4506 | loss:2.0733730792999268 lr:8.300558964119478e-05 tokens_per_second_per_gpu:2229.8872547130545 
Step 4507 | loss:2.0800909996032715 lr:8.296681472893031e-05 tokens_per_second_per_gpu:2190.6517854155027 
Step 4508 | loss:2.129061222076416 lr:8.292804245393562e-05 tokens_per_second_per_gpu:2215.45820641724 
Step 4509 | loss:2.11173415184021 lr:8.288927282221381e-05 tokens_per_second_per_gpu:2223.202110677224 
Step 4510 | loss:2.0772318840026855 lr:8.285050583976764e-05 tokens_per_second_per_gpu:2221.4770016709454 
Step 4511 | loss:2.1121010780334473 lr:8.281174151259952e-05 tokens_per_second_per_gpu:2199.6252400946005 
Step 4512 | loss:2.1294164657592773 lr:8.277297984671132e-05 tokens_per_second_per_gpu:2223.7308909843746 
Step 4513 | loss:2.1084678173065186 lr:8.273422084810459e-05 tokens_per_second_per_gpu:2222.1465538499037 
Step 4514 | loss:2.066957950592041 lr:8.269546452278041e-05 tokens_per_second_per_gpu:2178.690442948877 
Step 4515 | loss:2.112807512283325 lr:8.265671087673943e-05 tokens_per_second_per_gpu:2201.7850959856432 
Step 4516 | loss:2.109750747680664 lr:8.261795991598201e-05 tokens_per_second_per_gpu:2228.827057321765 
Step 4517 | loss:2.070274829864502 lr:8.257921164650799e-05 tokens_per_second_per_gpu:2137.7688202519744 
Step 4518 | loss:2.2106008529663086 lr:8.254046607431681e-05 tokens_per_second_per_gpu:2222.8798537587895 
Step 4519 | loss:2.0450358390808105 lr:8.250172320540745e-05 tokens_per_second_per_gpu:2199.3677239733474 
Step 4520 | loss:2.111663818359375 lr:8.24629830457786e-05 tokens_per_second_per_gpu:2210.688528315231 
Step 4521 | loss:2.1189799308776855 lr:8.242424560142834e-05 tokens_per_second_per_gpu:2152.109737807547 
Step 4522 | loss:2.051140785217285 lr:8.23855108783545e-05 tokens_per_second_per_gpu:2219.8387123769558 
Step 4523 | loss:2.0561275482177734 lr:8.234677888255448e-05 tokens_per_second_per_gpu:2210.223509010109 
Step 4524 | loss:2.0827243328094482 lr:8.230804962002514e-05 tokens_per_second_per_gpu:2218.49587982037 
Step 4525 | loss:2.050259590148926 lr:8.226932309676298e-05 tokens_per_second_per_gpu:2183.2074344229527 
Step 4526 | loss:2.0265979766845703 lr:8.223059931876404e-05 tokens_per_second_per_gpu:2225.3051479431547 
Step 4527 | loss:2.0245046615600586 lr:8.21918782920241e-05 tokens_per_second_per_gpu:2209.7079993933553 
Step 4528 | loss:2.0859172344207764 lr:8.215316002253825e-05 tokens_per_second_per_gpu:2144.223230141543 
Step 4529 | loss:2.078789710998535 lr:8.211444451630138e-05 tokens_per_second_per_gpu:2207.557964034712 
Step 4530 | loss:2.0933175086975098 lr:8.207573177930781e-05 tokens_per_second_per_gpu:2168.979429558816 
Step 4531 | loss:2.1425371170043945 lr:8.203702181755148e-05 tokens_per_second_per_gpu:2225.2932026578487 
Step 4532 | loss:2.108582019805908 lr:8.199831463702594e-05 tokens_per_second_per_gpu:2209.008083437948 
Step 4533 | loss:2.0365729331970215 lr:8.195961024372427e-05 tokens_per_second_per_gpu:2207.342852176781 
Step 4534 | loss:2.098318576812744 lr:8.192090864363908e-05 tokens_per_second_per_gpu:2219.598032809291 
Step 4535 | loss:2.049945592880249 lr:8.188220984276262e-05 tokens_per_second_per_gpu:2181.4522984248674 
Step 4536 | loss:2.05808162689209 lr:8.184351384708666e-05 tokens_per_second_per_gpu:2184.660094772325 
Step 4537 | loss:2.1400773525238037 lr:8.180482066260252e-05 tokens_per_second_per_gpu:2222.653027121495 
Step 4538 | loss:2.1070494651794434 lr:8.17661302953012e-05 tokens_per_second_per_gpu:2215.6927916578097 
Step 4539 | loss:2.0903382301330566 lr:8.172744275117314e-05 tokens_per_second_per_gpu:2226.9232290575255 
Step 4540 | loss:2.0745253562927246 lr:8.168875803620834e-05 tokens_per_second_per_gpu:2207.057614048695 
Step 4541 | loss:2.0845158100128174 lr:8.165007615639646e-05 tokens_per_second_per_gpu:2207.0972956684145 
Step 4542 | loss:2.1575026512145996 lr:8.161139711772659e-05 tokens_per_second_per_gpu:2158.293928926291 
Step 4543 | loss:2.0497236251831055 lr:8.157272092618755e-05 tokens_per_second_per_gpu:2202.42280275891 
Step 4544 | loss:2.127793312072754 lr:8.153404758776757e-05 tokens_per_second_per_gpu:2160.399691936528 
Step 4545 | loss:2.108419895172119 lr:8.149537710845452e-05 tokens_per_second_per_gpu:2220.103537599371 
Step 4546 | loss:2.1268787384033203 lr:8.145670949423574e-05 tokens_per_second_per_gpu:2219.8793847985703 
Step 4547 | loss:2.138498306274414 lr:8.141804475109823e-05 tokens_per_second_per_gpu:2214.722057940319 
Step 4548 | loss:2.0938820838928223 lr:8.137938288502851e-05 tokens_per_second_per_gpu:2192.971264848061 
Step 4549 | loss:2.124931812286377 lr:8.134072390201264e-05 tokens_per_second_per_gpu:2135.416117629934 
Step 4550 | loss:2.0520219802856445 lr:8.130206780803625e-05 tokens_per_second_per_gpu:2212.423536161427 
Step 4551 | loss:2.063649892807007 lr:8.126341460908448e-05 tokens_per_second_per_gpu:2165.821622003012 
Step 4552 | loss:2.105593681335449 lr:8.122476431114205e-05 tokens_per_second_per_gpu:2188.832334179698 
Step 4553 | loss:2.0402991771698 lr:8.118611692019325e-05 tokens_per_second_per_gpu:2175.983101554425 
Step 4554 | loss:2.0396382808685303 lr:8.114747244222193e-05 tokens_per_second_per_gpu:2221.9973741678905 
Step 4555 | loss:2.105050563812256 lr:8.110883088321143e-05 tokens_per_second_per_gpu:2213.084293318188 
Step 4556 | loss:2.0710415840148926 lr:8.10701922491447e-05 tokens_per_second_per_gpu:2170.322286256455 
Step 4557 | loss:2.0935800075531006 lr:8.103155654600418e-05 tokens_per_second_per_gpu:2217.744185046068 
Step 4558 | loss:2.0790367126464844 lr:8.09929237797719e-05 tokens_per_second_per_gpu:2187.0289451214176 
Step 4559 | loss:2.062673568725586 lr:8.095429395642941e-05 tokens_per_second_per_gpu:2180.322972079909 
Step 4560 | loss:2.107466220855713 lr:8.091566708195786e-05 tokens_per_second_per_gpu:2229.660983811425 
Step 4561 | loss:2.0683932304382324 lr:8.087704316233782e-05 tokens_per_second_per_gpu:2213.1795389092986 
Step 4562 | loss:2.0317940711975098 lr:8.083842220354956e-05 tokens_per_second_per_gpu:2226.2402225200835 
Step 4563 | loss:2.051560401916504 lr:8.079980421157271e-05 tokens_per_second_per_gpu:2207.497022299484 
Step 4564 | loss:2.093970775604248 lr:8.076118919238666e-05 tokens_per_second_per_gpu:2204.0602346028263 
Step 4565 | loss:2.0746917724609375 lr:8.072257715197017e-05 tokens_per_second_per_gpu:2188.3689253454622 
Step 4566 | loss:2.0843262672424316 lr:8.068396809630158e-05 tokens_per_second_per_gpu:2196.9305850452547 
Step 4567 | loss:2.08872652053833 lr:8.06453620313588e-05 tokens_per_second_per_gpu:2228.116930234739 
Step 4568 | loss:2.1263082027435303 lr:8.060675896311925e-05 tokens_per_second_per_gpu:2225.0145888739003 
Step 4569 | loss:2.029560089111328 lr:8.056815889755984e-05 tokens_per_second_per_gpu:2190.9110164719286 
Step 4570 | loss:2.1134133338928223 lr:8.052956184065714e-05 tokens_per_second_per_gpu:2228.8918801257696 
Step 4571 | loss:2.093289852142334 lr:8.049096779838719e-05 tokens_per_second_per_gpu:2209.613856309594 
Step 4572 | loss:2.1034998893737793 lr:8.04523767767255e-05 tokens_per_second_per_gpu:2223.8590647277283 
Step 4573 | loss:2.0833921432495117 lr:8.04137887816472e-05 tokens_per_second_per_gpu:2133.129518883366 
Step 4574 | loss:2.0992119312286377 lr:8.037520381912685e-05 tokens_per_second_per_gpu:2115.6260829276894 
Step 4575 | loss:2.0347962379455566 lr:8.033662189513874e-05 tokens_per_second_per_gpu:2197.444075489601 
Step 4576 | loss:2.1217122077941895 lr:8.029804301565645e-05 tokens_per_second_per_gpu:2231.0362777177725 
Step 4577 | loss:2.1557202339172363 lr:8.025946718665325e-05 tokens_per_second_per_gpu:2226.596945131847 
Step 4578 | loss:2.0853748321533203 lr:8.022089441410185e-05 tokens_per_second_per_gpu:2225.7614161902525 
Step 4579 | loss:2.093933582305908 lr:8.018232470397455e-05 tokens_per_second_per_gpu:2219.1338871493795 
Step 4580 | loss:2.1303815841674805 lr:8.014375806224309e-05 tokens_per_second_per_gpu:2212.7024288877606 
Step 4581 | loss:2.100097179412842 lr:8.01051944948789e-05 tokens_per_second_per_gpu:2207.9267637985513 
Step 4582 | loss:2.1087470054626465 lr:8.006663400785272e-05 tokens_per_second_per_gpu:2159.226048136958 
Step 4583 | loss:2.1114296913146973 lr:8.0028076607135e-05 tokens_per_second_per_gpu:2154.480804789552 
Step 4584 | loss:2.178218364715576 lr:7.998952229869557e-05 tokens_per_second_per_gpu:2225.1902531895457 
Step 4585 | loss:2.0796689987182617 lr:7.995097108850384e-05 tokens_per_second_per_gpu:2218.2735170845604 
Step 4586 | loss:2.080918788909912 lr:7.991242298252881e-05 tokens_per_second_per_gpu:2224.7024090251607 
Step 4587 | loss:2.0659632682800293 lr:7.98738779867389e-05 tokens_per_second_per_gpu:2208.580532918314 
Step 4588 | loss:2.1071271896362305 lr:7.983533610710203e-05 tokens_per_second_per_gpu:2213.7385742416823 
Step 4589 | loss:2.0479538440704346 lr:7.979679734958578e-05 tokens_per_second_per_gpu:2189.0029819899805 
Step 4590 | loss:2.1185474395751953 lr:7.975826172015704e-05 tokens_per_second_per_gpu:2225.409621326569 
Step 4591 | loss:2.054516077041626 lr:7.971972922478243e-05 tokens_per_second_per_gpu:2205.4951711606027 
Step 4592 | loss:2.0517609119415283 lr:7.968119986942799e-05 tokens_per_second_per_gpu:2173.457434436179 
Step 4593 | loss:2.0841829776763916 lr:7.964267366005921e-05 tokens_per_second_per_gpu:2205.1347165606376 
Step 4594 | loss:2.077065944671631 lr:7.960415060264115e-05 tokens_per_second_per_gpu:2219.886537937742 
Step 4595 | loss:2.0778512954711914 lr:7.956563070313843e-05 tokens_per_second_per_gpu:2188.106618090651 
Step 4596 | loss:2.0327107906341553 lr:7.952711396751507e-05 tokens_per_second_per_gpu:2194.60114625485 
Step 4597 | loss:2.083639621734619 lr:7.948860040173474e-05 tokens_per_second_per_gpu:2209.459491298568 
Step 4598 | loss:2.0806095600128174 lr:7.945009001176052e-05 tokens_per_second_per_gpu:2083.6354341928286 
Step 4599 | loss:2.086850881576538 lr:7.941158280355501e-05 tokens_per_second_per_gpu:2195.1189269013553 
Step 4600 | loss:2.0993056297302246 lr:7.937307878308032e-05 tokens_per_second_per_gpu:2193.230662292243 
Step 4601 | loss:2.0423994064331055 lr:7.933457795629808e-05 tokens_per_second_per_gpu:2119.6161332733345 
Step 4602 | loss:2.064237594604492 lr:7.929608032916946e-05 tokens_per_second_per_gpu:2224.9593001699277 
Step 4603 | loss:2.047637462615967 lr:7.925758590765505e-05 tokens_per_second_per_gpu:2194.2868415998755 
Step 4604 | loss:2.136857032775879 lr:7.921909469771504e-05 tokens_per_second_per_gpu:2111.030817537463 
Step 4605 | loss:2.10886549949646 lr:7.918060670530904e-05 tokens_per_second_per_gpu:2165.777581001437 
Step 4606 | loss:2.0894734859466553 lr:7.914212193639614e-05 tokens_per_second_per_gpu:2216.545763020106 
Step 4607 | loss:2.099902868270874 lr:7.910364039693508e-05 tokens_per_second_per_gpu:2230.8434355991762 
Step 4608 | loss:2.1285717487335205 lr:7.9065162092884e-05 tokens_per_second_per_gpu:2186.1372807308735 
Step 4609 | loss:2.0784735679626465 lr:7.902668703020047e-05 tokens_per_second_per_gpu:2166.877497636018 
Step 4610 | loss:2.08819580078125 lr:7.89882152148417e-05 tokens_per_second_per_gpu:2182.86941874705 
Step 4611 | loss:2.1220479011535645 lr:7.89497466527643e-05 tokens_per_second_per_gpu:2205.8721396087794 
Step 4612 | loss:2.0648365020751953 lr:7.89112813499244e-05 tokens_per_second_per_gpu:2191.4951965947344 
Step 4613 | loss:2.0903868675231934 lr:7.887281931227765e-05 tokens_per_second_per_gpu:2185.92439662393 
Step 4614 | loss:2.0678093433380127 lr:7.88343605457792e-05 tokens_per_second_per_gpu:2223.51326142077 
Step 4615 | loss:2.0812196731567383 lr:7.87959050563836e-05 tokens_per_second_per_gpu:2224.0165836856545 
Step 4616 | loss:2.1181907653808594 lr:7.875745285004504e-05 tokens_per_second_per_gpu:2231.8044169430373 
Step 4617 | loss:2.1158831119537354 lr:7.871900393271704e-05 tokens_per_second_per_gpu:2197.470940454043 
Step 4618 | loss:2.104787588119507 lr:7.868055831035276e-05 tokens_per_second_per_gpu:2228.043622330235 
Step 4619 | loss:2.0673956871032715 lr:7.864211598890478e-05 tokens_per_second_per_gpu:2179.6522285306874 
Step 4620 | loss:2.1611056327819824 lr:7.860367697432518e-05 tokens_per_second_per_gpu:2224.6089168968956 
Step 4621 | loss:2.099921941757202 lr:7.856524127256548e-05 tokens_per_second_per_gpu:2227.5050088208204 
Step 4622 | loss:2.047787666320801 lr:7.852680888957673e-05 tokens_per_second_per_gpu:2199.4920177497897 
Step 4623 | loss:2.11480712890625 lr:7.848837983130951e-05 tokens_per_second_per_gpu:2218.200417908204 
Step 4624 | loss:2.057727336883545 lr:7.844995410371381e-05 tokens_per_second_per_gpu:2210.747370407388 
Step 4625 | loss:2.1255781650543213 lr:7.841153171273914e-05 tokens_per_second_per_gpu:2224.8828184350973 
Step 4626 | loss:2.052855968475342 lr:7.837311266433452e-05 tokens_per_second_per_gpu:2215.1368766419523 
Step 4627 | loss:2.0548291206359863 lr:7.833469696444833e-05 tokens_per_second_per_gpu:2206.6476833147976 
Step 4628 | loss:2.076174736022949 lr:7.829628461902858e-05 tokens_per_second_per_gpu:2204.2729259802363 
Step 4629 | loss:2.1081466674804688 lr:7.825787563402273e-05 tokens_per_second_per_gpu:2192.8951151968845 
Step 4630 | loss:2.1920862197875977 lr:7.821947001537766e-05 tokens_per_second_per_gpu:2159.7156942084353 
Step 4631 | loss:2.0870203971862793 lr:7.818106776903977e-05 tokens_per_second_per_gpu:2228.3677734640414 
Step 4632 | loss:2.070216417312622 lr:7.814266890095494e-05 tokens_per_second_per_gpu:2224.8103598489047 
Step 4633 | loss:2.083782911300659 lr:7.810427341706844e-05 tokens_per_second_per_gpu:2225.6800344579196 
Step 4634 | loss:2.1764607429504395 lr:7.806588132332517e-05 tokens_per_second_per_gpu:2210.7763896358356 
Step 4635 | loss:2.0861194133758545 lr:7.802749262566944e-05 tokens_per_second_per_gpu:2202.2512646855967 
Step 4636 | loss:2.0802555084228516 lr:7.798910733004496e-05 tokens_per_second_per_gpu:2226.4451573883566 
Step 4637 | loss:2.043102741241455 lr:7.795072544239502e-05 tokens_per_second_per_gpu:2203.808082358449 
Step 4638 | loss:2.0970888137817383 lr:7.791234696866233e-05 tokens_per_second_per_gpu:2223.9254816742464 
Step 4639 | loss:2.101256847381592 lr:7.787397191478901e-05 tokens_per_second_per_gpu:2179.1727472612247 
Step 4640 | loss:2.117661952972412 lr:7.783560028671681e-05 tokens_per_second_per_gpu:2214.1132283738702 
Step 4641 | loss:2.0908305644989014 lr:7.779723209038683e-05 tokens_per_second_per_gpu:2229.6536649622317 
Step 4642 | loss:2.043010711669922 lr:7.775886733173964e-05 tokens_per_second_per_gpu:2133.7603829305112 
Step 4643 | loss:2.087584972381592 lr:7.772050601671535e-05 tokens_per_second_per_gpu:2123.052031639525 
Step 4644 | loss:2.041259288787842 lr:7.768214815125344e-05 tokens_per_second_per_gpu:2177.4552070970917 
Step 4645 | loss:2.0558791160583496 lr:7.764379374129292e-05 tokens_per_second_per_gpu:2189.5406448679787 
Step 4646 | loss:2.0464916229248047 lr:7.760544279277231e-05 tokens_per_second_per_gpu:2163.706172727181 
Step 4647 | loss:2.0930333137512207 lr:7.756709531162948e-05 tokens_per_second_per_gpu:2169.1023795175474 
Step 4648 | loss:2.0271434783935547 lr:7.752875130380181e-05 tokens_per_second_per_gpu:2157.154731946416 
Step 4649 | loss:2.0395355224609375 lr:7.749041077522614e-05 tokens_per_second_per_gpu:2203.0662855800865 
Step 4650 | loss:2.089855909347534 lr:7.745207373183887e-05 tokens_per_second_per_gpu:2217.6135534539208 
Step 4651 | loss:2.0863046646118164 lr:7.74137401795757e-05 tokens_per_second_per_gpu:2195.8943301468075 
Step 4652 | loss:2.088381052017212 lr:7.737541012437188e-05 tokens_per_second_per_gpu:2223.469603856326 
Step 4653 | loss:2.0667855739593506 lr:7.733708357216213e-05 tokens_per_second_per_gpu:2219.78322252434 
Step 4654 | loss:2.03940486907959 lr:7.729876052888053e-05 tokens_per_second_per_gpu:2226.831039670547 
Step 4655 | loss:2.06461763381958 lr:7.72604410004607e-05 tokens_per_second_per_gpu:2210.484275791298 
Step 4656 | loss:2.1004350185394287 lr:7.722212499283578e-05 tokens_per_second_per_gpu:2142.210004096822 
Step 4657 | loss:2.135854721069336 lr:7.718381251193822e-05 tokens_per_second_per_gpu:2215.571308578724 
Step 4658 | loss:2.102585792541504 lr:7.714550356370001e-05 tokens_per_second_per_gpu:2166.145358451946 
Step 4659 | loss:2.090149402618408 lr:7.710719815405257e-05 tokens_per_second_per_gpu:2193.9371980093665 
Step 4660 | loss:2.068425178527832 lr:7.706889628892673e-05 tokens_per_second_per_gpu:2137.4186586908622 
Step 4661 | loss:2.0419199466705322 lr:7.703059797425288e-05 tokens_per_second_per_gpu:2225.7055072903545 
Step 4662 | loss:2.054490327835083 lr:7.699230321596079e-05 tokens_per_second_per_gpu:2213.2130935830914 
Step 4663 | loss:2.074199676513672 lr:7.695401201997967e-05 tokens_per_second_per_gpu:2219.9709533170408 
Step 4664 | loss:2.0939087867736816 lr:7.69157243922382e-05 tokens_per_second_per_gpu:2199.394111596476 
Step 4665 | loss:2.114262819290161 lr:7.687744033866445e-05 tokens_per_second_per_gpu:2196.909901628574 
Step 4666 | loss:2.0284104347229004 lr:7.683915986518609e-05 tokens_per_second_per_gpu:2212.959444549163 
Step 4667 | loss:2.0996007919311523 lr:7.680088297773006e-05 tokens_per_second_per_gpu:2210.3411249683854 
Step 4668 | loss:2.1110761165618896 lr:7.676260968222286e-05 tokens_per_second_per_gpu:2229.186947181839 
Step 4669 | loss:2.0891995429992676 lr:7.672433998459035e-05 tokens_per_second_per_gpu:2228.109516936847 
Step 4670 | loss:2.1143836975097656 lr:7.668607389075792e-05 tokens_per_second_per_gpu:2214.8113219464485 
Step 4671 | loss:2.084529399871826 lr:7.66478114066503e-05 tokens_per_second_per_gpu:2220.8518949833247 
Step 4672 | loss:2.038188934326172 lr:7.660955253819178e-05 tokens_per_second_per_gpu:2195.411746378815 
Step 4673 | loss:2.109858512878418 lr:7.657129729130602e-05 tokens_per_second_per_gpu:2228.4714268180405 
Step 4674 | loss:2.060670852661133 lr:7.653304567191611e-05 tokens_per_second_per_gpu:2217.711615208053 
Step 4675 | loss:2.098881721496582 lr:7.649479768594459e-05 tokens_per_second_per_gpu:2186.194970409779 
Step 4676 | loss:2.042757034301758 lr:7.645655333931343e-05 tokens_per_second_per_gpu:2222.8230819929627 
Step 4677 | loss:2.063326358795166 lr:7.641831263794412e-05 tokens_per_second_per_gpu:2209.7360070063114 
Step 4678 | loss:2.107487201690674 lr:7.638007558775746e-05 tokens_per_second_per_gpu:2187.1774731653036 
Step 4679 | loss:2.073204517364502 lr:7.634184219467376e-05 tokens_per_second_per_gpu:2213.0024785281294 
Step 4680 | loss:2.067824363708496 lr:7.630361246461275e-05 tokens_per_second_per_gpu:2209.038886504988 
Step 4681 | loss:2.049034595489502 lr:7.626538640349353e-05 tokens_per_second_per_gpu:2204.32566936989 
Step 4682 | loss:2.0861639976501465 lr:7.622716401723476e-05 tokens_per_second_per_gpu:2223.485216434838 
Step 4683 | loss:2.1031274795532227 lr:7.618894531175446e-05 tokens_per_second_per_gpu:2205.2552062533005 
Step 4684 | loss:2.0477538108825684 lr:7.615073029297003e-05 tokens_per_second_per_gpu:2198.0297209621535 
Step 4685 | loss:2.0600266456604004 lr:7.61125189667984e-05 tokens_per_second_per_gpu:2189.791883705306 
Step 4686 | loss:2.036390781402588 lr:7.607431133915586e-05 tokens_per_second_per_gpu:2212.5308276189244 
Step 4687 | loss:2.0255179405212402 lr:7.60361074159581e-05 tokens_per_second_per_gpu:2220.2029898296546 
Step 4688 | loss:2.0995278358459473 lr:7.599790720312035e-05 tokens_per_second_per_gpu:2224.0477495566565 
Step 4689 | loss:2.147721529006958 lr:7.595971070655717e-05 tokens_per_second_per_gpu:2167.420581647952 
Step 4690 | loss:2.0531058311462402 lr:7.592151793218257e-05 tokens_per_second_per_gpu:2147.7406681072052 
Step 4691 | loss:2.0773439407348633 lr:7.588332888591001e-05 tokens_per_second_per_gpu:2149.7970436136807 
Step 4692 | loss:2.1099090576171875 lr:7.584514357365229e-05 tokens_per_second_per_gpu:2209.5749860934893 
Step 4693 | loss:2.027927875518799 lr:7.580696200132177e-05 tokens_per_second_per_gpu:2176.5955501090466 
Step 4694 | loss:2.0564255714416504 lr:7.576878417483009e-05 tokens_per_second_per_gpu:2212.7631458796127 
Step 4695 | loss:2.0579566955566406 lr:7.573061010008839e-05 tokens_per_second_per_gpu:2218.6431806563573 
Step 4696 | loss:2.072892904281616 lr:7.569243978300722e-05 tokens_per_second_per_gpu:2228.7519099436513 
Step 4697 | loss:2.1399285793304443 lr:7.565427322949654e-05 tokens_per_second_per_gpu:2215.5656389558967 
Step 4698 | loss:2.074446201324463 lr:7.561611044546567e-05 tokens_per_second_per_gpu:2189.591698029251 
Step 4699 | loss:2.086257219314575 lr:7.557795143682346e-05 tokens_per_second_per_gpu:2194.1008972682234 
Step 4700 | loss:2.0157597064971924 lr:7.553979620947815e-05 tokens_per_second_per_gpu:2227.2518241879907 
Step 4701 | loss:2.107732057571411 lr:7.550164476933732e-05 tokens_per_second_per_gpu:2226.399937912417 
Step 4702 | loss:2.0684194564819336 lr:7.546349712230798e-05 tokens_per_second_per_gpu:2195.9162632428925 
Step 4703 | loss:2.123441696166992 lr:7.542535327429658e-05 tokens_per_second_per_gpu:2214.0352793321895 
Step 4704 | loss:2.0555787086486816 lr:7.538721323120906e-05 tokens_per_second_per_gpu:2221.3122564576115 
Step 4705 | loss:2.068173408508301 lr:7.534907699895059e-05 tokens_per_second_per_gpu:2225.1625149083065 
Step 4706 | loss:2.1308789253234863 lr:7.531094458342593e-05 tokens_per_second_per_gpu:2200.9606866209606 
Step 4707 | loss:2.0643718242645264 lr:7.527281599053914e-05 tokens_per_second_per_gpu:2177.723255135263 
Step 4708 | loss:2.0496773719787598 lr:7.523469122619368e-05 tokens_per_second_per_gpu:2200.4279073266466 
Step 4709 | loss:2.0987322330474854 lr:7.51965702962925e-05 tokens_per_second_per_gpu:2230.127492192524 
Step 4710 | loss:2.04270601272583 lr:7.515845320673793e-05 tokens_per_second_per_gpu:2225.3924230321068 
Step 4711 | loss:2.0817551612854004 lr:7.512033996343165e-05 tokens_per_second_per_gpu:2224.116700701322 
Step 4712 | loss:2.142997980117798 lr:7.50822305722748e-05 tokens_per_second_per_gpu:2213.9682987666215 
Step 4713 | loss:2.091658115386963 lr:7.504412503916791e-05 tokens_per_second_per_gpu:2206.8836936288494 
Step 4714 | loss:2.1305415630340576 lr:7.500602337001086e-05 tokens_per_second_per_gpu:2198.764769928874 
Step 4715 | loss:2.1440742015838623 lr:7.496792557070302e-05 tokens_per_second_per_gpu:2215.2367829100767 
Step 4716 | loss:2.049635887145996 lr:7.492983164714316e-05 tokens_per_second_per_gpu:2186.8476273398105 
Step 4717 | loss:2.1437277793884277 lr:7.489174160522933e-05 tokens_per_second_per_gpu:2206.5208029907576 
Step 4718 | loss:2.0709738731384277 lr:7.485365545085914e-05 tokens_per_second_per_gpu:2171.439047822052 
Step 4719 | loss:2.0615129470825195 lr:7.481557318992942e-05 tokens_per_second_per_gpu:2213.1180868293877 
Step 4720 | loss:2.1212854385375977 lr:7.47774948283366e-05 tokens_per_second_per_gpu:2224.9249731284135 
Step 4721 | loss:2.1589531898498535 lr:7.473942037197633e-05 tokens_per_second_per_gpu:2201.958135154072 
Step 4722 | loss:2.0978188514709473 lr:7.470134982674376e-05 tokens_per_second_per_gpu:2174.524475428793 
Step 4723 | loss:2.1605279445648193 lr:7.466328319853338e-05 tokens_per_second_per_gpu:2214.476471702823 
Step 4724 | loss:2.042919397354126 lr:7.462522049323908e-05 tokens_per_second_per_gpu:2200.20698219516 
Step 4725 | loss:2.0677175521850586 lr:7.458716171675421e-05 tokens_per_second_per_gpu:2113.5975401827877 
Step 4726 | loss:2.173079013824463 lr:7.454910687497143e-05 tokens_per_second_per_gpu:2216.3123213081276 
Step 4727 | loss:2.0239357948303223 lr:7.451105597378282e-05 tokens_per_second_per_gpu:2214.5890538629365 
Step 4728 | loss:2.0850515365600586 lr:7.447300901907988e-05 tokens_per_second_per_gpu:2220.9821097762015 
Step 4729 | loss:2.0807456970214844 lr:7.443496601675339e-05 tokens_per_second_per_gpu:2155.994186804976 
Step 4730 | loss:2.0744755268096924 lr:7.439692697269364e-05 tokens_per_second_per_gpu:2214.1282005351522 
Step 4731 | loss:2.134143829345703 lr:7.43588918927903e-05 tokens_per_second_per_gpu:2160.885254363581 
Step 4732 | loss:2.0454020500183105 lr:7.432086078293234e-05 tokens_per_second_per_gpu:2232.872480939237 
Step 4733 | loss:2.0809326171875 lr:7.428283364900821e-05 tokens_per_second_per_gpu:2217.93253730792 
Step 4734 | loss:2.1010231971740723 lr:7.424481049690566e-05 tokens_per_second_per_gpu:2224.7065079327463 
Step 4735 | loss:2.100980281829834 lr:7.420679133251185e-05 tokens_per_second_per_gpu:2223.943350454373 
Step 4736 | loss:2.032867431640625 lr:7.416877616171336e-05 tokens_per_second_per_gpu:2227.460566978435 
Step 4737 | loss:2.022007942199707 lr:7.413076499039617e-05 tokens_per_second_per_gpu:2232.331168324665 
Step 4738 | loss:2.0605459213256836 lr:7.409275782444551e-05 tokens_per_second_per_gpu:2170.8358539741575 
Step 4739 | loss:2.1149563789367676 lr:7.405475466974616e-05 tokens_per_second_per_gpu:2151.172103608898 
Step 4740 | loss:2.128230094909668 lr:7.401675553218216e-05 tokens_per_second_per_gpu:2226.1348133526867 
Step 4741 | loss:2.0730204582214355 lr:7.397876041763694e-05 tokens_per_second_per_gpu:2212.272242656435 
Step 4742 | loss:2.1142287254333496 lr:7.394076933199336e-05 tokens_per_second_per_gpu:2155.964062575019 
Step 4743 | loss:2.1311442852020264 lr:7.390278228113365e-05 tokens_per_second_per_gpu:2114.7697742975365 
Step 4744 | loss:2.0664548873901367 lr:7.386479927093935e-05 tokens_per_second_per_gpu:2218.2246362735623 
Step 4745 | loss:2.1261253356933594 lr:7.382682030729146e-05 tokens_per_second_per_gpu:2224.4078501952663 
Step 4746 | loss:2.099574089050293 lr:7.378884539607022e-05 tokens_per_second_per_gpu:2136.7520139122566 
Step 4747 | loss:2.096907615661621 lr:7.375087454315548e-05 tokens_per_second_per_gpu:2197.72613527409 
Step 4748 | loss:2.064236640930176 lr:7.371290775442621e-05 tokens_per_second_per_gpu:2230.4559535703656 
Step 4749 | loss:2.0805091857910156 lr:7.36749450357609e-05 tokens_per_second_per_gpu:2225.2528676444867 
Step 4750 | loss:2.073908567428589 lr:7.363698639303732e-05 tokens_per_second_per_gpu:2133.181540997275 
Step 4751 | loss:2.1215178966522217 lr:7.359903183213269e-05 tokens_per_second_per_gpu:2213.9174121626693 
Step 4752 | loss:2.0814714431762695 lr:7.356108135892357e-05 tokens_per_second_per_gpu:2200.140932503092 
Step 4753 | loss:2.1487553119659424 lr:7.352313497928584e-05 tokens_per_second_per_gpu:2229.174763642152 
Step 4754 | loss:2.1003761291503906 lr:7.348519269909486e-05 tokens_per_second_per_gpu:2188.267024020856 
Step 4755 | loss:2.0600404739379883 lr:7.344725452422523e-05 tokens_per_second_per_gpu:2215.6209702237456 
Step 4756 | loss:2.1325230598449707 lr:7.340932046055096e-05 tokens_per_second_per_gpu:2122.9479931058145 
Step 4757 | loss:2.1389174461364746 lr:7.33713905139454e-05 tokens_per_second_per_gpu:2214.0015411423296 
Step 4758 | loss:2.0810718536376953 lr:7.333346469028138e-05 tokens_per_second_per_gpu:2228.664799055519 
Step 4759 | loss:2.10945200920105 lr:7.329554299543095e-05 tokens_per_second_per_gpu:2175.7705977011296 
Step 4760 | loss:2.055300235748291 lr:7.325762543526558e-05 tokens_per_second_per_gpu:2231.0104350041283 
Step 4761 | loss:2.145367383956909 lr:7.321971201565612e-05 tokens_per_second_per_gpu:2207.509640763781 
Step 4762 | loss:2.030085563659668 lr:7.318180274247266e-05 tokens_per_second_per_gpu:2200.790991764393 
Step 4763 | loss:2.0377254486083984 lr:7.314389762158485e-05 tokens_per_second_per_gpu:2217.3349681803156 
Step 4764 | loss:2.064596176147461 lr:7.310599665886156e-05 tokens_per_second_per_gpu:2193.408482559843 
Step 4765 | loss:2.124377965927124 lr:7.306809986017101e-05 tokens_per_second_per_gpu:2115.2110678014214 
Step 4766 | loss:2.1162004470825195 lr:7.303020723138083e-05 tokens_per_second_per_gpu:2154.6527096364307 
Step 4767 | loss:2.0151281356811523 lr:7.299231877835797e-05 tokens_per_second_per_gpu:2204.867873575423 
Step 4768 | loss:2.0425591468811035 lr:7.29544345069688e-05 tokens_per_second_per_gpu:2126.6287324642003 
Step 4769 | loss:2.09940242767334 lr:7.291655442307892e-05 tokens_per_second_per_gpu:2225.40839476312 
Step 4770 | loss:2.086920738220215 lr:7.287867853255342e-05 tokens_per_second_per_gpu:2191.926861217477 
Step 4771 | loss:2.0658020973205566 lr:7.284080684125661e-05 tokens_per_second_per_gpu:2207.647365806903 
Step 4772 | loss:2.0504817962646484 lr:7.280293935505225e-05 tokens_per_second_per_gpu:2204.8419761467994 
Step 4773 | loss:2.0317373275756836 lr:7.276507607980336e-05 tokens_per_second_per_gpu:2165.9515568181305 
Step 4774 | loss:2.052074909210205 lr:7.272721702137244e-05 tokens_per_second_per_gpu:2151.8412485216745 
Step 4775 | loss:2.0853939056396484 lr:7.26893621856212e-05 tokens_per_second_per_gpu:2158.2241710506137 
Step 4776 | loss:2.073744058609009 lr:7.26515115784108e-05 tokens_per_second_per_gpu:2203.9715137755375 
Step 4777 | loss:2.1327309608459473 lr:7.261366520560161e-05 tokens_per_second_per_gpu:2217.1548517612805 
Step 4778 | loss:2.1260485649108887 lr:7.257582307305348e-05 tokens_per_second_per_gpu:2167.2769228563907 
Step 4779 | loss:2.0198161602020264 lr:7.253798518662561e-05 tokens_per_second_per_gpu:2211.7872306244462 
Step 4780 | loss:2.0831122398376465 lr:7.250015155217642e-05 tokens_per_second_per_gpu:2231.416411276466 
Step 4781 | loss:2.1199660301208496 lr:7.246232217556377e-05 tokens_per_second_per_gpu:2229.064670227954 
Step 4782 | loss:2.033050537109375 lr:7.242449706264484e-05 tokens_per_second_per_gpu:2223.8097060738673 
Step 4783 | loss:2.0816521644592285 lr:7.238667621927606e-05 tokens_per_second_per_gpu:2222.514239588687 
Step 4784 | loss:2.091783046722412 lr:7.234885965131337e-05 tokens_per_second_per_gpu:2226.4518610871846 
Step 4785 | loss:2.0786702632904053 lr:7.231104736461194e-05 tokens_per_second_per_gpu:2217.066710686143 
Step 4786 | loss:2.0146615505218506 lr:7.227323936502627e-05 tokens_per_second_per_gpu:2215.045043210819 
Step 4787 | loss:2.1157822608947754 lr:7.223543565841024e-05 tokens_per_second_per_gpu:2212.982802153044 
Step 4788 | loss:2.041916847229004 lr:7.219763625061707e-05 tokens_per_second_per_gpu:2216.621552812833 
Step 4789 | loss:2.144606590270996 lr:7.215984114749919e-05 tokens_per_second_per_gpu:2210.103303710754 
Step 4790 | loss:2.0698654651641846 lr:7.212205035490855e-05 tokens_per_second_per_gpu:2184.7492539276654 
Step 4791 | loss:2.103902816772461 lr:7.208426387869636e-05 tokens_per_second_per_gpu:2230.6305633499665 
Step 4792 | loss:2.105952262878418 lr:7.20464817247131e-05 tokens_per_second_per_gpu:2218.001971488038 
Step 4793 | loss:2.0905654430389404 lr:7.200870389880867e-05 tokens_per_second_per_gpu:2211.1467328770877 
Step 4794 | loss:2.123842239379883 lr:7.197093040683218e-05 tokens_per_second_per_gpu:2195.5509410385234 
Step 4795 | loss:2.0748682022094727 lr:7.193316125463225e-05 tokens_per_second_per_gpu:2230.6233752076037 
Step 4796 | loss:2.0938963890075684 lr:7.189539644805668e-05 tokens_per_second_per_gpu:2196.7377137193084 
Step 4797 | loss:2.130009651184082 lr:7.185763599295264e-05 tokens_per_second_per_gpu:2215.482336633303 
Step 4798 | loss:2.116635799407959 lr:7.181987989516661e-05 tokens_per_second_per_gpu:2232.345755220179 
Step 4799 | loss:2.0588326454162598 lr:7.178212816054446e-05 tokens_per_second_per_gpu:2218.389092858362 
Step 4800 | loss:2.097759246826172 lr:7.174438079493128e-05 tokens_per_second_per_gpu:2210.627403532381 
Step 4801 | loss:2.1000475883483887 lr:7.170663780417161e-05 tokens_per_second_per_gpu:2170.0515912157343 
Step 4802 | loss:2.0359396934509277 lr:7.166889919410919e-05 tokens_per_second_per_gpu:2190.1128620212503 
Step 4803 | loss:2.0903334617614746 lr:7.163116497058719e-05 tokens_per_second_per_gpu:2231.661016459957 
Step 4804 | loss:2.0231051445007324 lr:7.159343513944801e-05 tokens_per_second_per_gpu:2196.939785319296 
Step 4805 | loss:2.0616097450256348 lr:7.155570970653338e-05 tokens_per_second_per_gpu:2196.3605318641094 
Step 4806 | loss:2.0779647827148438 lr:7.151798867768444e-05 tokens_per_second_per_gpu:2221.8171964857625 
Step 4807 | loss:2.1110520362854004 lr:7.148027205874157e-05 tokens_per_second_per_gpu:2196.070564763325 
Step 4808 | loss:2.06225323677063 lr:7.144255985554446e-05 tokens_per_second_per_gpu:2158.2197099904124 
Step 4809 | loss:2.049832820892334 lr:7.140485207393217e-05 tokens_per_second_per_gpu:2213.7249037161278 
Step 4810 | loss:2.0872530937194824 lr:7.136714871974296e-05 tokens_per_second_per_gpu:2223.5593272421443 
Step 4811 | loss:2.077012062072754 lr:7.132944979881459e-05 tokens_per_second_per_gpu:2213.381602713231 
Step 4812 | loss:2.056267738342285 lr:7.129175531698401e-05 tokens_per_second_per_gpu:2232.917140158609 
Step 4813 | loss:2.0353891849517822 lr:7.125406528008747e-05 tokens_per_second_per_gpu:2100.676537800782 
Step 4814 | loss:2.085146903991699 lr:7.121637969396059e-05 tokens_per_second_per_gpu:2147.919828176766 
Step 4815 | loss:2.090421438217163 lr:7.117869856443827e-05 tokens_per_second_per_gpu:2227.184307186591 
Step 4816 | loss:2.126194477081299 lr:7.11410218973547e-05 tokens_per_second_per_gpu:2145.3614539646205 
Step 4817 | loss:2.094529151916504 lr:7.110334969854344e-05 tokens_per_second_per_gpu:2181.1320266195526 
Step 4818 | loss:2.0785341262817383 lr:7.106568197383734e-05 tokens_per_second_per_gpu:2187.8188222994104 
Step 4819 | loss:2.092866897583008 lr:7.102801872906852e-05 tokens_per_second_per_gpu:2225.103493854396 
Step 4820 | loss:2.118912696838379 lr:7.099035997006842e-05 tokens_per_second_per_gpu:2205.494738328066 
Step 4821 | loss:2.061382293701172 lr:7.095270570266779e-05 tokens_per_second_per_gpu:2182.9965059762744 
Step 4822 | loss:2.070235013961792 lr:7.091505593269671e-05 tokens_per_second_per_gpu:2215.3511170613915 
Step 4823 | loss:2.1007838249206543 lr:7.087741066598453e-05 tokens_per_second_per_gpu:2168.1154410427966 
Step 4824 | loss:2.0828700065612793 lr:7.083976990835994e-05 tokens_per_second_per_gpu:2212.9667903541035 
Step 4825 | loss:2.109574317932129 lr:7.080213366565084e-05 tokens_per_second_per_gpu:2126.7427463454433 
Step 4826 | loss:2.105820655822754 lr:7.076450194368455e-05 tokens_per_second_per_gpu:2220.3803103441383 
Step 4827 | loss:2.073357582092285 lr:7.072687474828765e-05 tokens_per_second_per_gpu:2214.3195856042917 
Step 4828 | loss:2.080453395843506 lr:7.068925208528598e-05 tokens_per_second_per_gpu:2216.8338227368745 
Step 4829 | loss:2.1024999618530273 lr:7.065163396050471e-05 tokens_per_second_per_gpu:2206.5983609623195 
Step 4830 | loss:2.128770112991333 lr:7.06140203797683e-05 tokens_per_second_per_gpu:2233.578687209085 
Step 4831 | loss:2.113971471786499 lr:7.05764113489005e-05 tokens_per_second_per_gpu:2188.600357379111 
Step 4832 | loss:2.0657665729522705 lr:7.053880687372435e-05 tokens_per_second_per_gpu:2224.1650779005035 
Step 4833 | loss:2.0543482303619385 lr:7.050120696006226e-05 tokens_per_second_per_gpu:2230.8261342577007 
Step 4834 | loss:2.115866184234619 lr:7.046361161373585e-05 tokens_per_second_per_gpu:2139.471310003562 
Step 4835 | loss:2.0774357318878174 lr:7.0426020840566e-05 tokens_per_second_per_gpu:2229.4523555069704 
Step 4836 | loss:2.038763999938965 lr:7.038843464637302e-05 tokens_per_second_per_gpu:2161.511169576226 
Step 4837 | loss:2.0419697761535645 lr:7.035085303697632e-05 tokens_per_second_per_gpu:2187.182683633861 
Step 4838 | loss:2.07708740234375 lr:7.03132760181948e-05 tokens_per_second_per_gpu:2126.0578648984474 
Step 4839 | loss:2.063377857208252 lr:7.027570359584657e-05 tokens_per_second_per_gpu:2158.477113081965 
Step 4840 | loss:2.0550942420959473 lr:7.023813577574893e-05 tokens_per_second_per_gpu:2228.610722927224 
Step 4841 | loss:2.1359219551086426 lr:7.020057256371863e-05 tokens_per_second_per_gpu:2221.443366106846 
Step 4842 | loss:2.088012218475342 lr:7.016301396557156e-05 tokens_per_second_per_gpu:2212.061447019424 
Step 4843 | loss:2.0609002113342285 lr:7.012545998712308e-05 tokens_per_second_per_gpu:2221.266232172093 
Step 4844 | loss:2.059614419937134 lr:7.008791063418759e-05 tokens_per_second_per_gpu:2199.9289941981065 
Step 4845 | loss:2.050286054611206 lr:7.005036591257899e-05 tokens_per_second_per_gpu:2182.5071886101027 
Step 4846 | loss:2.0397610664367676 lr:7.001282582811033e-05 tokens_per_second_per_gpu:2221.3052709329927 
Step 4847 | loss:2.0773072242736816 lr:6.997529038659402e-05 tokens_per_second_per_gpu:2229.89143803383 
Step 4848 | loss:2.1083264350891113 lr:6.993775959384167e-05 tokens_per_second_per_gpu:2164.9117047773407 
Step 4849 | loss:2.108185291290283 lr:6.990023345566431e-05 tokens_per_second_per_gpu:2211.93700875874 
Step 4850 | loss:2.162837505340576 lr:6.986271197787207e-05 tokens_per_second_per_gpu:2223.0101644722527 
Step 4851 | loss:2.086386203765869 lr:6.982519516627453e-05 tokens_per_second_per_gpu:2199.828754391711 
Step 4852 | loss:2.0795130729675293 lr:6.978768302668037e-05 tokens_per_second_per_gpu:2221.8517328451326 
Step 4853 | loss:2.1197633743286133 lr:6.975017556489769e-05 tokens_per_second_per_gpu:2171.09751161617 
Step 4854 | loss:2.05302357673645 lr:6.971267278673386e-05 tokens_per_second_per_gpu:2195.169291633577 
Step 4855 | loss:2.1122331619262695 lr:6.967517469799545e-05 tokens_per_second_per_gpu:2175.7566349070466 
Step 4856 | loss:2.0657620429992676 lr:6.96376813044883e-05 tokens_per_second_per_gpu:2222.77473585668 
Step 4857 | loss:2.0698533058166504 lr:6.960019261201761e-05 tokens_per_second_per_gpu:2232.44223650863 
Step 4858 | loss:2.1344759464263916 lr:6.956270862638778e-05 tokens_per_second_per_gpu:2231.74348007298 
Step 4859 | loss:2.053476095199585 lr:6.952522935340246e-05 tokens_per_second_per_gpu:2205.589440544248 
Step 4860 | loss:2.0240073204040527 lr:6.948775479886471e-05 tokens_per_second_per_gpu:2222.3535030633075 
Step 4861 | loss:2.1298816204071045 lr:6.945028496857672e-05 tokens_per_second_per_gpu:2203.5581635086937 
Step 4862 | loss:2.08370304107666 lr:6.941281986833996e-05 tokens_per_second_per_gpu:2229.1296268000815 
Step 4863 | loss:2.0884804725646973 lr:6.937535950395526e-05 tokens_per_second_per_gpu:2223.7446422107882 
Step 4864 | loss:2.078369140625 lr:6.933790388122256e-05 tokens_per_second_per_gpu:2216.2928429462672 
Step 4865 | loss:2.0777833461761475 lr:6.930045300594123e-05 tokens_per_second_per_gpu:2223.6300476834695 
Step 4866 | loss:2.1412911415100098 lr:6.926300688390987e-05 tokens_per_second_per_gpu:2227.9722974301544 
Step 4867 | loss:2.0770444869995117 lr:6.922556552092625e-05 tokens_per_second_per_gpu:2198.987270654982 
Step 4868 | loss:2.086709499359131 lr:6.918812892278749e-05 tokens_per_second_per_gpu:2226.5805153382626 
Step 4869 | loss:2.046921730041504 lr:6.91506970952899e-05 tokens_per_second_per_gpu:2174.6335301319373 
Step 4870 | loss:2.0118398666381836 lr:6.911327004422917e-05 tokens_per_second_per_gpu:2215.6391930133555 
Step 4871 | loss:2.0943727493286133 lr:6.907584777540013e-05 tokens_per_second_per_gpu:2226.2340158077272 
Step 4872 | loss:2.0891246795654297 lr:6.903843029459696e-05 tokens_per_second_per_gpu:2135.9393536413018 
Step 4873 | loss:2.082186698913574 lr:6.9001017607613e-05 tokens_per_second_per_gpu:2215.5047480378375 
Step 4874 | loss:2.0986132621765137 lr:6.896360972024094e-05 tokens_per_second_per_gpu:2178.4809197798218 
Step 4875 | loss:2.1120896339416504 lr:6.892620663827265e-05 tokens_per_second_per_gpu:2169.7528799130687 
Step 4876 | loss:2.058372974395752 lr:6.888880836749938e-05 tokens_per_second_per_gpu:2220.997801599723 
Step 4877 | loss:2.070767402648926 lr:6.885141491371147e-05 tokens_per_second_per_gpu:2189.29737274966 
Step 4878 | loss:2.055938720703125 lr:6.881402628269864e-05 tokens_per_second_per_gpu:2221.764104419908 
Step 4879 | loss:2.1219944953918457 lr:6.87766424802498e-05 tokens_per_second_per_gpu:2214.626645347439 
Step 4880 | loss:2.078469753265381 lr:6.873926351215312e-05 tokens_per_second_per_gpu:2233.031603807858 
Step 4881 | loss:2.0576725006103516 lr:6.870188938419608e-05 tokens_per_second_per_gpu:2182.7105056472947 
Step 4882 | loss:2.0729968547821045 lr:6.866452010216533e-05 tokens_per_second_per_gpu:2164.6023297901797 
Step 4883 | loss:2.065626621246338 lr:6.862715567184681e-05 tokens_per_second_per_gpu:2209.557688522378 
Step 4884 | loss:2.1300599575042725 lr:6.858979609902571e-05 tokens_per_second_per_gpu:2209.262048230673 
Step 4885 | loss:2.0783305168151855 lr:6.855244138948639e-05 tokens_per_second_per_gpu:2190.227510342349 
Step 4886 | loss:2.0985987186431885 lr:6.851509154901264e-05 tokens_per_second_per_gpu:2189.199390617905 
Step 4887 | loss:2.0540854930877686 lr:6.847774658338733e-05 tokens_per_second_per_gpu:2148.6782735978 
Step 4888 | loss:2.0951550006866455 lr:6.844040649839263e-05 tokens_per_second_per_gpu:2121.626023714405 
Step 4889 | loss:2.0911927223205566 lr:6.840307129980996e-05 tokens_per_second_per_gpu:2235.446683872635 
Step 4890 | loss:2.122130870819092 lr:6.836574099341997e-05 tokens_per_second_per_gpu:2209.281947569364 
Step 4891 | loss:2.104379653930664 lr:6.832841558500251e-05 tokens_per_second_per_gpu:2211.8642602838486 
Step 4892 | loss:2.0906853675842285 lr:6.829109508033679e-05 tokens_per_second_per_gpu:2151.258159210205 
Step 4893 | loss:2.0972299575805664 lr:6.82537794852012e-05 tokens_per_second_per_gpu:2217.3233255644486 
Step 4894 | loss:2.059462070465088 lr:6.821646880537332e-05 tokens_per_second_per_gpu:2224.5215600389884 
Step 4895 | loss:2.071119785308838 lr:6.817916304663002e-05 tokens_per_second_per_gpu:2220.545411378699 
Step 4896 | loss:2.005619525909424 lr:6.814186221474735e-05 tokens_per_second_per_gpu:2203.9843056354102 
Step 4897 | loss:2.1233038902282715 lr:6.810456631550076e-05 tokens_per_second_per_gpu:2211.979056636709 
Step 4898 | loss:2.0750184059143066 lr:6.806727535466473e-05 tokens_per_second_per_gpu:2205.3099426755343 
Step 4899 | loss:2.087285041809082 lr:6.80299893380131e-05 tokens_per_second_per_gpu:2219.448551892877 
Step 4900 | loss:2.0445971488952637 lr:6.79927082713189e-05 tokens_per_second_per_gpu:2231.124014617769 
Step 4901 | loss:2.0736875534057617 lr:6.795543216035437e-05 tokens_per_second_per_gpu:2228.410859131273 
Step 4902 | loss:2.0700135231018066 lr:6.791816101089111e-05 tokens_per_second_per_gpu:2211.791438744214 
Step 4903 | loss:2.071878671646118 lr:6.78808948286998e-05 tokens_per_second_per_gpu:2195.1958079543047 
Step 4904 | loss:2.11088490486145 lr:6.78436336195504e-05 tokens_per_second_per_gpu:2227.4923686114166 
Step 4905 | loss:2.088334798812866 lr:6.780637738921216e-05 tokens_per_second_per_gpu:2167.4328379170047 
Step 4906 | loss:2.1042673587799072 lr:6.776912614345344e-05 tokens_per_second_per_gpu:2231.2914551899503 
Step 4907 | loss:2.0775976181030273 lr:6.773187988804192e-05 tokens_per_second_per_gpu:2221.88116286896 
Step 4908 | loss:2.007371187210083 lr:6.769463862874454e-05 tokens_per_second_per_gpu:2220.5973416633096 
Step 4909 | loss:2.045480728149414 lr:6.765740237132736e-05 tokens_per_second_per_gpu:2226.328319904278 
Step 4910 | loss:2.061398506164551 lr:6.762017112155572e-05 tokens_per_second_per_gpu:2195.5611094392984 
Step 4911 | loss:2.086522340774536 lr:6.758294488519421e-05 tokens_per_second_per_gpu:2115.738104217541 
Step 4912 | loss:2.0763626098632812 lr:6.754572366800656e-05 tokens_per_second_per_gpu:2202.130699945211 
Step 4913 | loss:2.027254581451416 lr:6.750850747575581e-05 tokens_per_second_per_gpu:2210.4117061976763 
Step 4914 | loss:2.0492141246795654 lr:6.747129631420423e-05 tokens_per_second_per_gpu:2214.740894990844 
Step 4915 | loss:2.0943892002105713 lr:6.743409018911324e-05 tokens_per_second_per_gpu:2223.729350021016 
Step 4916 | loss:2.0290908813476562 lr:6.73968891062435e-05 tokens_per_second_per_gpu:2196.254621509691 
Step 4917 | loss:2.107016086578369 lr:6.73596930713549e-05 tokens_per_second_per_gpu:2228.7383500887545 
Step 4918 | loss:2.1098999977111816 lr:6.732250209020653e-05 tokens_per_second_per_gpu:2191.5785179200934 
Step 4919 | loss:2.100670337677002 lr:6.728531616855677e-05 tokens_per_second_per_gpu:2223.840502852569 
Step 4920 | loss:2.0494563579559326 lr:6.724813531216316e-05 tokens_per_second_per_gpu:2175.1638319411295 
Step 4921 | loss:2.1103944778442383 lr:6.72109595267824e-05 tokens_per_second_per_gpu:2194.591724453971 
Step 4922 | loss:2.062628746032715 lr:6.717378881817053e-05 tokens_per_second_per_gpu:2207.120825818372 
Step 4923 | loss:2.0805273056030273 lr:6.713662319208267e-05 tokens_per_second_per_gpu:2190.046059770771 
Step 4924 | loss:2.0944724082946777 lr:6.709946265427332e-05 tokens_per_second_per_gpu:2133.4078010268067 
Step 4925 | loss:2.0887656211853027 lr:6.7062307210496e-05 tokens_per_second_per_gpu:2176.622963415358 
Step 4926 | loss:2.0482287406921387 lr:6.702515686650358e-05 tokens_per_second_per_gpu:2168.693954164269 
Step 4927 | loss:2.0103323459625244 lr:6.698801162804807e-05 tokens_per_second_per_gpu:2182.6000344093773 
Step 4928 | loss:2.0698142051696777 lr:6.695087150088071e-05 tokens_per_second_per_gpu:2172.859244274678 
Step 4929 | loss:2.0438597202301025 lr:6.691373649075203e-05 tokens_per_second_per_gpu:2230.3861738634746 
Step 4930 | loss:2.113095998764038 lr:6.68766066034116e-05 tokens_per_second_per_gpu:2140.321599533151 
Step 4931 | loss:2.014242172241211 lr:6.683948184460834e-05 tokens_per_second_per_gpu:2171.8533277431493 
Step 4932 | loss:2.0871739387512207 lr:6.680236222009028e-05 tokens_per_second_per_gpu:2218.8110203323163 
Step 4933 | loss:2.1255526542663574 lr:6.676524773560472e-05 tokens_per_second_per_gpu:2203.879834722215 
Step 4934 | loss:2.006258010864258 lr:6.672813839689814e-05 tokens_per_second_per_gpu:2229.918175739489 
Step 4935 | loss:2.0078206062316895 lr:6.669103420971625e-05 tokens_per_second_per_gpu:2226.226262761944 
Step 4936 | loss:2.106473445892334 lr:6.665393517980394e-05 tokens_per_second_per_gpu:2211.59527168337 
Step 4937 | loss:2.121170997619629 lr:6.661684131290525e-05 tokens_per_second_per_gpu:2208.840363037102 
Step 4938 | loss:2.089573860168457 lr:6.657975261476352e-05 tokens_per_second_per_gpu:2205.845991354441 
Step 4939 | loss:2.0996975898742676 lr:6.654266909112119e-05 tokens_per_second_per_gpu:2170.9779462691263 
Step 4940 | loss:2.058668375015259 lr:6.650559074772e-05 tokens_per_second_per_gpu:2226.721123977851 
Step 4941 | loss:2.0791192054748535 lr:6.646851759030082e-05 tokens_per_second_per_gpu:2231.367884479201 
Step 4942 | loss:2.0912599563598633 lr:6.643144962460374e-05 tokens_per_second_per_gpu:2176.023020680386 
Step 4943 | loss:2.0959670543670654 lr:6.639438685636803e-05 tokens_per_second_per_gpu:2201.2175867666147 
Step 4944 | loss:2.084336519241333 lr:6.635732929133213e-05 tokens_per_second_per_gpu:2224.2772480109597 
Step 4945 | loss:2.0401742458343506 lr:6.63202769352338e-05 tokens_per_second_per_gpu:2157.27807896028 
Step 4946 | loss:2.021040201187134 lr:6.628322979380982e-05 tokens_per_second_per_gpu:2187.7441555455403 
Step 4947 | loss:2.1228184700012207 lr:6.62461878727963e-05 tokens_per_second_per_gpu:2206.633602171728 
Step 4948 | loss:2.0807361602783203 lr:6.620915117792844e-05 tokens_per_second_per_gpu:2225.117354336862 
Step 4949 | loss:2.076920986175537 lr:6.617211971494072e-05 tokens_per_second_per_gpu:2189.573971255849 
Step 4950 | loss:2.0951967239379883 lr:6.613509348956672e-05 tokens_per_second_per_gpu:2233.5418910371627 
Step 4951 | loss:2.0336995124816895 lr:6.609807250753935e-05 tokens_per_second_per_gpu:2216.9441203033307 
Step 4952 | loss:2.0811429023742676 lr:6.60610567745905e-05 tokens_per_second_per_gpu:2179.6777830904134 
Step 4953 | loss:2.120443344116211 lr:6.602404629645146e-05 tokens_per_second_per_gpu:2163.5129857784323 
Step 4954 | loss:2.1263699531555176 lr:6.598704107885254e-05 tokens_per_second_per_gpu:2062.2532001277773 
Step 4955 | loss:2.0820717811584473 lr:6.59500411275233e-05 tokens_per_second_per_gpu:2199.2502608613277 
Step 4956 | loss:2.112623691558838 lr:6.591304644819259e-05 tokens_per_second_per_gpu:2230.933600444418 
Step 4957 | loss:2.065627098083496 lr:6.587605704658826e-05 tokens_per_second_per_gpu:2094.399584800593 
Step 4958 | loss:2.0479235649108887 lr:6.583907292843742e-05 tokens_per_second_per_gpu:2139.696129038467 
Step 4959 | loss:2.1234703063964844 lr:6.580209409946641e-05 tokens_per_second_per_gpu:2195.7788446673117 
Step 4960 | loss:2.070183515548706 lr:6.576512056540067e-05 tokens_per_second_per_gpu:2168.8469971741706 
Step 4961 | loss:2.037445545196533 lr:6.572815233196486e-05 tokens_per_second_per_gpu:2227.236365104572 
Step 4962 | loss:2.128648281097412 lr:6.569118940488288e-05 tokens_per_second_per_gpu:2199.6682358316607 
Step 4963 | loss:2.124638557434082 lr:6.56542317898777e-05 tokens_per_second_per_gpu:2199.5952164207993 
Step 4964 | loss:2.0850894451141357 lr:6.56172794926715e-05 tokens_per_second_per_gpu:2224.7477166597055 
Step 4965 | loss:2.1127381324768066 lr:6.558033251898569e-05 tokens_per_second_per_gpu:2161.081033430461 
Step 4966 | loss:2.030088424682617 lr:6.554339087454076e-05 tokens_per_second_per_gpu:2222.0365475192534 
Step 4967 | loss:2.044663429260254 lr:6.550645456505647e-05 tokens_per_second_per_gpu:2109.3816873801316 
Step 4968 | loss:2.0947532653808594 lr:6.546952359625176e-05 tokens_per_second_per_gpu:2201.7838410176782 
Step 4969 | loss:2.1231400966644287 lr:6.543259797384463e-05 tokens_per_second_per_gpu:2211.1461726648186 
Step 4970 | loss:2.0776357650756836 lr:6.539567770355234e-05 tokens_per_second_per_gpu:2197.3036610033414 
Step 4971 | loss:2.064648151397705 lr:6.535876279109127e-05 tokens_per_second_per_gpu:2225.493912996797 
Step 4972 | loss:2.0746073722839355 lr:6.53218532421771e-05 tokens_per_second_per_gpu:2169.486586698744 
Step 4973 | loss:2.1213746070861816 lr:6.528494906252449e-05 tokens_per_second_per_gpu:2193.202716300264 
Step 4974 | loss:2.0808627605438232 lr:6.524805025784741e-05 tokens_per_second_per_gpu:2224.292455094168 
Step 4975 | loss:2.112537145614624 lr:6.521115683385892e-05 tokens_per_second_per_gpu:2175.277550611191 
Step 4976 | loss:2.0646328926086426 lr:6.517426879627132e-05 tokens_per_second_per_gpu:2178.4935591489234 
Step 4977 | loss:2.0880298614501953 lr:6.513738615079595e-05 tokens_per_second_per_gpu:2234.4744984866024 
Step 4978 | loss:2.0615997314453125 lr:6.510050890314347e-05 tokens_per_second_per_gpu:2201.925631797787 
Step 4979 | loss:2.0439796447753906 lr:6.50636370590236e-05 tokens_per_second_per_gpu:2214.72371719086 
Step 4980 | loss:2.0610976219177246 lr:6.502677062414528e-05 tokens_per_second_per_gpu:2100.025885160863 
Step 4981 | loss:2.058448314666748 lr:6.498990960421654e-05 tokens_per_second_per_gpu:2168.9403418202014 
Step 4982 | loss:2.1162328720092773 lr:6.495305400494464e-05 tokens_per_second_per_gpu:2228.4432849032496 
Step 4983 | loss:2.050868272781372 lr:6.491620383203602e-05 tokens_per_second_per_gpu:2227.2226179415975 
Step 4984 | loss:2.0430922508239746 lr:6.487935909119622e-05 tokens_per_second_per_gpu:2235.132597106872 
Step 4985 | loss:2.09297776222229 lr:6.484251978812992e-05 tokens_per_second_per_gpu:2206.562166740062 
Step 4986 | loss:2.0810842514038086 lr:6.480568592854103e-05 tokens_per_second_per_gpu:2171.6456134188456 
Step 4987 | loss:2.1441469192504883 lr:6.476885751813255e-05 tokens_per_second_per_gpu:2230.553336277913 
Step 4988 | loss:2.0866966247558594 lr:6.47320345626067e-05 tokens_per_second_per_gpu:2221.124606388124 
Step 4989 | loss:2.120868682861328 lr:6.469521706766483e-05 tokens_per_second_per_gpu:2226.0218416953453 
Step 4990 | loss:2.0739426612854004 lr:6.465840503900746e-05 tokens_per_second_per_gpu:2231.7831361861176 
Step 4991 | loss:2.1249442100524902 lr:6.462159848233417e-05 tokens_per_second_per_gpu:2226.4142346131953 
Step 4992 | loss:2.0290842056274414 lr:6.458479740334383e-05 tokens_per_second_per_gpu:2233.559715508413 
Step 4993 | loss:2.069091558456421 lr:6.454800180773432e-05 tokens_per_second_per_gpu:2214.366305075313 
Step 4994 | loss:2.0644001960754395 lr:6.451121170120284e-05 tokens_per_second_per_gpu:2225.141180515237 
Step 4995 | loss:2.144322633743286 lr:6.447442708944564e-05 tokens_per_second_per_gpu:2129.9221409524675 
Step 4996 | loss:2.0228867530822754 lr:6.44376479781581e-05 tokens_per_second_per_gpu:2232.51689265682 
Step 4997 | loss:2.1004555225372314 lr:6.440087437303474e-05 tokens_per_second_per_gpu:2229.938809876497 
Step 4998 | loss:2.111180305480957 lr:6.43641062797693e-05 tokens_per_second_per_gpu:2179.482501268054 
Step 4999 | loss:2.03503680229187 lr:6.432734370405467e-05 tokens_per_second_per_gpu:2215.3830122954028 
Step 5000 | loss:2.06959867477417 lr:6.429058665158279e-05 tokens_per_second_per_gpu:2212.2937530711715 
Step 5001 | loss:2.118147611618042 lr:6.425383512804484e-05 tokens_per_second_per_gpu:2244.3444386432975 
Step 5002 | loss:2.1104297637939453 lr:6.421708913913107e-05 tokens_per_second_per_gpu:2159.9652110493403 
Step 5003 | loss:2.0081586837768555 lr:6.418034869053089e-05 tokens_per_second_per_gpu:2219.400757202447 
Step 5004 | loss:2.0213422775268555 lr:6.414361378793294e-05 tokens_per_second_per_gpu:2196.1297434234475 
Step 5005 | loss:2.0579819679260254 lr:6.410688443702492e-05 tokens_per_second_per_gpu:2140.084102931668 
Step 5006 | loss:2.0705578327178955 lr:6.407016064349363e-05 tokens_per_second_per_gpu:2196.078370323017 
Step 5007 | loss:2.069246292114258 lr:6.40334424130251e-05 tokens_per_second_per_gpu:2173.372990240041 
Step 5008 | loss:2.0477004051208496 lr:6.399672975130444e-05 tokens_per_second_per_gpu:2232.7569030570558 
Step 5009 | loss:2.094926357269287 lr:6.396002266401589e-05 tokens_per_second_per_gpu:2221.937747193617 
Step 5010 | loss:2.125321388244629 lr:6.392332115684296e-05 tokens_per_second_per_gpu:2195.015000358208 
Step 5011 | loss:2.079537868499756 lr:6.388662523546811e-05 tokens_per_second_per_gpu:2208.6181838684097 
Step 5012 | loss:2.101151943206787 lr:6.3849934905573e-05 tokens_per_second_per_gpu:2222.1085735196966 
Step 5013 | loss:2.0653018951416016 lr:6.381325017283851e-05 tokens_per_second_per_gpu:2212.5085307438017 
Step 5014 | loss:2.1379318237304688 lr:6.37765710429445e-05 tokens_per_second_per_gpu:2220.448328098511 
Step 5015 | loss:2.135303497314453 lr:6.37398975215701e-05 tokens_per_second_per_gpu:2189.228503637166 
Step 5016 | loss:2.0956621170043945 lr:6.370322961439355e-05 tokens_per_second_per_gpu:2217.4874460442907 
Step 5017 | loss:2.1086490154266357 lr:6.366656732709213e-05 tokens_per_second_per_gpu:2224.494651228863 
Step 5018 | loss:2.030996084213257 lr:6.362991066534231e-05 tokens_per_second_per_gpu:2235.8313484389696 
Step 5019 | loss:1.9988760948181152 lr:6.359325963481972e-05 tokens_per_second_per_gpu:2234.1450421649142 
Step 5020 | loss:2.1487998962402344 lr:6.355661424119905e-05 tokens_per_second_per_gpu:2143.6563712202083 
Step 5021 | loss:2.12143611907959 lr:6.351997449015418e-05 tokens_per_second_per_gpu:2217.28903624931 
Step 5022 | loss:2.0949056148529053 lr:6.34833403873581e-05 tokens_per_second_per_gpu:2215.3007434445776 
Step 5023 | loss:2.0602879524230957 lr:6.34467119384829e-05 tokens_per_second_per_gpu:2188.169399284214 
Step 5024 | loss:2.0667755603790283 lr:6.341008914919979e-05 tokens_per_second_per_gpu:2189.7977598501184 
Step 5025 | loss:2.032453775405884 lr:6.337347202517911e-05 tokens_per_second_per_gpu:2211.3481891349993 
Step 5026 | loss:2.1056785583496094 lr:6.33368605720904e-05 tokens_per_second_per_gpu:2229.1182314975654 
Step 5027 | loss:2.0629701614379883 lr:6.330025479560223e-05 tokens_per_second_per_gpu:2234.098711999744 
Step 5028 | loss:2.075244426727295 lr:6.326365470138231e-05 tokens_per_second_per_gpu:2177.837683846137 
Step 5029 | loss:2.1327970027923584 lr:6.322706029509746e-05 tokens_per_second_per_gpu:2230.0748529761368 
Step 5030 | loss:2.0817604064941406 lr:6.319047158241367e-05 tokens_per_second_per_gpu:2151.2510479438006 
Step 5031 | loss:2.0764667987823486 lr:6.3153888568996e-05 tokens_per_second_per_gpu:2226.3010025572853 
Step 5032 | loss:2.0752744674682617 lr:6.311731126050866e-05 tokens_per_second_per_gpu:2226.0462087158685 
Step 5033 | loss:2.0631492137908936 lr:6.308073966261496e-05 tokens_per_second_per_gpu:2216.598334527253 
Step 5034 | loss:2.096248149871826 lr:6.304417378097731e-05 tokens_per_second_per_gpu:2218.7802038024906 
Step 5035 | loss:2.115469455718994 lr:6.300761362125727e-05 tokens_per_second_per_gpu:2229.7639508286115 
Step 5036 | loss:2.1156015396118164 lr:6.297105918911545e-05 tokens_per_second_per_gpu:2230.6549377482347 
Step 5037 | loss:2.0802226066589355 lr:6.293451049021168e-05 tokens_per_second_per_gpu:2227.1079462395796 
Step 5038 | loss:2.073458194732666 lr:6.289796753020484e-05 tokens_per_second_per_gpu:2223.4288587156584 
Step 5039 | loss:2.0566906929016113 lr:6.286143031475289e-05 tokens_per_second_per_gpu:2078.8066262281795 
Step 5040 | loss:2.0869693756103516 lr:6.282489884951295e-05 tokens_per_second_per_gpu:2230.2022974954484 
Step 5041 | loss:2.0753774642944336 lr:6.278837314014119e-05 tokens_per_second_per_gpu:2204.5832689746735 
Step 5042 | loss:2.1183815002441406 lr:6.2751853192293e-05 tokens_per_second_per_gpu:2218.7194464473137 
Step 5043 | loss:2.0369303226470947 lr:6.271533901162278e-05 tokens_per_second_per_gpu:2177.42582034506 
Step 5044 | loss:2.0530025959014893 lr:6.267883060378409e-05 tokens_per_second_per_gpu:2182.41608185683 
Step 5045 | loss:2.048332691192627 lr:6.264232797442952e-05 tokens_per_second_per_gpu:2236.3881555319313 
Step 5046 | loss:2.0778937339782715 lr:6.260583112921082e-05 tokens_per_second_per_gpu:2226.4439476508264 
Step 5047 | loss:2.059938907623291 lr:6.256934007377893e-05 tokens_per_second_per_gpu:2190.9641245526 
Step 5048 | loss:2.073617458343506 lr:6.253285481378371e-05 tokens_per_second_per_gpu:2191.3476633057035 
Step 5049 | loss:2.0650205612182617 lr:6.249637535487429e-05 tokens_per_second_per_gpu:2231.0202525275117 
Step 5050 | loss:2.0872082710266113 lr:6.24599017026988e-05 tokens_per_second_per_gpu:2227.579895167095 
Step 5051 | loss:2.1218364238739014 lr:6.242343386290447e-05 tokens_per_second_per_gpu:2231.691477816681 
Step 5052 | loss:2.086167335510254 lr:6.238697184113768e-05 tokens_per_second_per_gpu:2216.1646289137557 
Step 5053 | loss:2.077711582183838 lr:6.235051564304395e-05 tokens_per_second_per_gpu:2161.6745913432956 
Step 5054 | loss:2.115490436553955 lr:6.231406527426776e-05 tokens_per_second_per_gpu:2231.634693699541 
Step 5055 | loss:2.061091661453247 lr:6.227762074045283e-05 tokens_per_second_per_gpu:2203.3658557602353 
Step 5056 | loss:2.076244354248047 lr:6.224118204724185e-05 tokens_per_second_per_gpu:2219.0088875810766 
Step 5057 | loss:2.1053695678710938 lr:6.220474920027673e-05 tokens_per_second_per_gpu:2207.026684033858 
Step 5058 | loss:2.093994617462158 lr:6.216832220519837e-05 tokens_per_second_per_gpu:2165.3298041765042 
Step 5059 | loss:2.0412955284118652 lr:6.213190106764684e-05 tokens_per_second_per_gpu:2223.167472879576 
Step 5060 | loss:2.1001265048980713 lr:6.209548579326126e-05 tokens_per_second_per_gpu:2160.8596748929467 
Step 5061 | loss:2.0468368530273438 lr:6.205907638767984e-05 tokens_per_second_per_gpu:2235.2866955630466 
Step 5062 | loss:2.1154422760009766 lr:6.202267285653988e-05 tokens_per_second_per_gpu:2224.3024762615532 
Step 5063 | loss:2.112921953201294 lr:6.198627520547782e-05 tokens_per_second_per_gpu:2229.2225336784954 
Step 5064 | loss:2.095979690551758 lr:6.194988344012917e-05 tokens_per_second_per_gpu:2184.6420658815573 
Step 5065 | loss:2.1120080947875977 lr:6.191349756612849e-05 tokens_per_second_per_gpu:2205.4410721873983 
Step 5066 | loss:2.0984349250793457 lr:6.187711758910943e-05 tokens_per_second_per_gpu:2170.7374734384744 
Step 5067 | loss:2.0954668521881104 lr:6.184074351470479e-05 tokens_per_second_per_gpu:2213.7747568719624 
Step 5068 | loss:2.096726417541504 lr:6.180437534854635e-05 tokens_per_second_per_gpu:2231.546750843411 
Step 5069 | loss:2.080383539199829 lr:6.176801309626508e-05 tokens_per_second_per_gpu:2220.7144759655584 
Step 5070 | loss:2.057236671447754 lr:6.173165676349103e-05 tokens_per_second_per_gpu:2232.742360774628 
Step 5071 | loss:2.036896228790283 lr:6.169530635585327e-05 tokens_per_second_per_gpu:2228.3875952305475 
Step 5072 | loss:2.089850902557373 lr:6.165896187897993e-05 tokens_per_second_per_gpu:2222.2802825167 
Step 5073 | loss:2.0221571922302246 lr:6.16226233384983e-05 tokens_per_second_per_gpu:2199.5703425303395 
Step 5074 | loss:2.078263521194458 lr:6.158629074003479e-05 tokens_per_second_per_gpu:2208.2741774448873 
Step 5075 | loss:2.0788378715515137 lr:6.154996408921474e-05 tokens_per_second_per_gpu:2169.3279298585862 
Step 5076 | loss:2.1057348251342773 lr:6.15136433916627e-05 tokens_per_second_per_gpu:2224.925793664979 
Step 5077 | loss:2.0802512168884277 lr:6.147732865300221e-05 tokens_per_second_per_gpu:2229.551795067841 
Step 5078 | loss:2.0221996307373047 lr:6.144101987885595e-05 tokens_per_second_per_gpu:2231.131791998199 
Step 5079 | loss:2.072345733642578 lr:6.140471707484563e-05 tokens_per_second_per_gpu:2231.558357216803 
Step 5080 | loss:2.108398675918579 lr:6.136842024659211e-05 tokens_per_second_per_gpu:2171.814617133876 
Step 5081 | loss:2.0549864768981934 lr:6.133212939971521e-05 tokens_per_second_per_gpu:2218.9117671606186 
Step 5082 | loss:2.042532205581665 lr:6.129584453983397e-05 tokens_per_second_per_gpu:2192.0260373661145 
Step 5083 | loss:2.040160655975342 lr:6.125956567256634e-05 tokens_per_second_per_gpu:2217.8828230872464 
Step 5084 | loss:2.150341510772705 lr:6.122329280352945e-05 tokens_per_second_per_gpu:2171.108683330157 
Step 5085 | loss:2.074306011199951 lr:6.11870259383395e-05 tokens_per_second_per_gpu:2216.94195818482 
Step 5086 | loss:2.053129196166992 lr:6.115076508261171e-05 tokens_per_second_per_gpu:2188.502777404897 
Step 5087 | loss:2.142547130584717 lr:6.11145102419604e-05 tokens_per_second_per_gpu:2226.4778633019173 
Step 5088 | loss:2.070744037628174 lr:6.107826142199894e-05 tokens_per_second_per_gpu:2224.5716717354776 
Step 5089 | loss:2.0846269130706787 lr:6.104201862833979e-05 tokens_per_second_per_gpu:2218.482077108372 
Step 5090 | loss:2.078230857849121 lr:6.100578186659448e-05 tokens_per_second_per_gpu:2125.4030192954706 
Step 5091 | loss:2.0694990158081055 lr:6.0969551142373607e-05 tokens_per_second_per_gpu:2225.3773737640513 
Step 5092 | loss:2.1527457237243652 lr:6.09333264612868e-05 tokens_per_second_per_gpu:2152.8240542857807 
Step 5093 | loss:2.107581853866577 lr:6.089710782894273e-05 tokens_per_second_per_gpu:2150.8584816268053 
Step 5094 | loss:2.056150436401367 lr:6.086089525094926e-05 tokens_per_second_per_gpu:2198.835898434536 
Step 5095 | loss:2.1291539669036865 lr:6.0824688732913134e-05 tokens_per_second_per_gpu:2221.410142839294 
Step 5096 | loss:2.0483546257019043 lr:6.0788488280440327e-05 tokens_per_second_per_gpu:2228.2339959767746 
Step 5097 | loss:2.097971200942993 lr:6.075229389913579e-05 tokens_per_second_per_gpu:2202.410077287585 
Step 5098 | loss:2.0942020416259766 lr:6.071610559460354e-05 tokens_per_second_per_gpu:2193.4275959071283 
Step 5099 | loss:2.1292495727539062 lr:6.067992337244663e-05 tokens_per_second_per_gpu:2177.37159128202 
Step 5100 | loss:2.115736484527588 lr:6.06437472382672e-05 tokens_per_second_per_gpu:2172.2746284787895 
Step 5101 | loss:2.068136692047119 lr:6.060757719766651e-05 tokens_per_second_per_gpu:2223.2533309638784 
Step 5102 | loss:2.101968765258789 lr:6.0571413256244756e-05 tokens_per_second_per_gpu:2211.659263319845 
Step 5103 | loss:2.0758824348449707 lr:6.053525541960128e-05 tokens_per_second_per_gpu:2132.250755022762 
Step 5104 | loss:2.1061885356903076 lr:6.0499103693334414e-05 tokens_per_second_per_gpu:2174.7758190733175 
Step 5105 | loss:2.0960850715637207 lr:6.0462958083041564e-05 tokens_per_second_per_gpu:2225.0847382949823 
Step 5106 | loss:2.039332866668701 lr:6.0426818594319236e-05 tokens_per_second_per_gpu:2198.94609829161 
Step 5107 | loss:2.043776035308838 lr:6.039068523276297e-05 tokens_per_second_per_gpu:2226.5644142599162 
Step 5108 | loss:2.0921316146850586 lr:6.03545580039673e-05 tokens_per_second_per_gpu:2134.3999451244385 
Step 5109 | loss:2.0470821857452393 lr:6.031843691352588e-05 tokens_per_second_per_gpu:2221.0214058536067 
Step 5110 | loss:2.1280603408813477 lr:6.028232196703134e-05 tokens_per_second_per_gpu:2213.862324554093 
Step 5111 | loss:2.0800535678863525 lr:6.0246213170075435e-05 tokens_per_second_per_gpu:2225.4750021746477 
Step 5112 | loss:2.0877392292022705 lr:6.021011052824894e-05 tokens_per_second_per_gpu:2220.793190325439 
Step 5113 | loss:2.087111711502075 lr:6.017401404714169e-05 tokens_per_second_per_gpu:2164.1673138618216 
Step 5114 | loss:2.0488719940185547 lr:6.013792373234249e-05 tokens_per_second_per_gpu:2179.0299846668645 
Step 5115 | loss:2.0579707622528076 lr:6.010183958943931e-05 tokens_per_second_per_gpu:2108.751499804858 
Step 5116 | loss:2.0559310913085938 lr:6.006576162401905e-05 tokens_per_second_per_gpu:2186.5140701341757 
Step 5117 | loss:2.070939779281616 lr:6.002968984166775e-05 tokens_per_second_per_gpu:2188.318920783951 
Step 5118 | loss:2.11759352684021 lr:5.999362424797046e-05 tokens_per_second_per_gpu:2207.073952358363 
Step 5119 | loss:2.015164852142334 lr:5.995756484851123e-05 tokens_per_second_per_gpu:2215.1929322391898 
Step 5120 | loss:2.058398962020874 lr:5.992151164887316e-05 tokens_per_second_per_gpu:2221.80064886777 
Step 5121 | loss:2.092528820037842 lr:5.988546465463845e-05 tokens_per_second_per_gpu:2217.3129390498684 
Step 5122 | loss:2.0704922676086426 lr:5.984942387138831e-05 tokens_per_second_per_gpu:2223.445741131447 
Step 5123 | loss:2.0999841690063477 lr:5.981338930470295e-05 tokens_per_second_per_gpu:2192.329496264169 
Step 5124 | loss:2.0836548805236816 lr:5.977736096016169e-05 tokens_per_second_per_gpu:2181.9363900516432 
Step 5125 | loss:2.080733060836792 lr:5.974133884334282e-05 tokens_per_second_per_gpu:2127.488186659786 
Step 5126 | loss:2.0833845138549805 lr:5.9705322959823664e-05 tokens_per_second_per_gpu:2185.485874736013 
Step 5127 | loss:2.074216842651367 lr:5.966931331518061e-05 tokens_per_second_per_gpu:2219.9508847867305 
Step 5128 | loss:2.085857391357422 lr:5.963330991498914e-05 tokens_per_second_per_gpu:2136.04474643191 
Step 5129 | loss:2.003376007080078 lr:5.9597312764823635e-05 tokens_per_second_per_gpu:2212.763243786372 
Step 5130 | loss:2.050002098083496 lr:5.956132187025765e-05 tokens_per_second_per_gpu:2207.3376284085 
Step 5131 | loss:2.0813488960266113 lr:5.952533723686364e-05 tokens_per_second_per_gpu:2228.6451398426734 
Step 5132 | loss:2.0580694675445557 lr:5.948935887021314e-05 tokens_per_second_per_gpu:2214.5844686356763 
Step 5133 | loss:2.14853572845459 lr:5.9453386775876776e-05 tokens_per_second_per_gpu:2180.983982520834 
Step 5134 | loss:2.133974075317383 lr:5.9417420959424156e-05 tokens_per_second_per_gpu:2204.150111775536 
Step 5135 | loss:2.047024726867676 lr:5.938146142642386e-05 tokens_per_second_per_gpu:2218.6831454963617 
Step 5136 | loss:2.09722900390625 lr:5.934550818244361e-05 tokens_per_second_per_gpu:2221.9935086377936 
Step 5137 | loss:2.0795440673828125 lr:5.930956123305006e-05 tokens_per_second_per_gpu:2171.8987372916736 
Step 5138 | loss:2.063192129135132 lr:5.927362058380889e-05 tokens_per_second_per_gpu:2219.2140438817187 
Step 5139 | loss:2.1044886112213135 lr:5.923768624028488e-05 tokens_per_second_per_gpu:2181.026846895814 
Step 5140 | loss:2.0676865577697754 lr:5.920175820804181e-05 tokens_per_second_per_gpu:2194.6647415466437 
Step 5141 | loss:2.0996270179748535 lr:5.9165836492642426e-05 tokens_per_second_per_gpu:2227.2458043919382 
Step 5142 | loss:2.075059175491333 lr:5.912992109964854e-05 tokens_per_second_per_gpu:2208.1615755636276 
Step 5143 | loss:2.09304141998291 lr:5.909401203462095e-05 tokens_per_second_per_gpu:2215.794563144686 
Step 5144 | loss:2.081573247909546 lr:5.9058109303119543e-05 tokens_per_second_per_gpu:2199.743207125049 
Step 5145 | loss:2.076892375946045 lr:5.90222129107032e-05 tokens_per_second_per_gpu:2192.9854620650854 
Step 5146 | loss:2.083454132080078 lr:5.898632286292978e-05 tokens_per_second_per_gpu:2176.4325028827893 
Step 5147 | loss:2.0866987705230713 lr:5.895043916535616e-05 tokens_per_second_per_gpu:2217.0769857651812 
Step 5148 | loss:2.075347423553467 lr:5.891456182353825e-05 tokens_per_second_per_gpu:2191.904685767517 
Step 5149 | loss:2.116832971572876 lr:5.8878690843031084e-05 tokens_per_second_per_gpu:2216.7246944600865 
Step 5150 | loss:2.09771728515625 lr:5.884282622938849e-05 tokens_per_second_per_gpu:2154.1345085919843 
Step 5151 | loss:1.9945425987243652 lr:5.880696798816352e-05 tokens_per_second_per_gpu:2226.6563385911936 
Step 5152 | loss:2.1001996994018555 lr:5.877111612490812e-05 tokens_per_second_per_gpu:2196.47305632839 
Step 5153 | loss:2.086186647415161 lr:5.873527064517326e-05 tokens_per_second_per_gpu:2173.28123207461 
Step 5154 | loss:2.050632953643799 lr:5.869943155450892e-05 tokens_per_second_per_gpu:2225.39451819318 
Step 5155 | loss:2.1032586097717285 lr:5.8663598858464205e-05 tokens_per_second_per_gpu:2170.1635445141237 
Step 5156 | loss:2.1241750717163086 lr:5.862777256258706e-05 tokens_per_second_per_gpu:2160.9912472005135 
Step 5157 | loss:2.1395106315612793 lr:5.8591952672424545e-05 tokens_per_second_per_gpu:2102.736156851241 
Step 5158 | loss:2.1421728134155273 lr:5.8556139193522695e-05 tokens_per_second_per_gpu:2219.8359473824885 
Step 5159 | loss:2.066310405731201 lr:5.8520332131426523e-05 tokens_per_second_per_gpu:2227.5778187238593 
Step 5160 | loss:2.0794379711151123 lr:5.8484531491680126e-05 tokens_per_second_per_gpu:2197.3038203297024 
Step 5161 | loss:2.0655813217163086 lr:5.844873727982656e-05 tokens_per_second_per_gpu:2211.164411767802 
Step 5162 | loss:2.0831408500671387 lr:5.8412949501407874e-05 tokens_per_second_per_gpu:2174.1878959914475 
Step 5163 | loss:2.026064395904541 lr:5.837716816196515e-05 tokens_per_second_per_gpu:2224.309149702662 
Step 5164 | loss:2.115673780441284 lr:5.834139326703838e-05 tokens_per_second_per_gpu:2148.397209154918 
Step 5165 | loss:2.019374370574951 lr:5.8305624822166796e-05 tokens_per_second_per_gpu:2191.5427651542623 
Step 5166 | loss:2.110309362411499 lr:5.826986283288832e-05 tokens_per_second_per_gpu:2222.8783712834847 
Step 5167 | loss:2.057588577270508 lr:5.8234107304740104e-05 tokens_per_second_per_gpu:2220.4610496588484 
Step 5168 | loss:2.151205539703369 lr:5.8198358243258233e-05 tokens_per_second_per_gpu:2198.1413882027628 
Step 5169 | loss:2.085305690765381 lr:5.8162615653977705e-05 tokens_per_second_per_gpu:2164.5623512080547 
Step 5170 | loss:2.062842607498169 lr:5.81268795424326e-05 tokens_per_second_per_gpu:2150.195867694529 
Step 5171 | loss:2.066378593444824 lr:5.80911499141561e-05 tokens_per_second_per_gpu:2227.4043901735654 
Step 5172 | loss:2.0622105598449707 lr:5.805542677468014e-05 tokens_per_second_per_gpu:2166.1901242646372 
Step 5173 | loss:2.0125699043273926 lr:5.8019710129535844e-05 tokens_per_second_per_gpu:2224.063349736574 
Step 5174 | loss:2.044586181640625 lr:5.798399998425329e-05 tokens_per_second_per_gpu:2209.400043405144 
Step 5175 | loss:2.0883798599243164 lr:5.7948296344361405e-05 tokens_per_second_per_gpu:2183.239607475249 
Step 5176 | loss:2.054112434387207 lr:5.791259921538834e-05 tokens_per_second_per_gpu:2211.9686949601164 
Step 5177 | loss:2.0837647914886475 lr:5.787690860286115e-05 tokens_per_second_per_gpu:2202.470676575976 
Step 5178 | loss:2.0733304023742676 lr:5.784122451230576e-05 tokens_per_second_per_gpu:2183.4190471382744 
Step 5179 | loss:2.0873780250549316 lr:5.7805546949247225e-05 tokens_per_second_per_gpu:2192.026594679715 
Step 5180 | loss:2.0080955028533936 lr:5.776987591920955e-05 tokens_per_second_per_gpu:2220.731875883249 
Step 5181 | loss:2.071981906890869 lr:5.7734211427715714e-05 tokens_per_second_per_gpu:2186.40335774278 
Step 5182 | loss:2.069983959197998 lr:5.769855348028772e-05 tokens_per_second_per_gpu:2142.0180869502187 
Step 5183 | loss:2.02401065826416 lr:5.766290208244656e-05 tokens_per_second_per_gpu:2223.9466336527566 
Step 5184 | loss:2.0612268447875977 lr:5.762725723971212e-05 tokens_per_second_per_gpu:2168.1828157248815 
Step 5185 | loss:2.0674915313720703 lr:5.759161895760334e-05 tokens_per_second_per_gpu:2157.714967379023 
Step 5186 | loss:2.0897045135498047 lr:5.755598724163818e-05 tokens_per_second_per_gpu:2220.90336308076 
Step 5187 | loss:2.0479068756103516 lr:5.752036209733351e-05 tokens_per_second_per_gpu:2181.9688677758295 
Step 5188 | loss:2.0502545833587646 lr:5.748474353020524e-05 tokens_per_second_per_gpu:2185.335557923325 
Step 5189 | loss:2.1407828330993652 lr:5.7449131545768275e-05 tokens_per_second_per_gpu:2192.6504176395383 
Step 5190 | loss:2.1250314712524414 lr:5.741352614953639e-05 tokens_per_second_per_gpu:2178.406752274972 
Step 5191 | loss:2.112600326538086 lr:5.7377927347022384e-05 tokens_per_second_per_gpu:2217.5366001573984 
Step 5192 | loss:2.044335126876831 lr:5.734233514373822e-05 tokens_per_second_per_gpu:2224.0559893262107 
Step 5193 | loss:2.131188154220581 lr:5.730674954519455e-05 tokens_per_second_per_gpu:2216.008981795932 
Step 5194 | loss:2.0915215015411377 lr:5.7271170556901164e-05 tokens_per_second_per_gpu:2233.8970461199924 
Step 5195 | loss:2.0539703369140625 lr:5.723559818436688e-05 tokens_per_second_per_gpu:2228.1715571675095 
Step 5196 | loss:2.0017666816711426 lr:5.7200032433099285e-05 tokens_per_second_per_gpu:2230.4940729699133 
Step 5197 | loss:2.1050407886505127 lr:5.71644733086051e-05 tokens_per_second_per_gpu:2219.399180986608 
Step 5198 | loss:2.015260934829712 lr:5.7128920816390096e-05 tokens_per_second_per_gpu:2169.001389349053 
Step 5199 | loss:2.095028877258301 lr:5.709337496195881e-05 tokens_per_second_per_gpu:2095.9113854388174 
Step 5200 | loss:2.051145315170288 lr:5.7057835750814867e-05 tokens_per_second_per_gpu:2219.1898150771913 
Step 5201 | loss:2.0881874561309814 lr:5.7022303188460913e-05 tokens_per_second_per_gpu:2215.8142341260473 
Step 5202 | loss:2.1315133571624756 lr:5.698677728039836e-05 tokens_per_second_per_gpu:2193.989943870239 
Step 5203 | loss:2.077404737472534 lr:5.695125803212786e-05 tokens_per_second_per_gpu:2204.905494555075 
Step 5204 | loss:2.0548720359802246 lr:5.6915745449148894e-05 tokens_per_second_per_gpu:2177.539153715449 
Step 5205 | loss:2.0960192680358887 lr:5.6880239536959845e-05 tokens_per_second_per_gpu:2200.4258436882265 
Step 5206 | loss:2.069540023803711 lr:5.6844740301058194e-05 tokens_per_second_per_gpu:2215.8237398016495 
Step 5207 | loss:2.0308101177215576 lr:5.680924774694031e-05 tokens_per_second_per_gpu:2218.251294504424 
Step 5208 | loss:2.1056370735168457 lr:5.677376188010156e-05 tokens_per_second_per_gpu:2204.3526002885333 
Step 5209 | loss:2.0228261947631836 lr:5.673828270603627e-05 tokens_per_second_per_gpu:2144.398559155233 
Step 5210 | loss:2.0482726097106934 lr:5.6702810230237754e-05 tokens_per_second_per_gpu:2185.1533629910155 
Step 5211 | loss:2.064404010772705 lr:5.666734445819819e-05 tokens_per_second_per_gpu:2199.582104790644 
Step 5212 | loss:2.1313962936401367 lr:5.6631885395408825e-05 tokens_per_second_per_gpu:2152.5986004712654 
Step 5213 | loss:2.093327760696411 lr:5.659643304735983e-05 tokens_per_second_per_gpu:2169.733279259106 
Step 5214 | loss:2.023090124130249 lr:5.6560987419540346e-05 tokens_per_second_per_gpu:2224.258847879405 
Step 5215 | loss:2.0316686630249023 lr:5.652554851743845e-05 tokens_per_second_per_gpu:2175.0531917154276 
Step 5216 | loss:2.0818324089050293 lr:5.6490116346541243e-05 tokens_per_second_per_gpu:2134.2411735240366 
Step 5217 | loss:2.1492481231689453 lr:5.645469091233466e-05 tokens_per_second_per_gpu:2223.039088863535 
Step 5218 | loss:2.0413758754730225 lr:5.641927222030364e-05 tokens_per_second_per_gpu:2194.7702608523514 
Step 5219 | loss:2.0922794342041016 lr:5.6383860275932256e-05 tokens_per_second_per_gpu:2086.3857764615864 
Step 5220 | loss:2.0982234477996826 lr:5.6348455084703235e-05 tokens_per_second_per_gpu:2167.6431173983647 
Step 5221 | loss:2.088198184967041 lr:5.631305665209847e-05 tokens_per_second_per_gpu:2193.6870229245637 
Step 5222 | loss:2.067391872406006 lr:5.6277664983598775e-05 tokens_per_second_per_gpu:2182.653644076626 
Step 5223 | loss:2.023705005645752 lr:5.624228008468377e-05 tokens_per_second_per_gpu:2096.6362215059094 
Step 5224 | loss:2.0233728885650635 lr:5.620690196083227e-05 tokens_per_second_per_gpu:2143.5182430344225 
Step 5225 | loss:2.0841128826141357 lr:5.6171530617521894e-05 tokens_per_second_per_gpu:2225.13669116838 
Step 5226 | loss:2.0575671195983887 lr:5.613616606022918e-05 tokens_per_second_per_gpu:2215.509469531768 
Step 5227 | loss:2.131099224090576 lr:5.6100808294429674e-05 tokens_per_second_per_gpu:2161.267488382423 
Step 5228 | loss:2.0876224040985107 lr:5.6065457325597936e-05 tokens_per_second_per_gpu:2200.462695775005 
Step 5229 | loss:2.0938422679901123 lr:5.6030113159207276e-05 tokens_per_second_per_gpu:2224.055713860381 
Step 5230 | loss:2.0755040645599365 lr:5.599477580073018e-05 tokens_per_second_per_gpu:2226.9425485285906 
Step 5231 | loss:2.12312912940979 lr:5.595944525563799e-05 tokens_per_second_per_gpu:2222.9386271971257 
Step 5232 | loss:2.1059978008270264 lr:5.592412152940088e-05 tokens_per_second_per_gpu:2112.0382252171285 
Step 5233 | loss:2.041444778442383 lr:5.588880462748814e-05 tokens_per_second_per_gpu:2207.768451219088 
Step 5234 | loss:2.0814285278320312 lr:5.58534945553679e-05 tokens_per_second_per_gpu:2199.257915813641 
Step 5235 | loss:2.0997707843780518 lr:5.581819131850729e-05 tokens_per_second_per_gpu:2207.775505851177 
Step 5236 | loss:2.105966567993164 lr:5.578289492237232e-05 tokens_per_second_per_gpu:2161.486539082839 
Step 5237 | loss:2.081709384918213 lr:5.5747605372428056e-05 tokens_per_second_per_gpu:2210.978647563151 
Step 5238 | loss:2.0547921657562256 lr:5.571232267413833e-05 tokens_per_second_per_gpu:2200.558764902666 
Step 5239 | loss:2.081207513809204 lr:5.5677046832966015e-05 tokens_per_second_per_gpu:2214.5484273451807 
Step 5240 | loss:2.0730526447296143 lr:5.5641777854372966e-05 tokens_per_second_per_gpu:2069.298084617775 
Step 5241 | loss:2.0627822875976562 lr:5.56065157438199e-05 tokens_per_second_per_gpu:2218.5408455537927 
Step 5242 | loss:2.083329200744629 lr:5.557126050676649e-05 tokens_per_second_per_gpu:2169.82406485756 
Step 5243 | loss:2.0779643058776855 lr:5.5536012148671376e-05 tokens_per_second_per_gpu:2227.9092697711812 
Step 5244 | loss:2.0628719329833984 lr:5.5500770674992065e-05 tokens_per_second_per_gpu:2140.266580095584 
Step 5245 | loss:2.0818049907684326 lr:5.546553609118501e-05 tokens_per_second_per_gpu:2214.8893098582653 
Step 5246 | loss:2.1221816539764404 lr:5.5430308402705754e-05 tokens_per_second_per_gpu:2191.3537458863293 
Step 5247 | loss:2.0800323486328125 lr:5.539508761500851e-05 tokens_per_second_per_gpu:2208.8731321167097 
Step 5248 | loss:2.0824391841888428 lr:5.535987373354663e-05 tokens_per_second_per_gpu:2228.5070311404334 
Step 5249 | loss:2.0662355422973633 lr:5.532466676377235e-05 tokens_per_second_per_gpu:2210.3638376296467 
Step 5250 | loss:2.0387048721313477 lr:5.528946671113668e-05 tokens_per_second_per_gpu:2220.8873284156575 
Step 5251 | loss:2.040360927581787 lr:5.525427358108981e-05 tokens_per_second_per_gpu:2206.1775145135025 
Step 5252 | loss:2.096813917160034 lr:5.5219087379080745e-05 tokens_per_second_per_gpu:2208.2217413610456 
Step 5253 | loss:2.061696767807007 lr:5.5183908110557336e-05 tokens_per_second_per_gpu:2217.066243257582 
Step 5254 | loss:2.0646262168884277 lr:5.5148735780966456e-05 tokens_per_second_per_gpu:2206.110557900827 
Step 5255 | loss:2.0337648391723633 lr:5.511357039575393e-05 tokens_per_second_per_gpu:2202.048327567865 
Step 5256 | loss:2.077836751937866 lr:5.507841196036434e-05 tokens_per_second_per_gpu:2226.8002915571165 
Step 5257 | loss:2.0528199672698975 lr:5.504326048024142e-05 tokens_per_second_per_gpu:2213.1288214334427 
Step 5258 | loss:2.0777246952056885 lr:5.500811596082776e-05 tokens_per_second_per_gpu:2195.4461784450896 
Step 5259 | loss:2.0481886863708496 lr:5.497297840756469e-05 tokens_per_second_per_gpu:2201.064684125718 
Step 5260 | loss:2.064387798309326 lr:5.493784782589269e-05 tokens_per_second_per_gpu:2228.0373873746316 
Step 5261 | loss:2.0234742164611816 lr:5.490272422125105e-05 tokens_per_second_per_gpu:2182.013121634892 
Step 5262 | loss:2.063220500946045 lr:5.4867607599077986e-05 tokens_per_second_per_gpu:2180.6643828008423 
Step 5263 | loss:2.063455104827881 lr:5.483249796481069e-05 tokens_per_second_per_gpu:2226.559754331383 
Step 5264 | loss:2.096583127975464 lr:5.479739532388526e-05 tokens_per_second_per_gpu:2230.973794851308 
Step 5265 | loss:2.0973222255706787 lr:5.476229968173658e-05 tokens_per_second_per_gpu:2218.2912815414606 
Step 5266 | loss:2.063026189804077 lr:5.4727211043798566e-05 tokens_per_second_per_gpu:2179.1478014083586 
Step 5267 | loss:2.10237717628479 lr:5.469212941550417e-05 tokens_per_second_per_gpu:2227.6214438944585 
Step 5268 | loss:2.0863730907440186 lr:5.465705480228498e-05 tokens_per_second_per_gpu:2176.0136338287116 
Step 5269 | loss:2.078690528869629 lr:5.4621987209571704e-05 tokens_per_second_per_gpu:2215.8900210877773 
Step 5270 | loss:2.0641260147094727 lr:5.458692664279393e-05 tokens_per_second_per_gpu:2200.1073888248807 
Step 5271 | loss:2.0168991088867188 lr:5.4551873107380055e-05 tokens_per_second_per_gpu:2205.4818397957524 
Step 5272 | loss:2.0713987350463867 lr:5.451682660875747e-05 tokens_per_second_per_gpu:2173.7097633442713 
Step 5273 | loss:2.0714688301086426 lr:5.448178715235257e-05 tokens_per_second_per_gpu:2204.6563817502547 
Step 5274 | loss:2.0562400817871094 lr:5.444675474359045e-05 tokens_per_second_per_gpu:2185.0977412013463 
Step 5275 | loss:2.067723512649536 lr:5.441172938789526e-05 tokens_per_second_per_gpu:2182.8365392732417 
Step 5276 | loss:2.063110828399658 lr:5.437671109069007e-05 tokens_per_second_per_gpu:2129.7644072303656 
Step 5277 | loss:2.163189649581909 lr:5.4341699857396665e-05 tokens_per_second_per_gpu:2185.092892324301 
Step 5278 | loss:2.0649118423461914 lr:5.4306695693436024e-05 tokens_per_second_per_gpu:2167.405953396865 
Step 5279 | loss:2.077949285507202 lr:5.4271698604227875e-05 tokens_per_second_per_gpu:2226.764101190337 
Step 5280 | loss:2.072175979614258 lr:5.423670859519079e-05 tokens_per_second_per_gpu:2199.927238504776 
Step 5281 | loss:2.1260318756103516 lr:5.420172567174233e-05 tokens_per_second_per_gpu:2166.732836668183 
Step 5282 | loss:2.07719349861145 lr:5.416674983929897e-05 tokens_per_second_per_gpu:2169.6116504000524 
Step 5283 | loss:2.10408878326416 lr:5.413178110327607e-05 tokens_per_second_per_gpu:2222.446611159637 
Step 5284 | loss:2.0629303455352783 lr:5.409681946908787e-05 tokens_per_second_per_gpu:2181.98966188459 
Step 5285 | loss:2.0846176147460938 lr:5.4061864942147544e-05 tokens_per_second_per_gpu:2177.002338116778 
Step 5286 | loss:2.051882028579712 lr:5.402691752786711e-05 tokens_per_second_per_gpu:2145.5938919825976 
Step 5287 | loss:2.0148861408233643 lr:5.399197723165752e-05 tokens_per_second_per_gpu:2189.9681176407066 
Step 5288 | loss:2.0755300521850586 lr:5.395704405892865e-05 tokens_per_second_per_gpu:2217.8838202311017 
Step 5289 | loss:2.1366281509399414 lr:5.392211801508924e-05 tokens_per_second_per_gpu:2219.197005957309 
Step 5290 | loss:2.096729278564453 lr:5.388719910554694e-05 tokens_per_second_per_gpu:2216.272936661302 
Step 5291 | loss:2.151679039001465 lr:5.385228733570832e-05 tokens_per_second_per_gpu:2148.9223512369445 
Step 5292 | loss:2.0844945907592773 lr:5.3817382710978736e-05 tokens_per_second_per_gpu:2191.626144314309 
Step 5293 | loss:2.0050721168518066 lr:5.378248523676255e-05 tokens_per_second_per_gpu:2165.9120310015405 
Step 5294 | loss:2.08836030960083 lr:5.3747594918462996e-05 tokens_per_second_per_gpu:2195.460223137051 
Step 5295 | loss:2.0996782779693604 lr:5.371271176148218e-05 tokens_per_second_per_gpu:2179.4042794243965 
Step 5296 | loss:2.0640954971313477 lr:5.36778357712211e-05 tokens_per_second_per_gpu:2180.03757988662 
Step 5297 | loss:2.0442323684692383 lr:5.3642966953079685e-05 tokens_per_second_per_gpu:2104.526965515469 
Step 5298 | loss:2.1219825744628906 lr:5.360810531245666e-05 tokens_per_second_per_gpu:2179.323930039541 
Step 5299 | loss:2.081124782562256 lr:5.357325085474969e-05 tokens_per_second_per_gpu:2170.742832000787 
Step 5300 | loss:2.068012237548828 lr:5.3538403585355444e-05 tokens_per_second_per_gpu:2156.72853283098 
Step 5301 | loss:2.1030163764953613 lr:5.350356350966925e-05 tokens_per_second_per_gpu:2201.0409257511133 
Step 5302 | loss:2.126201629638672 lr:5.34687306330855e-05 tokens_per_second_per_gpu:2211.109593706022 
Step 5303 | loss:2.053292989730835 lr:5.343390496099743e-05 tokens_per_second_per_gpu:2211.9375202191195 
Step 5304 | loss:2.066661834716797 lr:5.339908649879704e-05 tokens_per_second_per_gpu:2168.5531416342114 
Step 5305 | loss:1.99906325340271 lr:5.3364275251875416e-05 tokens_per_second_per_gpu:2208.3841223643785 
Step 5306 | loss:2.055941104888916 lr:5.332947122562244e-05 tokens_per_second_per_gpu:2192.3077497825248 
Step 5307 | loss:1.946938395500183 lr:5.3294674425426796e-05 tokens_per_second_per_gpu:2222.580195103479 
Step 5308 | loss:2.140774965286255 lr:5.325988485667614e-05 tokens_per_second_per_gpu:2188.094784586614 
Step 5309 | loss:2.0780792236328125 lr:5.322510252475699e-05 tokens_per_second_per_gpu:2166.7163757426592 
Step 5310 | loss:2.065094470977783 lr:5.3190327435054735e-05 tokens_per_second_per_gpu:2183.7415083932206 
Step 5311 | loss:2.0670154094696045 lr:5.315555959295365e-05 tokens_per_second_per_gpu:2220.826108153928 
Step 5312 | loss:2.0531699657440186 lr:5.312079900383693e-05 tokens_per_second_per_gpu:2187.6558474563417 
Step 5313 | loss:2.1130826473236084 lr:5.308604567308653e-05 tokens_per_second_per_gpu:2207.2935600514716 
Step 5314 | loss:2.0479977130889893 lr:5.305129960608335e-05 tokens_per_second_per_gpu:2136.688567262285 
Step 5315 | loss:2.086811065673828 lr:5.3016560808207214e-05 tokens_per_second_per_gpu:2225.955756048161 
Step 5316 | loss:2.0434978008270264 lr:5.298182928483675e-05 tokens_per_second_per_gpu:2162.916170762088 
Step 5317 | loss:2.0253243446350098 lr:5.29471050413495e-05 tokens_per_second_per_gpu:2181.69217341528 
Step 5318 | loss:2.070427179336548 lr:5.291238808312189e-05 tokens_per_second_per_gpu:2225.5607567189318 
Step 5319 | loss:2.0498385429382324 lr:5.2877678415529105e-05 tokens_per_second_per_gpu:2197.573093909434 
Step 5320 | loss:2.101344108581543 lr:5.2842976043945346e-05 tokens_per_second_per_gpu:2160.4743930070535 
Step 5321 | loss:2.0699987411499023 lr:5.280828097374361e-05 tokens_per_second_per_gpu:2184.5121300247843 
Step 5322 | loss:2.1167969703674316 lr:5.277359321029578e-05 tokens_per_second_per_gpu:2197.6694328257377 
Step 5323 | loss:2.0747506618499756 lr:5.273891275897263e-05 tokens_per_second_per_gpu:2201.989186816843 
Step 5324 | loss:1.9947468042373657 lr:5.270423962514377e-05 tokens_per_second_per_gpu:2133.454096808138 
Step 5325 | loss:2.105903148651123 lr:5.266957381417761e-05 tokens_per_second_per_gpu:2197.424529699456 
Step 5326 | loss:2.0700387954711914 lr:5.26349153314416e-05 tokens_per_second_per_gpu:2208.147355351844 
Step 5327 | loss:2.087467670440674 lr:5.2600264182301975e-05 tokens_per_second_per_gpu:2129.795427789729 
Step 5328 | loss:2.081432819366455 lr:5.2565620372123724e-05 tokens_per_second_per_gpu:2227.521338358482 
Step 5329 | loss:2.0185060501098633 lr:5.253098390627082e-05 tokens_per_second_per_gpu:2152.8912074059667 
Step 5330 | loss:2.031151056289673 lr:5.249635479010614e-05 tokens_per_second_per_gpu:2204.7648136177236 
Step 5331 | loss:2.0212717056274414 lr:5.246173302899121e-05 tokens_per_second_per_gpu:2212.4585789878493 
Step 5332 | loss:2.1079459190368652 lr:5.242711862828669e-05 tokens_per_second_per_gpu:2166.6212453315297 
Step 5333 | loss:2.1076102256774902 lr:5.239251159335197e-05 tokens_per_second_per_gpu:2133.879615444258 
Step 5334 | loss:2.0439977645874023 lr:5.2357911929545224e-05 tokens_per_second_per_gpu:2189.0713241860917 
Step 5335 | loss:2.04726505279541 lr:5.232331964222361e-05 tokens_per_second_per_gpu:2199.176692179347 
Step 5336 | loss:2.0970005989074707 lr:5.228873473674307e-05 tokens_per_second_per_gpu:2181.286710102666 
Step 5337 | loss:2.0865702629089355 lr:5.225415721845846e-05 tokens_per_second_per_gpu:2208.7550747674386 
Step 5338 | loss:2.1373000144958496 lr:5.221958709272343e-05 tokens_per_second_per_gpu:2180.279079350785 
Step 5339 | loss:2.062413215637207 lr:5.218502436489059e-05 tokens_per_second_per_gpu:2207.1375111433767 
Step 5340 | loss:2.0683364868164062 lr:5.215046904031122e-05 tokens_per_second_per_gpu:2211.719615149879 
Step 5341 | loss:2.008876085281372 lr:5.211592112433563e-05 tokens_per_second_per_gpu:2214.739869959068 
Step 5342 | loss:2.0305776596069336 lr:5.20813806223129e-05 tokens_per_second_per_gpu:2190.3234786878297 
Step 5343 | loss:2.024017333984375 lr:5.2046847539590995e-05 tokens_per_second_per_gpu:2181.6297022421263 
Step 5344 | loss:2.065491199493408 lr:5.20123218815167e-05 tokens_per_second_per_gpu:2207.566273199201 
Step 5345 | loss:2.0940659046173096 lr:5.197780365343572e-05 tokens_per_second_per_gpu:2221.115012665932 
Step 5346 | loss:2.088207960128784 lr:5.194329286069246e-05 tokens_per_second_per_gpu:2212.7810408688156 
Step 5347 | loss:2.0371265411376953 lr:5.190878950863033e-05 tokens_per_second_per_gpu:2170.9880161361534 
Step 5348 | loss:2.0560531616210938 lr:5.187429360259152e-05 tokens_per_second_per_gpu:2214.3224303855895 
Step 5349 | loss:2.0733814239501953 lr:5.1839805147917064e-05 tokens_per_second_per_gpu:2141.408499675233 
Step 5350 | loss:2.0607919692993164 lr:5.180532414994688e-05 tokens_per_second_per_gpu:2214.097961575878 
Step 5351 | loss:2.076063871383667 lr:5.1770850614019705e-05 tokens_per_second_per_gpu:2224.248262723051 
Step 5352 | loss:2.02362060546875 lr:5.173638454547303e-05 tokens_per_second_per_gpu:2165.761746265293 
Step 5353 | loss:2.1529316902160645 lr:5.17019259496434e-05 tokens_per_second_per_gpu:2191.9023228710557 
Step 5354 | loss:2.0493342876434326 lr:5.166747483186607e-05 tokens_per_second_per_gpu:2218.5728906531203 
Step 5355 | loss:2.0737640857696533 lr:5.163303119747509e-05 tokens_per_second_per_gpu:2222.921772996297 
Step 5356 | loss:2.073270320892334 lr:5.159859505180342e-05 tokens_per_second_per_gpu:2193.7913868339597 
Step 5357 | loss:2.108004570007324 lr:5.156416640018292e-05 tokens_per_second_per_gpu:2223.2000851121243 
Step 5358 | loss:2.1545474529266357 lr:5.152974524794409e-05 tokens_per_second_per_gpu:2219.45366774814 
Step 5359 | loss:2.031432628631592 lr:5.149533160041653e-05 tokens_per_second_per_gpu:2186.8787698615024 
Step 5360 | loss:2.106782913208008 lr:5.1460925462928546e-05 tokens_per_second_per_gpu:2221.541242086117 
Step 5361 | loss:2.0024356842041016 lr:5.14265268408072e-05 tokens_per_second_per_gpu:2200.7540203215544 
Step 5362 | loss:2.083125591278076 lr:5.139213573937851e-05 tokens_per_second_per_gpu:2216.949958211526 
Step 5363 | loss:2.1400392055511475 lr:5.1357752163967296e-05 tokens_per_second_per_gpu:2153.3955559549154 
Step 5364 | loss:2.058502197265625 lr:5.1323376119897214e-05 tokens_per_second_per_gpu:2185.159356047284 
Step 5365 | loss:2.029775619506836 lr:5.128900761249076e-05 tokens_per_second_per_gpu:2177.1323502052924 
Step 5366 | loss:2.022505760192871 lr:5.125464664706927e-05 tokens_per_second_per_gpu:2213.7877021178406 
Step 5367 | loss:2.0152640342712402 lr:5.122029322895283e-05 tokens_per_second_per_gpu:2170.987900245374 
Step 5368 | loss:2.083465576171875 lr:5.118594736346047e-05 tokens_per_second_per_gpu:2200.09425225511 
Step 5369 | loss:2.031597137451172 lr:5.1151609055910014e-05 tokens_per_second_per_gpu:2208.1874949538023 
Step 5370 | loss:2.1007561683654785 lr:5.1117278311618054e-05 tokens_per_second_per_gpu:2201.5896363550837 
Step 5371 | loss:2.0758800506591797 lr:5.108295513590014e-05 tokens_per_second_per_gpu:2215.155548820012 
Step 5372 | loss:2.068518877029419 lr:5.104863953407053e-05 tokens_per_second_per_gpu:2216.4165463927857 
Step 5373 | loss:2.0687501430511475 lr:5.101433151144234e-05 tokens_per_second_per_gpu:2218.4930534684836 
Step 5374 | loss:2.032951831817627 lr:5.098003107332754e-05 tokens_per_second_per_gpu:2216.513001764346 
Step 5375 | loss:2.066737174987793 lr:5.09457382250369e-05 tokens_per_second_per_gpu:2171.189676440868 
Step 5376 | loss:2.0852179527282715 lr:5.0911452971880024e-05 tokens_per_second_per_gpu:2226.734166854927 
Step 5377 | loss:2.0493338108062744 lr:5.087717531916536e-05 tokens_per_second_per_gpu:2179.4079840873437 
Step 5378 | loss:2.0993428230285645 lr:5.084290527220019e-05 tokens_per_second_per_gpu:2190.417570335008 
Step 5379 | loss:2.0993001461029053 lr:5.080864283629048e-05 tokens_per_second_per_gpu:2177.631396002653 
Step 5380 | loss:2.0484328269958496 lr:5.0774388016741234e-05 tokens_per_second_per_gpu:2228.914349326019 
Step 5381 | loss:1.9971177577972412 lr:5.0740140818856174e-05 tokens_per_second_per_gpu:2227.788915452319 
Step 5382 | loss:2.0585501194000244 lr:5.0705901247937746e-05 tokens_per_second_per_gpu:2210.833139047172 
Step 5383 | loss:2.0479488372802734 lr:5.067166930928737e-05 tokens_per_second_per_gpu:2153.6222113088993 
Step 5384 | loss:2.05594539642334 lr:5.063744500820521e-05 tokens_per_second_per_gpu:2155.964066630622 
Step 5385 | loss:2.065871477127075 lr:5.060322834999025e-05 tokens_per_second_per_gpu:2208.028109827138 
Step 5386 | loss:2.076744556427002 lr:5.056901933994029e-05 tokens_per_second_per_gpu:2226.683463436536 
Step 5387 | loss:2.093750238418579 lr:5.053481798335202e-05 tokens_per_second_per_gpu:2226.2341919213095 
Step 5388 | loss:2.0547709465026855 lr:5.05006242855208e-05 tokens_per_second_per_gpu:2174.9753152439393 
Step 5389 | loss:2.091620445251465 lr:5.04664382517409e-05 tokens_per_second_per_gpu:2210.9310681682323 
Step 5390 | loss:2.0576894283294678 lr:5.04322598873054e-05 tokens_per_second_per_gpu:2218.7429220732374 
Step 5391 | loss:2.0130233764648438 lr:5.039808919750617e-05 tokens_per_second_per_gpu:2217.1005047255126 
Step 5392 | loss:2.0773375034332275 lr:5.0363926187633924e-05 tokens_per_second_per_gpu:2227.1936786908227 
Step 5393 | loss:2.051191806793213 lr:5.0329770862978185e-05 tokens_per_second_per_gpu:2203.0461118077196 
Step 5394 | loss:2.016716718673706 lr:5.0295623228827194e-05 tokens_per_second_per_gpu:2180.714332490522 
Step 5395 | loss:2.0602011680603027 lr:5.02614832904681e-05 tokens_per_second_per_gpu:2154.81660196475 
Step 5396 | loss:2.0639631748199463 lr:5.022735105318686e-05 tokens_per_second_per_gpu:2207.652534575123 
Step 5397 | loss:2.1122477054595947 lr:5.0193226522268166e-05 tokens_per_second_per_gpu:2229.2848017911742 
Step 5398 | loss:2.0756845474243164 lr:5.015910970299562e-05 tokens_per_second_per_gpu:2189.87057186721 
Step 5399 | loss:2.052219867706299 lr:5.012500060065157e-05 tokens_per_second_per_gpu:2223.713263455441 
Step 5400 | loss:2.0661730766296387 lr:5.009089922051706e-05 tokens_per_second_per_gpu:2213.124885773103 
Step 5401 | loss:2.0423433780670166 lr:5.0056805567872225e-05 tokens_per_second_per_gpu:2208.288640830517 
Step 5402 | loss:2.066183567047119 lr:5.00227196479957e-05 tokens_per_second_per_gpu:2228.078785667688 
Step 5403 | loss:2.0530991554260254 lr:4.9988641466165074e-05 tokens_per_second_per_gpu:2208.8536049870763 
Step 5404 | loss:2.023062229156494 lr:4.995457102765675e-05 tokens_per_second_per_gpu:2111.368013279152 
Step 5405 | loss:2.1045026779174805 lr:4.992050833774591e-05 tokens_per_second_per_gpu:2151.4872168532834 
Step 5406 | loss:2.130371570587158 lr:4.9886453401706414e-05 tokens_per_second_per_gpu:2176.2476202336047 
Step 5407 | loss:2.064331531524658 lr:4.9852406224811144e-05 tokens_per_second_per_gpu:2226.211827066352 
Step 5408 | loss:2.0575222969055176 lr:4.981836681233167e-05 tokens_per_second_per_gpu:2191.678004278451 
Step 5409 | loss:2.022784948348999 lr:4.97843351695383e-05 tokens_per_second_per_gpu:2145.57950015105 
Step 5410 | loss:2.0575976371765137 lr:4.97503113017002e-05 tokens_per_second_per_gpu:2180.2673971169834 
Step 5411 | loss:2.0871739387512207 lr:4.971629521408535e-05 tokens_per_second_per_gpu:2221.5803569611776 
Step 5412 | loss:2.1044068336486816 lr:4.968228691196051e-05 tokens_per_second_per_gpu:2205.36338901741 
Step 5413 | loss:2.1289749145507812 lr:4.964828640059121e-05 tokens_per_second_per_gpu:2169.6602229674713 
Step 5414 | loss:2.0362019538879395 lr:4.961429368524184e-05 tokens_per_second_per_gpu:2167.8147421790213 
Step 5415 | loss:2.0764613151550293 lr:4.9580308771175454e-05 tokens_per_second_per_gpu:2216.310187138105 
Step 5416 | loss:2.02038311958313 lr:4.9546331663654036e-05 tokens_per_second_per_gpu:2104.132727998436 
Step 5417 | loss:2.0493953227996826 lr:4.951236236793828e-05 tokens_per_second_per_gpu:2195.7197079985517 
Step 5418 | loss:2.110276222229004 lr:4.9478400889287705e-05 tokens_per_second_per_gpu:2211.807649260429 
Step 5419 | loss:2.094730854034424 lr:4.944444723296061e-05 tokens_per_second_per_gpu:2194.279533307935 
Step 5420 | loss:2.086763858795166 lr:4.9410501404214124e-05 tokens_per_second_per_gpu:2222.682738643663 
Step 5421 | loss:2.047553300857544 lr:4.9376563408304056e-05 tokens_per_second_per_gpu:2204.4465065628815 
Step 5422 | loss:2.052114963531494 lr:4.934263325048508e-05 tokens_per_second_per_gpu:2175.604320212195 
Step 5423 | loss:2.0793228149414062 lr:4.9308710936010674e-05 tokens_per_second_per_gpu:2225.517515627799 
Step 5424 | loss:2.0336787700653076 lr:4.9274796470133054e-05 tokens_per_second_per_gpu:2226.1488684556753 
Step 5425 | loss:2.0168886184692383 lr:4.924088985810324e-05 tokens_per_second_per_gpu:2190.459949803417 
Step 5426 | loss:2.0721659660339355 lr:4.9206991105171094e-05 tokens_per_second_per_gpu:2187.425636746286 
Step 5427 | loss:2.017971992492676 lr:4.9173100216585076e-05 tokens_per_second_per_gpu:2202.5158384240335 
Step 5428 | loss:2.082981586456299 lr:4.91392171975927e-05 tokens_per_second_per_gpu:2201.9372543405493 
Step 5429 | loss:2.0363433361053467 lr:4.910534205344001e-05 tokens_per_second_per_gpu:2226.12765238299 
Step 5430 | loss:2.091090202331543 lr:4.9071474789371974e-05 tokens_per_second_per_gpu:2200.253988009065 
Step 5431 | loss:2.0873923301696777 lr:4.903761541063231e-05 tokens_per_second_per_gpu:2210.7756337584847 
Step 5432 | loss:2.0599982738494873 lr:4.900376392246354e-05 tokens_per_second_per_gpu:2220.263395209714 
Step 5433 | loss:2.0432631969451904 lr:4.8969920330106813e-05 tokens_per_second_per_gpu:2173.7620422867944 
Step 5434 | loss:2.0530929565429688 lr:4.89360846388023e-05 tokens_per_second_per_gpu:2185.5865865473725 
Step 5435 | loss:2.068305492401123 lr:4.890225685378883e-05 tokens_per_second_per_gpu:2208.5859075802227 
Step 5436 | loss:2.154456377029419 lr:4.886843698030391e-05 tokens_per_second_per_gpu:2140.333188589079 
Step 5437 | loss:2.0936965942382812 lr:4.883462502358397e-05 tokens_per_second_per_gpu:2198.063999056684 
Step 5438 | loss:2.0373120307922363 lr:4.880082098886414e-05 tokens_per_second_per_gpu:2208.2248252441036 
Step 5439 | loss:2.070664882659912 lr:4.8767024881378346e-05 tokens_per_second_per_gpu:2217.7913044547136 
Step 5440 | loss:2.0860958099365234 lr:4.873323670635929e-05 tokens_per_second_per_gpu:2196.4994848606484 
Step 5441 | loss:2.1118476390838623 lr:4.8699456469038474e-05 tokens_per_second_per_gpu:2183.9423953341134 
Step 5442 | loss:2.09859299659729 lr:4.866568417464605e-05 tokens_per_second_per_gpu:2218.8825054641216 
Step 5443 | loss:2.078464984893799 lr:4.863191982841107e-05 tokens_per_second_per_gpu:2186.9716034597463 
Step 5444 | loss:2.063967227935791 lr:4.859816343556132e-05 tokens_per_second_per_gpu:2069.4338551592027 
Step 5445 | loss:2.048262119293213 lr:4.856441500132333e-05 tokens_per_second_per_gpu:2225.8995936459382 
Step 5446 | loss:2.0465171337127686 lr:4.8530674530922415e-05 tokens_per_second_per_gpu:2146.729446456702 
Step 5447 | loss:2.073427677154541 lr:4.84969420295827e-05 tokens_per_second_per_gpu:2201.8258650326093 
Step 5448 | loss:2.1215198040008545 lr:4.846321750252696e-05 tokens_per_second_per_gpu:2189.4445680091508 
Step 5449 | loss:2.079092264175415 lr:4.8429500954976835e-05 tokens_per_second_per_gpu:2205.344820516613 
Step 5450 | loss:2.0534074306488037 lr:4.839579239215269e-05 tokens_per_second_per_gpu:2218.1710162986196 
Step 5451 | loss:2.023282051086426 lr:4.836209181927369e-05 tokens_per_second_per_gpu:2186.821524781769 
Step 5452 | loss:2.0366194248199463 lr:4.832839924155773e-05 tokens_per_second_per_gpu:2216.0954075807103 
Step 5453 | loss:2.077148914337158 lr:4.8294714664221494e-05 tokens_per_second_per_gpu:2190.1904319022387 
Step 5454 | loss:2.027571678161621 lr:4.826103809248031e-05 tokens_per_second_per_gpu:2228.3543629406317 
Step 5455 | loss:2.1047377586364746 lr:4.8227369531548526e-05 tokens_per_second_per_gpu:2150.8718407814386 
Step 5456 | loss:2.064606189727783 lr:4.8193708986638953e-05 tokens_per_second_per_gpu:2192.8805533244613 
Step 5457 | loss:2.11500883102417 lr:4.8160056462963346e-05 tokens_per_second_per_gpu:2197.2575096697433 
Step 5458 | loss:2.1354169845581055 lr:4.8126411965732164e-05 tokens_per_second_per_gpu:2195.9866319526964 
Step 5459 | loss:2.1069765090942383 lr:4.8092775500154666e-05 tokens_per_second_per_gpu:2213.5768943097955 
Step 5460 | loss:2.1260018348693848 lr:4.8059147071438715e-05 tokens_per_second_per_gpu:2226.4533803892496 
Step 5461 | loss:2.0549373626708984 lr:4.802552668479115e-05 tokens_per_second_per_gpu:2157.6894664613533 
Step 5462 | loss:2.0897741317749023 lr:4.799191434541749e-05 tokens_per_second_per_gpu:2211.9075269129853 
Step 5463 | loss:2.0826635360717773 lr:4.795831005852186e-05 tokens_per_second_per_gpu:2203.584013116847 
Step 5464 | loss:2.09859561920166 lr:4.792471382930731e-05 tokens_per_second_per_gpu:2220.0868496203407 
Step 5465 | loss:2.055338144302368 lr:4.789112566297559e-05 tokens_per_second_per_gpu:2231.794549399235 
Step 5466 | loss:2.080801248550415 lr:4.785754556472718e-05 tokens_per_second_per_gpu:2215.612452997378 
Step 5467 | loss:2.0887451171875 lr:4.782397353976136e-05 tokens_per_second_per_gpu:2204.66113546376 
Step 5468 | loss:2.0832200050354004 lr:4.779040959327614e-05 tokens_per_second_per_gpu:2198.791612170995 
Step 5469 | loss:2.0476508140563965 lr:4.775685373046821e-05 tokens_per_second_per_gpu:2205.9666056443875 
Step 5470 | loss:2.0670924186706543 lr:4.77233059565331e-05 tokens_per_second_per_gpu:2216.7892782102685 
Step 5471 | loss:2.0306646823883057 lr:4.768976627666505e-05 tokens_per_second_per_gpu:2228.8145488483833 
Step 5472 | loss:2.0564215183258057 lr:4.7656234696057055e-05 tokens_per_second_per_gpu:2220.4618329516975 
Step 5473 | loss:2.0573344230651855 lr:4.762271121990085e-05 tokens_per_second_per_gpu:2159.357049356811 
Step 5474 | loss:2.065138816833496 lr:4.7589195853386956e-05 tokens_per_second_per_gpu:2171.9673399803687 
Step 5475 | loss:2.034848690032959 lr:4.755568860170453e-05 tokens_per_second_per_gpu:2212.850133215403 
Step 5476 | loss:2.043226718902588 lr:4.752218947004158e-05 tokens_per_second_per_gpu:2151.1591315634687 
Step 5477 | loss:2.1182103157043457 lr:4.7488698463584804e-05 tokens_per_second_per_gpu:2231.57592830463 
Step 5478 | loss:2.1388866901397705 lr:4.745521558751968e-05 tokens_per_second_per_gpu:2228.165102478007 
Step 5479 | loss:2.1053595542907715 lr:4.742174084703037e-05 tokens_per_second_per_gpu:2213.115082599848 
Step 5480 | loss:2.055924415588379 lr:4.738827424729989e-05 tokens_per_second_per_gpu:2178.329179361547 
Step 5481 | loss:2.1179251670837402 lr:4.735481579350978e-05 tokens_per_second_per_gpu:2184.2210903103555 
Step 5482 | loss:2.0858826637268066 lr:4.73213654908406e-05 tokens_per_second_per_gpu:2166.577922639653 
Step 5483 | loss:2.0322256088256836 lr:4.728792334447141e-05 tokens_per_second_per_gpu:2221.03550873662 
Step 5484 | loss:2.114208221435547 lr:4.7254489359580126e-05 tokens_per_second_per_gpu:2174.9046441305113 
Step 5485 | loss:2.0545754432678223 lr:4.722106354134337e-05 tokens_per_second_per_gpu:2136.719083817747 
Step 5486 | loss:2.0536022186279297 lr:4.718764589493651e-05 tokens_per_second_per_gpu:2222.5184586324735 
Step 5487 | loss:2.064455509185791 lr:4.715423642553364e-05 tokens_per_second_per_gpu:2223.653389417504 
Step 5488 | loss:2.0979056358337402 lr:4.712083513830759e-05 tokens_per_second_per_gpu:2231.847124452943 
Step 5489 | loss:2.043299913406372 lr:4.7087442038429974e-05 tokens_per_second_per_gpu:2189.4929598662156 
Step 5490 | loss:2.0694990158081055 lr:4.7054057131071006e-05 tokens_per_second_per_gpu:2079.573256281964 
Step 5491 | loss:2.016124963760376 lr:4.702068042139973e-05 tokens_per_second_per_gpu:2212.3269336222193 
Step 5492 | loss:2.0271925926208496 lr:4.698731191458394e-05 tokens_per_second_per_gpu:2141.2684561731007 
Step 5493 | loss:2.05954647064209 lr:4.6953951615790104e-05 tokens_per_second_per_gpu:2184.3572105611006 
Step 5494 | loss:2.04520320892334 lr:4.692059953018344e-05 tokens_per_second_per_gpu:2122.3668227676417 
Step 5495 | loss:2.0688929557800293 lr:4.688725566292793e-05 tokens_per_second_per_gpu:2132.7434859398704 
Step 5496 | loss:2.0566630363464355 lr:4.685392001918618e-05 tokens_per_second_per_gpu:2184.155703791366 
Step 5497 | loss:2.0558676719665527 lr:4.682059260411963e-05 tokens_per_second_per_gpu:2213.2870162076997 
Step 5498 | loss:2.096864700317383 lr:4.67872734228884e-05 tokens_per_second_per_gpu:2217.1053600802115 
Step 5499 | loss:2.0924205780029297 lr:4.6753962480651336e-05 tokens_per_second_per_gpu:2215.919425178891 
Step 5500 | loss:2.116015911102295 lr:4.672065978256601e-05 tokens_per_second_per_gpu:2220.6907738307345 
Step 5501 | loss:2.0596799850463867 lr:4.6687365333788776e-05 tokens_per_second_per_gpu:2229.6880828190397 
Step 5502 | loss:2.055300712585449 lr:4.665407913947454e-05 tokens_per_second_per_gpu:2156.3757235355306 
Step 5503 | loss:2.0756964683532715 lr:4.662080120477719e-05 tokens_per_second_per_gpu:2208.333460373339 
Step 5504 | loss:2.064434051513672 lr:4.6587531534849074e-05 tokens_per_second_per_gpu:2188.64110872238 
Step 5505 | loss:2.0428273677825928 lr:4.6554270134841425e-05 tokens_per_second_per_gpu:2203.588459557786 
Step 5506 | loss:2.0452516078948975 lr:4.6521017009904136e-05 tokens_per_second_per_gpu:2202.5259716548326 
Step 5507 | loss:2.1039509773254395 lr:4.648777216518588e-05 tokens_per_second_per_gpu:2134.8049551140184 
Step 5508 | loss:2.078923225402832 lr:4.645453560583388e-05 tokens_per_second_per_gpu:2207.99595852984 
Step 5509 | loss:2.0996463298797607 lr:4.642130733699434e-05 tokens_per_second_per_gpu:2203.1202270765693 
Step 5510 | loss:2.0227153301239014 lr:4.6388087363811935e-05 tokens_per_second_per_gpu:2091.3758408796944 
Step 5511 | loss:2.0792059898376465 lr:4.635487569143019e-05 tokens_per_second_per_gpu:2200.362701403102 
Step 5512 | loss:2.134270191192627 lr:4.6321672324991306e-05 tokens_per_second_per_gpu:2224.969747558817 
Step 5513 | loss:2.1463308334350586 lr:4.62884772696362e-05 tokens_per_second_per_gpu:2198.4304170418404 
Step 5514 | loss:2.066460132598877 lr:4.625529053050451e-05 tokens_per_second_per_gpu:2226.8199188620197 
Step 5515 | loss:2.057185649871826 lr:4.622211211273458e-05 tokens_per_second_per_gpu:2228.2753790299234 
Step 5516 | loss:2.054422378540039 lr:4.618894202146351e-05 tokens_per_second_per_gpu:2161.889968546992 
Step 5517 | loss:2.0818169116973877 lr:4.615578026182697e-05 tokens_per_second_per_gpu:2064.041552269279 
Step 5518 | loss:2.1097378730773926 lr:4.612262683895951e-05 tokens_per_second_per_gpu:2214.050559858452 
Step 5519 | loss:2.04384183883667 lr:4.608948175799429e-05 tokens_per_second_per_gpu:2153.4106083881406 
Step 5520 | loss:2.073694944381714 lr:4.605634502406321e-05 tokens_per_second_per_gpu:2200.6689024760417 
Step 5521 | loss:2.1229467391967773 lr:4.6023216642296885e-05 tokens_per_second_per_gpu:2216.917249116017 
Step 5522 | loss:2.0914618968963623 lr:4.599009661782464e-05 tokens_per_second_per_gpu:2232.045706080593 
Step 5523 | loss:2.077258348464966 lr:4.595698495577443e-05 tokens_per_second_per_gpu:2179.264196614622 
Step 5524 | loss:2.099727153778076 lr:4.5923881661273015e-05 tokens_per_second_per_gpu:2187.344495457905 
Step 5525 | loss:2.1132442951202393 lr:4.589078673944581e-05 tokens_per_second_per_gpu:2175.5337441587226 
Step 5526 | loss:2.054323196411133 lr:4.5857700195416965e-05 tokens_per_second_per_gpu:2231.034580599433 
Step 5527 | loss:1.9700617790222168 lr:4.582462203430928e-05 tokens_per_second_per_gpu:2142.587196018214 
Step 5528 | loss:2.0932066440582275 lr:4.579155226124436e-05 tokens_per_second_per_gpu:2224.2879808374437 
Step 5529 | loss:2.0802009105682373 lr:4.57584908813423e-05 tokens_per_second_per_gpu:2187.7670500308427 
Step 5530 | loss:2.077786922454834 lr:4.57254378997222e-05 tokens_per_second_per_gpu:2196.4003937924454 
Step 5531 | loss:2.0417842864990234 lr:4.569239332150158e-05 tokens_per_second_per_gpu:2148.326639789339 
Step 5532 | loss:2.045015335083008 lr:4.565935715179681e-05 tokens_per_second_per_gpu:2147.4567282678568 
Step 5533 | loss:2.100748062133789 lr:4.5626329395722924e-05 tokens_per_second_per_gpu:2228.098608139579 
Step 5534 | loss:2.0466113090515137 lr:4.559331005839368e-05 tokens_per_second_per_gpu:2225.5318340100725 
Step 5535 | loss:2.0260260105133057 lr:4.5560299144921403e-05 tokens_per_second_per_gpu:2187.677553218706 
Step 5536 | loss:2.0756728649139404 lr:4.552729666041736e-05 tokens_per_second_per_gpu:2214.3344517860824 
Step 5537 | loss:2.041989803314209 lr:4.5494302609991266e-05 tokens_per_second_per_gpu:2205.3215646844983 
Step 5538 | loss:2.0439212322235107 lr:4.5461316998751654e-05 tokens_per_second_per_gpu:2196.7967280980984 
Step 5539 | loss:2.0667123794555664 lr:4.5428339831805734e-05 tokens_per_second_per_gpu:2218.048488968044 
Step 5540 | loss:2.0569357872009277 lr:4.53953711142594e-05 tokens_per_second_per_gpu:2125.523390445237 
Step 5541 | loss:2.0339765548706055 lr:4.5362410851217255e-05 tokens_per_second_per_gpu:2219.9588444691763 
Step 5542 | loss:2.078577995300293 lr:4.532945904778255e-05 tokens_per_second_per_gpu:2203.2590456247876 
Step 5543 | loss:2.0550880432128906 lr:4.529651570905732e-05 tokens_per_second_per_gpu:2184.5268013233863 
Step 5544 | loss:2.123619318008423 lr:4.526358084014213e-05 tokens_per_second_per_gpu:2227.5290260829606 
Step 5545 | loss:2.0697731971740723 lr:4.5230654446136375e-05 tokens_per_second_per_gpu:2171.882051641321 
Step 5546 | loss:2.0708775520324707 lr:4.519773653213809e-05 tokens_per_second_per_gpu:2229.004365981943 
Step 5547 | loss:2.0748400688171387 lr:4.5164827103244e-05 tokens_per_second_per_gpu:2214.6466474968684 
Step 5548 | loss:2.042060136795044 lr:4.51319261645495e-05 tokens_per_second_per_gpu:2182.7068103242127 
Step 5549 | loss:2.0896589756011963 lr:4.509903372114874e-05 tokens_per_second_per_gpu:2229.413308243264 
Step 5550 | loss:2.0808725357055664 lr:4.506614977813441e-05 tokens_per_second_per_gpu:2189.4995976251057 
Step 5551 | loss:2.0440707206726074 lr:4.5033274340598016e-05 tokens_per_second_per_gpu:2219.5612685879432 
Step 5552 | loss:2.1421866416931152 lr:4.500040741362971e-05 tokens_per_second_per_gpu:2228.2867985349894 
Step 5553 | loss:2.097203254699707 lr:4.49675490023183e-05 tokens_per_second_per_gpu:2143.738025504728 
Step 5554 | loss:2.055929183959961 lr:4.493469911175132e-05 tokens_per_second_per_gpu:2202.034179739732 
Step 5555 | loss:2.04929256439209 lr:4.4901857747014985e-05 tokens_per_second_per_gpu:2217.0852091093 
Step 5556 | loss:2.0108604431152344 lr:4.486902491319406e-05 tokens_per_second_per_gpu:2187.7178612571256 
Step 5557 | loss:2.027930736541748 lr:4.4836200615372224e-05 tokens_per_second_per_gpu:2227.1191749626164 
Step 5558 | loss:2.0337064266204834 lr:4.480338485863163e-05 tokens_per_second_per_gpu:2205.2275462411544 
Step 5559 | loss:2.0640640258789062 lr:4.477057764805318e-05 tokens_per_second_per_gpu:2223.0106936082443 
Step 5560 | loss:2.117706775665283 lr:4.473777898871647e-05 tokens_per_second_per_gpu:2119.8516186547185 
Step 5561 | loss:2.054924726486206 lr:4.4704988885699785e-05 tokens_per_second_per_gpu:2231.005844318853 
Step 5562 | loss:1.9881352186203003 lr:4.467220734408002e-05 tokens_per_second_per_gpu:2163.811818549342 
Step 5563 | loss:2.1198720932006836 lr:4.463943436893283e-05 tokens_per_second_per_gpu:2163.661187070821 
Step 5564 | loss:2.0662338733673096 lr:4.460666996533245e-05 tokens_per_second_per_gpu:2188.629135023358 
Step 5565 | loss:2.0601258277893066 lr:4.4573914138351836e-05 tokens_per_second_per_gpu:2208.1378762109725 
Step 5566 | loss:2.159494400024414 lr:4.454116689306262e-05 tokens_per_second_per_gpu:2185.5759137714977 
Step 5567 | loss:2.1138975620269775 lr:4.4508428234535114e-05 tokens_per_second_per_gpu:2227.121925511127 
Step 5568 | loss:2.026336908340454 lr:4.4475698167838284e-05 tokens_per_second_per_gpu:2211.2618466036465 
Step 5569 | loss:2.03664493560791 lr:4.444297669803981e-05 tokens_per_second_per_gpu:2128.6576634291373 
Step 5570 | loss:2.0376925468444824 lr:4.44102638302059e-05 tokens_per_second_per_gpu:2231.7858489535943 
Step 5571 | loss:2.0792927742004395 lr:4.437755956940158e-05 tokens_per_second_per_gpu:2176.906705825651 
Step 5572 | loss:2.0271735191345215 lr:4.434486392069051e-05 tokens_per_second_per_gpu:2205.5580950689514 
Step 5573 | loss:2.066432476043701 lr:4.431217688913497e-05 tokens_per_second_per_gpu:2168.161540495104 
Step 5574 | loss:2.0662262439727783 lr:4.427949847979595e-05 tokens_per_second_per_gpu:2203.760082354083 
Step 5575 | loss:2.0934977531433105 lr:4.424682869773309e-05 tokens_per_second_per_gpu:2226.468078840265 
Step 5576 | loss:2.0423378944396973 lr:4.421416754800473e-05 tokens_per_second_per_gpu:2224.01279571731 
Step 5577 | loss:2.0758066177368164 lr:4.4181515035667756e-05 tokens_per_second_per_gpu:2205.6565236208235 
Step 5578 | loss:2.073876142501831 lr:4.414887116577784e-05 tokens_per_second_per_gpu:2138.437276639315 
Step 5579 | loss:2.0569841861724854 lr:4.411623594338927e-05 tokens_per_second_per_gpu:2185.403717453776 
Step 5580 | loss:2.0465145111083984 lr:4.408360937355501e-05 tokens_per_second_per_gpu:2224.4332960480956 
Step 5581 | loss:2.0031609535217285 lr:4.405099146132666e-05 tokens_per_second_per_gpu:2188.5852658411204 
Step 5582 | loss:2.0994505882263184 lr:4.4018382211754546e-05 tokens_per_second_per_gpu:2136.289818233532 
Step 5583 | loss:2.1043639183044434 lr:4.398578162988748e-05 tokens_per_second_per_gpu:2193.3521107345127 
Step 5584 | loss:2.047163963317871 lr:4.3953189720773194e-05 tokens_per_second_per_gpu:2216.097085416427 
Step 5585 | loss:2.0408735275268555 lr:4.392060648945783e-05 tokens_per_second_per_gpu:2197.492299379467 
Step 5586 | loss:2.1015052795410156 lr:4.388803194098632e-05 tokens_per_second_per_gpu:2229.3591548021336 
Step 5587 | loss:2.0510802268981934 lr:4.385546608040223e-05 tokens_per_second_per_gpu:2219.4288386508124 
Step 5588 | loss:2.022523880004883 lr:4.382290891274778e-05 tokens_per_second_per_gpu:2173.6086863010623 
Step 5589 | loss:2.032813549041748 lr:4.379036044306383e-05 tokens_per_second_per_gpu:2210.538914721271 
Step 5590 | loss:2.007082939147949 lr:4.375782067638994e-05 tokens_per_second_per_gpu:2225.8746865389867 
Step 5591 | loss:2.059291362762451 lr:4.37252896177642e-05 tokens_per_second_per_gpu:2229.686401713192 
Step 5592 | loss:2.0689005851745605 lr:4.3692767272223486e-05 tokens_per_second_per_gpu:2159.091052919396 
Step 5593 | loss:2.0572094917297363 lr:4.366025364480327e-05 tokens_per_second_per_gpu:2212.268443543395 
Step 5594 | loss:2.0134449005126953 lr:4.362774874053768e-05 tokens_per_second_per_gpu:2228.538637497415 
Step 5595 | loss:2.0613110065460205 lr:4.359525256445948e-05 tokens_per_second_per_gpu:2168.3927614448667 
Step 5596 | loss:2.061553478240967 lr:4.356276512160014e-05 tokens_per_second_per_gpu:2233.9075302269416 
Step 5597 | loss:2.090045690536499 lr:4.3530286416989665e-05 tokens_per_second_per_gpu:2212.27798746708 
Step 5598 | loss:2.106710910797119 lr:4.3497816455656806e-05 tokens_per_second_per_gpu:2123.869871409997 
Step 5599 | loss:2.057238817214966 lr:4.346535524262891e-05 tokens_per_second_per_gpu:2230.7436578736438 
Step 5600 | loss:2.068427801132202 lr:4.3432902782932016e-05 tokens_per_second_per_gpu:2218.7053829906563 
Step 5601 | loss:2.085404872894287 lr:4.3400459081590774e-05 tokens_per_second_per_gpu:2227.894781411723 
Step 5602 | loss:2.07537841796875 lr:4.336802414362847e-05 tokens_per_second_per_gpu:2218.3836346061826 
Step 5603 | loss:2.031780242919922 lr:4.333559797406709e-05 tokens_per_second_per_gpu:2204.1593756005987 
Step 5604 | loss:2.084893226623535 lr:4.330318057792712e-05 tokens_per_second_per_gpu:2140.37287391824 
Step 5605 | loss:2.037649154663086 lr:4.327077196022791e-05 tokens_per_second_per_gpu:2167.735612568885 
Step 5606 | loss:2.0296308994293213 lr:4.323837212598724e-05 tokens_per_second_per_gpu:2197.2445151144575 
Step 5607 | loss:2.0862488746643066 lr:4.3205981080221644e-05 tokens_per_second_per_gpu:2185.386778610521 
Step 5608 | loss:2.0318329334259033 lr:4.317359882794627e-05 tokens_per_second_per_gpu:2223.6619734578667 
Step 5609 | loss:2.0851588249206543 lr:4.314122537417493e-05 tokens_per_second_per_gpu:2195.1513654726896 
Step 5610 | loss:2.076317310333252 lr:4.310886072391996e-05 tokens_per_second_per_gpu:2234.95849186782 
Step 5611 | loss:2.1038737297058105 lr:4.307650488219255e-05 tokens_per_second_per_gpu:2116.197409404554 
Step 5612 | loss:2.0432910919189453 lr:4.30441578540023e-05 tokens_per_second_per_gpu:2103.1506190091486 
Step 5613 | loss:2.042844295501709 lr:4.301181964435755e-05 tokens_per_second_per_gpu:2226.5774922765563 
Step 5614 | loss:2.085850715637207 lr:4.2979490258265296e-05 tokens_per_second_per_gpu:2127.3126014732607 
Step 5615 | loss:2.0599663257598877 lr:4.294716970073113e-05 tokens_per_second_per_gpu:2220.0714038109177 
Step 5616 | loss:2.0825188159942627 lr:4.291485797675927e-05 tokens_per_second_per_gpu:2220.720828213305 
Step 5617 | loss:2.0689055919647217 lr:4.288255509135263e-05 tokens_per_second_per_gpu:2229.95739308899 
Step 5618 | loss:2.0785467624664307 lr:4.285026104951264e-05 tokens_per_second_per_gpu:2232.491522698996 
Step 5619 | loss:2.054584503173828 lr:4.2817975856239444e-05 tokens_per_second_per_gpu:2231.7236610279797 
Step 5620 | loss:2.0958805084228516 lr:4.278569951653183e-05 tokens_per_second_per_gpu:2163.525477795296 
Step 5621 | loss:2.0486769676208496 lr:4.2753432035387163e-05 tokens_per_second_per_gpu:2155.2185020009156 
Step 5622 | loss:2.05682635307312 lr:4.2721173417801454e-05 tokens_per_second_per_gpu:2139.599160711845 
Step 5623 | loss:2.06082820892334 lr:4.2688923668769395e-05 tokens_per_second_per_gpu:2183.5669256086976 
Step 5624 | loss:2.104949474334717 lr:4.2656682793284185e-05 tokens_per_second_per_gpu:2164.702386258026 
Step 5625 | loss:2.0563793182373047 lr:4.262445079633774e-05 tokens_per_second_per_gpu:2199.791660169843 
Step 5626 | loss:2.0120372772216797 lr:4.259222768292061e-05 tokens_per_second_per_gpu:2123.566934377276 
Step 5627 | loss:2.0605170726776123 lr:4.2560013458021894e-05 tokens_per_second_per_gpu:2215.128805035714 
Step 5628 | loss:2.0731236934661865 lr:4.252780812662941e-05 tokens_per_second_per_gpu:2227.363824137178 
Step 5629 | loss:2.065091133117676 lr:4.249561169372952e-05 tokens_per_second_per_gpu:2205.5517829330247 
Step 5630 | loss:2.065511703491211 lr:4.2463424164307285e-05 tokens_per_second_per_gpu:2218.800568999532 
Step 5631 | loss:2.0976715087890625 lr:4.243124554334623e-05 tokens_per_second_per_gpu:2199.917052838977 
Step 5632 | loss:2.0792484283447266 lr:4.239907583582877e-05 tokens_per_second_per_gpu:2105.4304799189463 
Step 5633 | loss:2.1231470108032227 lr:4.2366915046735656e-05 tokens_per_second_per_gpu:2224.4175150901724 
Step 5634 | loss:2.10268497467041 lr:4.233476318104642e-05 tokens_per_second_per_gpu:2172.8670009821126 
Step 5635 | loss:2.1063833236694336 lr:4.230262024373919e-05 tokens_per_second_per_gpu:2227.6369874794486 
Step 5636 | loss:2.088134765625 lr:4.227048623979072e-05 tokens_per_second_per_gpu:2223.775473189079 
Step 5637 | loss:2.0955801010131836 lr:4.223836117417626e-05 tokens_per_second_per_gpu:2224.763259140144 
Step 5638 | loss:2.0947999954223633 lr:4.220624505186992e-05 tokens_per_second_per_gpu:2233.3636157831315 
Step 5639 | loss:2.0869414806365967 lr:4.217413787784416e-05 tokens_per_second_per_gpu:2138.619782061681 
Step 5640 | loss:2.127328872680664 lr:4.214203965707022e-05 tokens_per_second_per_gpu:2163.8762330592285 
Step 5641 | loss:2.100003719329834 lr:4.2109950394517906e-05 tokens_per_second_per_gpu:2228.089408836866 
Step 5642 | loss:2.0343170166015625 lr:4.207787009515564e-05 tokens_per_second_per_gpu:2214.7412534199457 
Step 5643 | loss:2.046820640563965 lr:4.2045798763950465e-05 tokens_per_second_per_gpu:2186.785318241213 
Step 5644 | loss:2.015472412109375 lr:4.201373640586803e-05 tokens_per_second_per_gpu:2149.3479482328967 
Step 5645 | loss:2.083725690841675 lr:4.1981683025872566e-05 tokens_per_second_per_gpu:2187.598257609298 
Step 5646 | loss:2.092095375061035 lr:4.194963862892694e-05 tokens_per_second_per_gpu:2219.3668713688544 
Step 5647 | loss:2.0180797576904297 lr:4.191760321999263e-05 tokens_per_second_per_gpu:2203.8769230049024 
Step 5648 | loss:2.0396437644958496 lr:4.1885576804029734e-05 tokens_per_second_per_gpu:2224.298899185054 
Step 5649 | loss:1.9966309070587158 lr:4.1853559385996936e-05 tokens_per_second_per_gpu:2231.9332202935457 
Step 5650 | loss:2.060544967651367 lr:4.182155097085156e-05 tokens_per_second_per_gpu:2227.3583769491906 
Step 5651 | loss:2.066150665283203 lr:4.178955156354945e-05 tokens_per_second_per_gpu:2228.6279957217944 
Step 5652 | loss:2.12262225151062 lr:4.1757561169045145e-05 tokens_per_second_per_gpu:2171.738479780163 
Step 5653 | loss:2.098820924758911 lr:4.172557979229177e-05 tokens_per_second_per_gpu:2219.4609048360326 
Step 5654 | loss:2.076504707336426 lr:4.169360743824102e-05 tokens_per_second_per_gpu:2219.73123528586 
Step 5655 | loss:2.066850423812866 lr:4.1661644111843235e-05 tokens_per_second_per_gpu:2160.8409164793534 
Step 5656 | loss:2.0873327255249023 lr:4.1629689818047326e-05 tokens_per_second_per_gpu:2222.905918491036 
Step 5657 | loss:2.134891986846924 lr:4.1597744561800854e-05 tokens_per_second_per_gpu:2228.2971709040485 
Step 5658 | loss:2.1046388149261475 lr:4.156580834804984e-05 tokens_per_second_per_gpu:2214.3512536887592 
Step 5659 | loss:2.041616678237915 lr:4.153388118173915e-05 tokens_per_second_per_gpu:2213.3745830665803 
Step 5660 | loss:2.097318172454834 lr:4.150196306781201e-05 tokens_per_second_per_gpu:2201.7141601986305 
Step 5661 | loss:2.1349048614501953 lr:4.147005401121037e-05 tokens_per_second_per_gpu:2174.1787714956963 
Step 5662 | loss:2.0839552879333496 lr:4.143815401687474e-05 tokens_per_second_per_gpu:2178.5241376829363 
Step 5663 | loss:2.026836395263672 lr:4.1406263089744255e-05 tokens_per_second_per_gpu:2216.605881567993 
Step 5664 | loss:2.0473098754882812 lr:4.137438123475662e-05 tokens_per_second_per_gpu:2228.455333947903 
Step 5665 | loss:2.0582988262176514 lr:4.134250845684817e-05 tokens_per_second_per_gpu:2134.7141077591064 
Step 5666 | loss:2.099851608276367 lr:4.131064476095374e-05 tokens_per_second_per_gpu:2231.1610395371417 
Step 5667 | loss:2.0187644958496094 lr:4.1278790152006874e-05 tokens_per_second_per_gpu:2161.890965178481 
Step 5668 | loss:2.1503663063049316 lr:4.124694463493966e-05 tokens_per_second_per_gpu:2216.5188041537594 
Step 5669 | loss:2.062650203704834 lr:4.1215108214682763e-05 tokens_per_second_per_gpu:2224.7776977461253 
Step 5670 | loss:2.0499792098999023 lr:4.118328089616547e-05 tokens_per_second_per_gpu:2231.197758097889 
Step 5671 | loss:2.1213459968566895 lr:4.115146268431568e-05 tokens_per_second_per_gpu:2234.460762482809 
Step 5672 | loss:2.0477209091186523 lr:4.111965358405977e-05 tokens_per_second_per_gpu:2187.049455338338 
Step 5673 | loss:2.0356497764587402 lr:4.108785360032283e-05 tokens_per_second_per_gpu:2169.004576842699 
Step 5674 | loss:2.160888433456421 lr:4.105606273802848e-05 tokens_per_second_per_gpu:2203.2807331365393 
Step 5675 | loss:2.0300710201263428 lr:4.1024281002098955e-05 tokens_per_second_per_gpu:2232.27048273728 
Step 5676 | loss:2.083383560180664 lr:4.099250839745503e-05 tokens_per_second_per_gpu:2181.472711205276 
Step 5677 | loss:2.0950303077697754 lr:4.096074492901617e-05 tokens_per_second_per_gpu:2169.409693871732 
Step 5678 | loss:2.0077295303344727 lr:4.092899060170027e-05 tokens_per_second_per_gpu:2231.054737115487 
Step 5679 | loss:2.0923476219177246 lr:4.089724542042389e-05 tokens_per_second_per_gpu:2226.3204505786043 
Step 5680 | loss:2.012056827545166 lr:4.086550939010227e-05 tokens_per_second_per_gpu:2219.52421305554 
Step 5681 | loss:2.108259677886963 lr:4.083378251564905e-05 tokens_per_second_per_gpu:2230.8401028465423 
Step 5682 | loss:2.0639071464538574 lr:4.080206480197659e-05 tokens_per_second_per_gpu:2092.1542492388935 
Step 5683 | loss:2.0717639923095703 lr:4.0770356253995756e-05 tokens_per_second_per_gpu:2223.0231804565574 
Step 5684 | loss:2.0841808319091797 lr:4.073865687661608e-05 tokens_per_second_per_gpu:2140.3071011025886 
Step 5685 | loss:2.0888068675994873 lr:4.070696667474549e-05 tokens_per_second_per_gpu:2187.9783341714938 
Step 5686 | loss:2.0636489391326904 lr:4.067528565329078e-05 tokens_per_second_per_gpu:2151.1640407480018 
Step 5687 | loss:2.0688819885253906 lr:4.0643613817157045e-05 tokens_per_second_per_gpu:2231.2865569514433 
Step 5688 | loss:2.051159381866455 lr:4.0611951171248116e-05 tokens_per_second_per_gpu:2219.9746817349837 
Step 5689 | loss:2.0662431716918945 lr:4.058029772046638e-05 tokens_per_second_per_gpu:2231.055755079564 
Step 5690 | loss:2.0982003211975098 lr:4.054865346971274e-05 tokens_per_second_per_gpu:2176.5593690628434 
Step 5691 | loss:2.114114284515381 lr:4.051701842388674e-05 tokens_per_second_per_gpu:2160.2428947439803 
Step 5692 | loss:2.058396339416504 lr:4.048539258788652e-05 tokens_per_second_per_gpu:2206.740502377659 
Step 5693 | loss:2.007843255996704 lr:4.045377596660866e-05 tokens_per_second_per_gpu:2221.8686034269626 
Step 5694 | loss:2.0323386192321777 lr:4.042216856494844e-05 tokens_per_second_per_gpu:2229.334017836223 
Step 5695 | loss:2.038349151611328 lr:4.0390570387799666e-05 tokens_per_second_per_gpu:2201.5632116210336 
Step 5696 | loss:2.09961199760437 lr:4.0358981440054744e-05 tokens_per_second_per_gpu:2233.2649237070445 
Step 5697 | loss:2.0316977500915527 lr:4.032740172660462e-05 tokens_per_second_per_gpu:2176.462851232729 
Step 5698 | loss:2.0775156021118164 lr:4.0295831252338866e-05 tokens_per_second_per_gpu:2233.789592831439 
Step 5699 | loss:2.064323902130127 lr:4.026427002214549e-05 tokens_per_second_per_gpu:2230.8039366946778 
Step 5700 | loss:2.0559492111206055 lr:4.023271804091121e-05 tokens_per_second_per_gpu:2115.194235545965 
Step 5701 | loss:2.1007285118103027 lr:4.0201175313521245e-05 tokens_per_second_per_gpu:2126.446378831823 
Step 5702 | loss:2.0550577640533447 lr:4.016964184485941e-05 tokens_per_second_per_gpu:2211.939682586436 
Step 5703 | loss:2.0616135597229004 lr:4.013811763980806e-05 tokens_per_second_per_gpu:2187.8761808245536 
Step 5704 | loss:2.0696969032287598 lr:4.010660270324816e-05 tokens_per_second_per_gpu:2146.3349781952156 
Step 5705 | loss:2.075057029724121 lr:4.007509704005916e-05 tokens_per_second_per_gpu:2232.4364428688527 
Step 5706 | loss:2.1317317485809326 lr:4.00436006551191e-05 tokens_per_second_per_gpu:2230.7376288515475 
Step 5707 | loss:2.097352981567383 lr:4.001211355330472e-05 tokens_per_second_per_gpu:2168.388111198547 
Step 5708 | loss:2.0847792625427246 lr:3.99806357394911e-05 tokens_per_second_per_gpu:2228.843351145512 
Step 5709 | loss:2.0513079166412354 lr:3.994916721855202e-05 tokens_per_second_per_gpu:2225.6211971045377 
Step 5710 | loss:2.040498733520508 lr:3.99177079953598e-05 tokens_per_second_per_gpu:2181.499985244032 
Step 5711 | loss:2.1183252334594727 lr:3.988625807478534e-05 tokens_per_second_per_gpu:2195.0305546469012 
Step 5712 | loss:2.124305248260498 lr:3.985481746169798e-05 tokens_per_second_per_gpu:2216.762258254013 
Step 5713 | loss:2.052006483078003 lr:3.9823386160965836e-05 tokens_per_second_per_gpu:2179.6971086233243 
Step 5714 | loss:2.0924506187438965 lr:3.979196417745536e-05 tokens_per_second_per_gpu:2226.707623056753 
Step 5715 | loss:2.0433578491210938 lr:3.9760551516031675e-05 tokens_per_second_per_gpu:2208.9482443303177 
Step 5716 | loss:2.045936346054077 lr:3.972914818155846e-05 tokens_per_second_per_gpu:2203.822749494575 
Step 5717 | loss:2.039750099182129 lr:3.969775417889793e-05 tokens_per_second_per_gpu:2159.628339022726 
Step 5718 | loss:2.0834484100341797 lr:3.966636951291086e-05 tokens_per_second_per_gpu:2160.568952699769 
Step 5719 | loss:2.073075532913208 lr:3.963499418845661e-05 tokens_per_second_per_gpu:2207.3284365298186 
Step 5720 | loss:2.0521926879882812 lr:3.9603628210392994e-05 tokens_per_second_per_gpu:2201.266483452885 
Step 5721 | loss:2.054098129272461 lr:3.957227158357647e-05 tokens_per_second_per_gpu:2173.6421049977453 
Step 5722 | loss:2.049323558807373 lr:3.9540924312862046e-05 tokens_per_second_per_gpu:2213.004740567932 
Step 5723 | loss:2.086801052093506 lr:3.950958640310324e-05 tokens_per_second_per_gpu:2220.6432224365462 
Step 5724 | loss:2.0597853660583496 lr:3.9478257859152146e-05 tokens_per_second_per_gpu:2188.8704491986205 
Step 5725 | loss:2.008573293685913 lr:3.9446938685859444e-05 tokens_per_second_per_gpu:2225.738590913434 
Step 5726 | loss:2.0250327587127686 lr:3.941562888807424e-05 tokens_per_second_per_gpu:2184.104872168606 
Step 5727 | loss:2.099891185760498 lr:3.9384328470644314e-05 tokens_per_second_per_gpu:2188.5749761761417 
Step 5728 | loss:2.0821871757507324 lr:3.9353037438415955e-05 tokens_per_second_per_gpu:2150.2005363649996 
Step 5729 | loss:2.0248122215270996 lr:3.9321755796233986e-05 tokens_per_second_per_gpu:2202.124426481072 
Step 5730 | loss:2.1196513175964355 lr:3.929048354894177e-05 tokens_per_second_per_gpu:2228.9364024153565 
Step 5731 | loss:2.0616743564605713 lr:3.925922070138128e-05 tokens_per_second_per_gpu:2199.4470173734494 
Step 5732 | loss:1.9947752952575684 lr:3.922796725839292e-05 tokens_per_second_per_gpu:2198.733358910524 
Step 5733 | loss:2.0891647338867188 lr:3.9196723224815676e-05 tokens_per_second_per_gpu:2228.193573681013 
Step 5734 | loss:2.051766872406006 lr:3.916548860548722e-05 tokens_per_second_per_gpu:2230.7287003170213 
Step 5735 | loss:2.0692038536071777 lr:3.9134263405243555e-05 tokens_per_second_per_gpu:2207.574148255548 
Step 5736 | loss:2.0868592262268066 lr:3.910304762891933e-05 tokens_per_second_per_gpu:2226.2572729389803 
Step 5737 | loss:2.0161361694335938 lr:3.9071841281347746e-05 tokens_per_second_per_gpu:2110.5326529541526 
Step 5738 | loss:2.0388710498809814 lr:3.9040644367360534e-05 tokens_per_second_per_gpu:2211.7839017785227 
Step 5739 | loss:2.08994197845459 lr:3.900945689178786e-05 tokens_per_second_per_gpu:2200.0252508960343 
Step 5740 | loss:2.087299346923828 lr:3.897827885945866e-05 tokens_per_second_per_gpu:2202.569457738859 
Step 5741 | loss:2.107086658477783 lr:3.8947110275200164e-05 tokens_per_second_per_gpu:2213.9608372523358 
Step 5742 | loss:2.081441879272461 lr:3.891595114383827e-05 tokens_per_second_per_gpu:2211.187573099101 
Step 5743 | loss:2.0380642414093018 lr:3.8884801470197395e-05 tokens_per_second_per_gpu:2188.8673482128456 
Step 5744 | loss:2.1111741065979004 lr:3.8853661259100484e-05 tokens_per_second_per_gpu:2216.0795581349794 
Step 5745 | loss:2.0607457160949707 lr:3.8822530515369e-05 tokens_per_second_per_gpu:2218.7273095330534 
Step 5746 | loss:2.058582305908203 lr:3.8791409243823015e-05 tokens_per_second_per_gpu:2228.305006792342 
Step 5747 | loss:2.08843731880188 lr:3.8760297449280994e-05 tokens_per_second_per_gpu:2192.1497433394184 
Step 5748 | loss:2.1090939044952393 lr:3.872919513656005e-05 tokens_per_second_per_gpu:2234.899479256152 
Step 5749 | loss:2.055905818939209 lr:3.869810231047578e-05 tokens_per_second_per_gpu:2182.183433355461 
Step 5750 | loss:2.0801453590393066 lr:3.866701897584234e-05 tokens_per_second_per_gpu:2178.6177720586397 
Step 5751 | loss:2.041339874267578 lr:3.863594513747241e-05 tokens_per_second_per_gpu:2223.8755447188933 
Step 5752 | loss:2.0664801597595215 lr:3.860488080017721e-05 tokens_per_second_per_gpu:2185.1886646566254 
Step 5753 | loss:2.0879106521606445 lr:3.857382596876642e-05 tokens_per_second_per_gpu:2226.999215132139 
Step 5754 | loss:2.0159189701080322 lr:3.854278064804832e-05 tokens_per_second_per_gpu:2227.475073691467 
Step 5755 | loss:2.0135936737060547 lr:3.851174484282969e-05 tokens_per_second_per_gpu:2224.4196900436345 
Step 5756 | loss:2.00665545463562 lr:3.848071855791585e-05 tokens_per_second_per_gpu:2207.0358424349424 
Step 5757 | loss:2.0918827056884766 lr:3.844970179811065e-05 tokens_per_second_per_gpu:2218.54633874283 
Step 5758 | loss:2.0562660694122314 lr:3.8418694568216476e-05 tokens_per_second_per_gpu:2198.6233637162786 
Step 5759 | loss:2.1483078002929688 lr:3.838769687303415e-05 tokens_per_second_per_gpu:2196.115589593143 
Step 5760 | loss:2.1120686531066895 lr:3.83567087173631e-05 tokens_per_second_per_gpu:2196.2074843337296 
Step 5761 | loss:2.068509340286255 lr:3.832573010600134e-05 tokens_per_second_per_gpu:2216.5012776732215 
Step 5762 | loss:2.023650884628296 lr:3.8294761043745245e-05 tokens_per_second_per_gpu:2230.5802782566 
Step 5763 | loss:2.1235949993133545 lr:3.826380153538981e-05 tokens_per_second_per_gpu:2217.4670875860666 
Step 5764 | loss:2.1422343254089355 lr:3.8232851585728545e-05 tokens_per_second_per_gpu:2134.350320402409 
Step 5765 | loss:2.08920955657959 lr:3.820191119955349e-05 tokens_per_second_per_gpu:2222.6913300240662 
Step 5766 | loss:2.0986485481262207 lr:3.817098038165514e-05 tokens_per_second_per_gpu:2226.15796299804 
Step 5767 | loss:2.0344254970550537 lr:3.814005913682263e-05 tokens_per_second_per_gpu:2225.399709263862 
Step 5768 | loss:2.0323190689086914 lr:3.810914746984343e-05 tokens_per_second_per_gpu:2171.7168042531794 
Step 5769 | loss:2.0694921016693115 lr:3.807824538550371e-05 tokens_per_second_per_gpu:2210.7239154865556 
Step 5770 | loss:2.0693159103393555 lr:3.804735288858804e-05 tokens_per_second_per_gpu:2218.980718884452 
Step 5771 | loss:2.06072735786438 lr:3.8016469983879556e-05 tokens_per_second_per_gpu:2181.9308720878626 
Step 5772 | loss:2.107248306274414 lr:3.798559667615991e-05 tokens_per_second_per_gpu:2217.1461054875194 
Step 5773 | loss:2.0387651920318604 lr:3.795473297020927e-05 tokens_per_second_per_gpu:2218.9594313159027 
Step 5774 | loss:2.053921699523926 lr:3.792387887080626e-05 tokens_per_second_per_gpu:2162.5429277757175 
Step 5775 | loss:2.1202940940856934 lr:3.789303438272807e-05 tokens_per_second_per_gpu:2228.620386399173 
Step 5776 | loss:2.052861213684082 lr:3.786219951075041e-05 tokens_per_second_per_gpu:2233.8345268057897 
Step 5777 | loss:2.0831398963928223 lr:3.7831374259647454e-05 tokens_per_second_per_gpu:2172.9565609777896 
Step 5778 | loss:2.0729198455810547 lr:3.780055863419195e-05 tokens_per_second_per_gpu:2219.701982677374 
Step 5779 | loss:2.0793466567993164 lr:3.776975263915513e-05 tokens_per_second_per_gpu:2220.92696039253 
Step 5780 | loss:2.059004545211792 lr:3.773895627930667e-05 tokens_per_second_per_gpu:2180.083449955286 
Step 5781 | loss:2.0656023025512695 lr:3.77081695594148e-05 tokens_per_second_per_gpu:2179.8505130612807 
Step 5782 | loss:2.0701653957366943 lr:3.7677392484246375e-05 tokens_per_second_per_gpu:2216.594638071404 
Step 5783 | loss:2.0501933097839355 lr:3.7646625058566556e-05 tokens_per_second_per_gpu:2197.0558568840097 
Step 5784 | loss:2.074091911315918 lr:3.761586728713912e-05 tokens_per_second_per_gpu:2226.9401314204188 
Step 5785 | loss:2.087836265563965 lr:3.758511917472637e-05 tokens_per_second_per_gpu:2152.9039494603235 
Step 5786 | loss:2.1985507011413574 lr:3.7554380726089e-05 tokens_per_second_per_gpu:2147.7207998234157 
Step 5787 | loss:2.0723049640655518 lr:3.7523651945986305e-05 tokens_per_second_per_gpu:2178.314191889731 
Step 5788 | loss:2.0552456378936768 lr:3.7492932839176157e-05 tokens_per_second_per_gpu:2137.5299600658773 
Step 5789 | loss:2.0304839611053467 lr:3.746222341041471e-05 tokens_per_second_per_gpu:2229.5642201544474 
Step 5790 | loss:2.0974645614624023 lr:3.743152366445682e-05 tokens_per_second_per_gpu:2211.0491746452867 
Step 5791 | loss:2.0893592834472656 lr:3.740083360605572e-05 tokens_per_second_per_gpu:2178.2820613710473 
Step 5792 | loss:1.981677770614624 lr:3.7370153239963216e-05 tokens_per_second_per_gpu:2202.4183897913927 
Step 5793 | loss:2.1057252883911133 lr:3.733948257092958e-05 tokens_per_second_per_gpu:2168.4290461713726 
Step 5794 | loss:2.113645315170288 lr:3.730882160370364e-05 tokens_per_second_per_gpu:2119.354754904736 
Step 5795 | loss:2.0854735374450684 lr:3.727817034303259e-05 tokens_per_second_per_gpu:2190.903883757689 
Step 5796 | loss:2.086519241333008 lr:3.7247528793662244e-05 tokens_per_second_per_gpu:2191.4102128109057 
Step 5797 | loss:2.026271104812622 lr:3.721689696033687e-05 tokens_per_second_per_gpu:2136.328034490994 
Step 5798 | loss:2.121084690093994 lr:3.718627484779923e-05 tokens_per_second_per_gpu:2179.654878443058 
Step 5799 | loss:2.0894417762756348 lr:3.7155662460790596e-05 tokens_per_second_per_gpu:2214.4366483044696 
Step 5800 | loss:2.0485587120056152 lr:3.7125059804050744e-05 tokens_per_second_per_gpu:2205.7467834993527 
Step 5801 | loss:2.0948095321655273 lr:3.7094466882317855e-05 tokens_per_second_per_gpu:2234.6608091730773 
Step 5802 | loss:2.051516532897949 lr:3.7063883700328714e-05 tokens_per_second_per_gpu:2184.1358041273947 
Step 5803 | loss:2.131840467453003 lr:3.703331026281855e-05 tokens_per_second_per_gpu:2227.44074106029 
Step 5804 | loss:2.079033851623535 lr:3.7002746574521086e-05 tokens_per_second_per_gpu:2192.9721062587746 
Step 5805 | loss:2.0635018348693848 lr:3.697219264016854e-05 tokens_per_second_per_gpu:2186.784258368143 
Step 5806 | loss:1.9908013343811035 lr:3.694164846449164e-05 tokens_per_second_per_gpu:2223.1940549413052 
Step 5807 | loss:2.0642848014831543 lr:3.691111405221952e-05 tokens_per_second_per_gpu:2210.6018442669924 
Step 5808 | loss:2.0471205711364746 lr:3.688058940807986e-05 tokens_per_second_per_gpu:2158.691534512505 
Step 5809 | loss:2.0253400802612305 lr:3.685007453679893e-05 tokens_per_second_per_gpu:2140.1517598803703 
Step 5810 | loss:2.1152093410491943 lr:3.681956944310129e-05 tokens_per_second_per_gpu:2175.046926656765 
Step 5811 | loss:2.081787109375 lr:3.678907413171011e-05 tokens_per_second_per_gpu:2217.645501007072 
Step 5812 | loss:2.121910333633423 lr:3.6758588607347056e-05 tokens_per_second_per_gpu:2198.367994511283 
Step 5813 | loss:2.06771183013916 lr:3.6728112874732176e-05 tokens_per_second_per_gpu:2187.287894390644 
Step 5814 | loss:2.082643747329712 lr:3.669764693858406e-05 tokens_per_second_per_gpu:2218.97735061635 
Step 5815 | loss:2.057370185852051 lr:3.6667190803619886e-05 tokens_per_second_per_gpu:2173.9597274057905 
Step 5816 | loss:2.100956439971924 lr:3.663674447455513e-05 tokens_per_second_per_gpu:2195.836167113477 
Step 5817 | loss:2.0559470653533936 lr:3.660630795610385e-05 tokens_per_second_per_gpu:2217.107741151255 
Step 5818 | loss:2.0832552909851074 lr:3.6575881252978585e-05 tokens_per_second_per_gpu:2229.465989003135 
Step 5819 | loss:2.071469306945801 lr:3.654546436989032e-05 tokens_per_second_per_gpu:2232.090964481117 
Step 5820 | loss:2.054945707321167 lr:3.651505731154857e-05 tokens_per_second_per_gpu:2199.847961130539 
Step 5821 | loss:2.059918165206909 lr:3.6484660082661326e-05 tokens_per_second_per_gpu:2195.6795250468263 
Step 5822 | loss:2.072004795074463 lr:3.645427268793494e-05 tokens_per_second_per_gpu:2110.736991304114 
Step 5823 | loss:2.082998275756836 lr:3.642389513207438e-05 tokens_per_second_per_gpu:2152.285995029348 
Step 5824 | loss:2.0650477409362793 lr:3.639352741978305e-05 tokens_per_second_per_gpu:2171.7012165130045 
Step 5825 | loss:2.0553340911865234 lr:3.63631695557628e-05 tokens_per_second_per_gpu:2171.5145603489514 
Step 5826 | loss:2.034360647201538 lr:3.633282154471399e-05 tokens_per_second_per_gpu:2141.27203132704 
Step 5827 | loss:2.072448253631592 lr:3.6302483391335476e-05 tokens_per_second_per_gpu:2138.5599982805084 
Step 5828 | loss:2.0782525539398193 lr:3.627215510032448e-05 tokens_per_second_per_gpu:2034.774976387022 
Step 5829 | loss:2.0843584537506104 lr:3.624183667637681e-05 tokens_per_second_per_gpu:2183.01551753157 
Step 5830 | loss:2.033175468444824 lr:3.62115281241867e-05 tokens_per_second_per_gpu:2110.961522017016 
Step 5831 | loss:2.1013708114624023 lr:3.618122944844686e-05 tokens_per_second_per_gpu:2155.115373936195 
Step 5832 | loss:2.052957057952881 lr:3.6150940653848485e-05 tokens_per_second_per_gpu:2180.0132705328915 
Step 5833 | loss:2.137852668762207 lr:3.612066174508125e-05 tokens_per_second_per_gpu:2197.89953310863 
Step 5834 | loss:2.087193489074707 lr:3.609039272683321e-05 tokens_per_second_per_gpu:2153.949779098461 
Step 5835 | loss:2.0590429306030273 lr:3.606013360379096e-05 tokens_per_second_per_gpu:2113.931394394488 
Step 5836 | loss:2.1081039905548096 lr:3.6029884380639654e-05 tokens_per_second_per_gpu:2199.201108626308 
Step 5837 | loss:1.9749075174331665 lr:3.5999645062062724e-05 tokens_per_second_per_gpu:2194.6839579616294 
Step 5838 | loss:2.096142530441284 lr:3.5969415652742186e-05 tokens_per_second_per_gpu:2162.912894292947 
Step 5839 | loss:2.0464353561401367 lr:3.5939196157358554e-05 tokens_per_second_per_gpu:2172.1572531290094 
Step 5840 | loss:2.061570167541504 lr:3.590898658059062e-05 tokens_per_second_per_gpu:2158.193979816343 
Step 5841 | loss:2.08096981048584 lr:3.5878786927115895e-05 tokens_per_second_per_gpu:2193.2712989393603 
Step 5842 | loss:2.069059133529663 lr:3.584859720161021e-05 tokens_per_second_per_gpu:2164.8099954136164 
Step 5843 | loss:2.092538356781006 lr:3.5818417408747826e-05 tokens_per_second_per_gpu:2172.518929439362 
Step 5844 | loss:2.1153404712677 lr:3.578824755320155e-05 tokens_per_second_per_gpu:2165.2124857399126 
Step 5845 | loss:2.0410172939300537 lr:3.575808763964261e-05 tokens_per_second_per_gpu:2196.148478923933 
Step 5846 | loss:2.103726387023926 lr:3.572793767274072e-05 tokens_per_second_per_gpu:2121.523382693654 
Step 5847 | loss:2.0835742950439453 lr:3.5697797657164035e-05 tokens_per_second_per_gpu:2153.763577996663 
Step 5848 | loss:2.1146676540374756 lr:3.566766759757919e-05 tokens_per_second_per_gpu:2185.4194810732333 
Step 5849 | loss:2.023219347000122 lr:3.5637547498651204e-05 tokens_per_second_per_gpu:2171.806378715385 
Step 5850 | loss:2.0219264030456543 lr:3.5607437365043636e-05 tokens_per_second_per_gpu:2183.924826044829 
Step 5851 | loss:2.091228485107422 lr:3.5577337201418496e-05 tokens_per_second_per_gpu:2195.3765605698804 
Step 5852 | loss:2.1072916984558105 lr:3.554724701243621e-05 tokens_per_second_per_gpu:2102.651349884661 
Step 5853 | loss:2.0868024826049805 lr:3.551716680275569e-05 tokens_per_second_per_gpu:2063.591854822309 
Step 5854 | loss:2.127899169921875 lr:3.548709657703433e-05 tokens_per_second_per_gpu:2134.3918744496336 
Step 5855 | loss:2.111203193664551 lr:3.545703633992786e-05 tokens_per_second_per_gpu:2182.615113628286 
Step 5856 | loss:2.0547678470611572 lr:3.542698609609059e-05 tokens_per_second_per_gpu:2197.563563715032 
Step 5857 | loss:2.1094231605529785 lr:3.539694585017523e-05 tokens_per_second_per_gpu:2133.250373466101 
Step 5858 | loss:2.014819383621216 lr:3.536691560683296e-05 tokens_per_second_per_gpu:2146.578373609769 
Step 5859 | loss:2.0764663219451904 lr:3.53368953707134e-05 tokens_per_second_per_gpu:2181.9971010965405 
Step 5860 | loss:2.0767602920532227 lr:3.530688514646464e-05 tokens_per_second_per_gpu:2197.117790942102 
Step 5861 | loss:2.0758495330810547 lr:3.5276884938733145e-05 tokens_per_second_per_gpu:2180.831545711483 
Step 5862 | loss:2.103105068206787 lr:3.5246894752163895e-05 tokens_per_second_per_gpu:2137.2228517747435 
Step 5863 | loss:2.090834617614746 lr:3.5216914591400386e-05 tokens_per_second_per_gpu:2127.112908988505 
Step 5864 | loss:2.066244125366211 lr:3.5186944461084405e-05 tokens_per_second_per_gpu:2194.0573077290182 
Step 5865 | loss:2.0566611289978027 lr:3.515698436585628e-05 tokens_per_second_per_gpu:2173.3272845541846 
Step 5866 | loss:2.05588698387146 lr:3.512703431035482e-05 tokens_per_second_per_gpu:2168.8613252482987 
Step 5867 | loss:2.086590528488159 lr:3.509709429921712e-05 tokens_per_second_per_gpu:2118.422003969574 
Step 5868 | loss:2.066519260406494 lr:3.5067164337078954e-05 tokens_per_second_per_gpu:2169.107489684695 
Step 5869 | loss:2.036803722381592 lr:3.5037244428574376e-05 tokens_per_second_per_gpu:2172.53725035352 
Step 5870 | loss:2.079364776611328 lr:3.5007334578335894e-05 tokens_per_second_per_gpu:2192.6930926811046 
Step 5871 | loss:2.0257182121276855 lr:3.497743479099449e-05 tokens_per_second_per_gpu:2195.8011706079633 
Step 5872 | loss:2.048442840576172 lr:3.494754507117964e-05 tokens_per_second_per_gpu:2195.4604321605884 
Step 5873 | loss:2.062824249267578 lr:3.4917665423519107e-05 tokens_per_second_per_gpu:2192.331649230247 
Step 5874 | loss:2.079437017440796 lr:3.4887795852639283e-05 tokens_per_second_per_gpu:2191.363067909838 
Step 5875 | loss:2.07550311088562 lr:3.4857936363164924e-05 tokens_per_second_per_gpu:2156.438549429463 
Step 5876 | loss:2.05893874168396 lr:3.482808695971913e-05 tokens_per_second_per_gpu:2134.595591864692 
Step 5877 | loss:2.071892023086548 lr:3.479824764692358e-05 tokens_per_second_per_gpu:2170.3876829186534 
Step 5878 | loss:2.065263271331787 lr:3.476841842939831e-05 tokens_per_second_per_gpu:2167.381598118636 
Step 5879 | loss:2.0641093254089355 lr:3.473859931176183e-05 tokens_per_second_per_gpu:2191.289744609601 
Step 5880 | loss:2.094235897064209 lr:3.470879029863107e-05 tokens_per_second_per_gpu:2185.7522489022904 
Step 5881 | loss:2.077265739440918 lr:3.467899139462142e-05 tokens_per_second_per_gpu:2183.807439063928 
Step 5882 | loss:2.099442481994629 lr:3.464920260434662e-05 tokens_per_second_per_gpu:2186.785007191872 
Step 5883 | loss:2.0543107986450195 lr:3.46194239324189e-05 tokens_per_second_per_gpu:2148.171400158213 
Step 5884 | loss:2.0530333518981934 lr:3.458965538344906e-05 tokens_per_second_per_gpu:2160.0128454793653 
Step 5885 | loss:2.080334424972534 lr:3.4559896962046066e-05 tokens_per_second_per_gpu:2127.4872789282113 
Step 5886 | loss:2.064509391784668 lr:3.453014867281752e-05 tokens_per_second_per_gpu:2191.573084362543 
Step 5887 | loss:2.0574874877929688 lr:3.4500410520369385e-05 tokens_per_second_per_gpu:2189.8665308654035 
Step 5888 | loss:2.076340913772583 lr:3.447068250930601e-05 tokens_per_second_per_gpu:2190.590016280917 
Step 5889 | loss:2.097496747970581 lr:3.444096464423021e-05 tokens_per_second_per_gpu:2189.408522193728 
Step 5890 | loss:2.042996406555176 lr:3.441125692974336e-05 tokens_per_second_per_gpu:2173.7782488816074 
Step 5891 | loss:2.035304069519043 lr:3.4381559370445025e-05 tokens_per_second_per_gpu:2169.1638946449093 
Step 5892 | loss:2.0571534633636475 lr:3.4351871970933355e-05 tokens_per_second_per_gpu:2109.7035953085924 
Step 5893 | loss:2.127448558807373 lr:3.432219473580492e-05 tokens_per_second_per_gpu:2141.341246851559 
Step 5894 | loss:2.1030778884887695 lr:3.4292527669654597e-05 tokens_per_second_per_gpu:2166.9330822661245 
Step 5895 | loss:2.0901851654052734 lr:3.426287077707585e-05 tokens_per_second_per_gpu:2195.6723815187083 
Step 5896 | loss:2.133965492248535 lr:3.4233224062660504e-05 tokens_per_second_per_gpu:2174.335424776844 
Step 5897 | loss:2.074321746826172 lr:3.420358753099875e-05 tokens_per_second_per_gpu:2186.0220913209337 
Step 5898 | loss:2.1383960247039795 lr:3.417396118667926e-05 tokens_per_second_per_gpu:2189.5472075086245 
Step 5899 | loss:2.1103262901306152 lr:3.414434503428913e-05 tokens_per_second_per_gpu:2195.6484459407584 
Step 5900 | loss:2.0271787643432617 lr:3.411473907841385e-05 tokens_per_second_per_gpu:2198.0689324542104 
Step 5901 | loss:2.0227417945861816 lr:3.408514332363737e-05 tokens_per_second_per_gpu:2178.0436026634775 
Step 5902 | loss:2.149761915206909 lr:3.405555777454206e-05 tokens_per_second_per_gpu:2101.4902263470995 
Step 5903 | loss:2.088994026184082 lr:3.4025982435708625e-05 tokens_per_second_per_gpu:2117.2651876106333 
Step 5904 | loss:2.042391300201416 lr:3.3996417311716275e-05 tokens_per_second_per_gpu:2200.273605150015 
Step 5905 | loss:2.0766119956970215 lr:3.396686240714263e-05 tokens_per_second_per_gpu:2179.70554232765 
Step 5906 | loss:2.0925607681274414 lr:3.393731772656371e-05 tokens_per_second_per_gpu:2146.211052905198 
Step 5907 | loss:2.0614662170410156 lr:3.390778327455396e-05 tokens_per_second_per_gpu:2186.2122112936186 
Step 5908 | loss:2.0903565883636475 lr:3.3878259055686255e-05 tokens_per_second_per_gpu:2181.7972452503477 
Step 5909 | loss:2.103032112121582 lr:3.384874507453182e-05 tokens_per_second_per_gpu:2184.396055600078 
Step 5910 | loss:2.062511920928955 lr:3.381924133566032e-05 tokens_per_second_per_gpu:2159.2699581136017 
Step 5911 | loss:2.0765700340270996 lr:3.378974784363997e-05 tokens_per_second_per_gpu:2161.906345230287 
Step 5912 | loss:2.11509370803833 lr:3.3760264603037196e-05 tokens_per_second_per_gpu:2181.826460168188 
Step 5913 | loss:2.043663263320923 lr:3.373079161841693e-05 tokens_per_second_per_gpu:2183.382690414646 
Step 5914 | loss:2.106782913208008 lr:3.3701328894342575e-05 tokens_per_second_per_gpu:2159.1078539739788 
Step 5915 | loss:2.082098960876465 lr:3.3671876435375795e-05 tokens_per_second_per_gpu:2186.9821855044834 
Step 5916 | loss:2.055771827697754 lr:3.364243424607676e-05 tokens_per_second_per_gpu:2179.132541013601 
Step 5917 | loss:2.0134706497192383 lr:3.361300233100414e-05 tokens_per_second_per_gpu:2094.7708414554495 
Step 5918 | loss:2.101698637008667 lr:3.3583580694714814e-05 tokens_per_second_per_gpu:2177.0912241888195 
Step 5919 | loss:2.098419666290283 lr:3.355416934176421e-05 tokens_per_second_per_gpu:2193.343726178371 
Step 5920 | loss:2.0005240440368652 lr:3.3524768276706155e-05 tokens_per_second_per_gpu:2176.6475065076474 
Step 5921 | loss:2.0670394897460938 lr:3.349537750409275e-05 tokens_per_second_per_gpu:2125.6407703185487 
Step 5922 | loss:2.0303542613983154 lr:3.3465997028474706e-05 tokens_per_second_per_gpu:2179.4352219843227 
Step 5923 | loss:2.074591636657715 lr:3.343662685440105e-05 tokens_per_second_per_gpu:2120.293726565829 
Step 5924 | loss:2.0715649127960205 lr:3.3407266986419125e-05 tokens_per_second_per_gpu:2081.495474425812 
Step 5925 | loss:2.0533018112182617 lr:3.33779174290748e-05 tokens_per_second_per_gpu:2154.9387692306705 
Step 5926 | loss:2.1044085025787354 lr:3.3348578186912295e-05 tokens_per_second_per_gpu:2194.385822990614 
Step 5927 | loss:2.106498956680298 lr:3.331924926447425e-05 tokens_per_second_per_gpu:2148.072378301969 
Step 5928 | loss:2.0462899208068848 lr:3.328993066630169e-05 tokens_per_second_per_gpu:2176.8070932562177 
Step 5929 | loss:2.0867972373962402 lr:3.326062239693409e-05 tokens_per_second_per_gpu:2191.59519118627 
Step 5930 | loss:2.0198323726654053 lr:3.323132446090923e-05 tokens_per_second_per_gpu:2141.1302355396583 
Step 5931 | loss:2.0840678215026855 lr:3.320203686276336e-05 tokens_per_second_per_gpu:2139.30423884709 
Step 5932 | loss:2.075401544570923 lr:3.3172759607031125e-05 tokens_per_second_per_gpu:2188.4538081003993 
Step 5933 | loss:2.045010566711426 lr:3.314349269824557e-05 tokens_per_second_per_gpu:2179.7602195755994 
Step 5934 | loss:2.050539970397949 lr:3.3114236140938104e-05 tokens_per_second_per_gpu:2088.965699430837 
Step 5935 | loss:2.119960069656372 lr:3.308498993963861e-05 tokens_per_second_per_gpu:2189.3877970079748 
Step 5936 | loss:2.039714813232422 lr:3.3055754098875244e-05 tokens_per_second_per_gpu:2154.0677319783754 
Step 5937 | loss:2.0453615188598633 lr:3.302652862317464e-05 tokens_per_second_per_gpu:2129.305165532182 
Step 5938 | loss:2.0049235820770264 lr:3.2997313517061876e-05 tokens_per_second_per_gpu:2192.876167628714 
Step 5939 | loss:2.098923683166504 lr:3.296810878506031e-05 tokens_per_second_per_gpu:2147.4842323866046 
Step 5940 | loss:2.078638792037964 lr:3.293891443169176e-05 tokens_per_second_per_gpu:2190.6673613693742 
Step 5941 | loss:2.0991368293762207 lr:3.290973046147645e-05 tokens_per_second_per_gpu:2102.3028302534276 
Step 5942 | loss:2.0969321727752686 lr:3.288055687893289e-05 tokens_per_second_per_gpu:2167.5818908931274 
Step 5943 | loss:2.07136869430542 lr:3.285139368857816e-05 tokens_per_second_per_gpu:2191.0089249067546 
Step 5944 | loss:2.110421895980835 lr:3.2822240894927614e-05 tokens_per_second_per_gpu:2172.671114893173 
Step 5945 | loss:2.016803026199341 lr:3.279309850249497e-05 tokens_per_second_per_gpu:2189.766511822228 
Step 5946 | loss:2.112212657928467 lr:3.27639665157924e-05 tokens_per_second_per_gpu:2191.39776783906 
Step 5947 | loss:2.071544647216797 lr:3.27348449393305e-05 tokens_per_second_per_gpu:2191.6754953064337 
Step 5948 | loss:2.109206199645996 lr:3.270573377761809e-05 tokens_per_second_per_gpu:2177.6956249147206 
Step 5949 | loss:2.0664150714874268 lr:3.2676633035162576e-05 tokens_per_second_per_gpu:2106.6694687535414 
Step 5950 | loss:2.0075464248657227 lr:3.264754271646968e-05 tokens_per_second_per_gpu:2188.7799033515303 
Step 5951 | loss:2.0700089931488037 lr:3.2618462826043426e-05 tokens_per_second_per_gpu:2159.489721839409 
Step 5952 | loss:2.0201311111450195 lr:3.258939336838631e-05 tokens_per_second_per_gpu:2195.718638311214 
Step 5953 | loss:2.0632898807525635 lr:3.256033434799921e-05 tokens_per_second_per_gpu:2156.1879373291276 
Step 5954 | loss:2.1011743545532227 lr:3.253128576938136e-05 tokens_per_second_per_gpu:2158.565566084044 
Step 5955 | loss:2.0835206508636475 lr:3.250224763703038e-05 tokens_per_second_per_gpu:2188.104716002456 
Step 5956 | loss:2.0014569759368896 lr:3.2473219955442334e-05 tokens_per_second_per_gpu:2193.59498109575 
Step 5957 | loss:2.057502508163452 lr:3.244420272911154e-05 tokens_per_second_per_gpu:2189.021982898303 
Step 5958 | loss:2.100499153137207 lr:3.241519596253081e-05 tokens_per_second_per_gpu:2136.1492969510537 
Step 5959 | loss:2.0646438598632812 lr:3.2386199660191285e-05 tokens_per_second_per_gpu:2168.561345790605 
Step 5960 | loss:2.084392547607422 lr:3.235721382658252e-05 tokens_per_second_per_gpu:2196.891085853931 
Step 5961 | loss:2.1040093898773193 lr:3.232823846619241e-05 tokens_per_second_per_gpu:2117.11164543944 
Step 5962 | loss:2.0154099464416504 lr:3.2299273583507286e-05 tokens_per_second_per_gpu:2115.6755692784022 
Step 5963 | loss:2.1071505546569824 lr:3.227031918301174e-05 tokens_per_second_per_gpu:2195.3042670545915 
Step 5964 | loss:2.0316340923309326 lr:3.2241375269188844e-05 tokens_per_second_per_gpu:2139.8409112645263 
Step 5965 | loss:2.037018299102783 lr:3.2212441846520115e-05 tokens_per_second_per_gpu:2150.596052188316 
Step 5966 | loss:2.0739381313323975 lr:3.218351891948522e-05 tokens_per_second_per_gpu:2134.961815970621 
Step 5967 | loss:2.080446243286133 lr:3.2154606492562414e-05 tokens_per_second_per_gpu:2165.9903277476815 
Step 5968 | loss:2.0998892784118652 lr:3.2125704570228246e-05 tokens_per_second_per_gpu:2192.7012803309303 
Step 5969 | loss:2.056610584259033 lr:3.209681315695754e-05 tokens_per_second_per_gpu:2184.2950190634183 
Step 5970 | loss:2.018810749053955 lr:3.20679322572237e-05 tokens_per_second_per_gpu:2177.363107323771 
Step 5971 | loss:2.108659505844116 lr:3.203906187549839e-05 tokens_per_second_per_gpu:2189.281117372836 
Step 5972 | loss:2.1093664169311523 lr:3.201020201625158e-05 tokens_per_second_per_gpu:2162.321763574926 
Step 5973 | loss:2.15220308303833 lr:3.19813526839517e-05 tokens_per_second_per_gpu:2111.9768555883543 
Step 5974 | loss:2.074867010116577 lr:3.195251388306559e-05 tokens_per_second_per_gpu:2159.207621851506 
Step 5975 | loss:2.044839382171631 lr:3.192368561805828e-05 tokens_per_second_per_gpu:2180.679860721437 
Step 5976 | loss:2.155799388885498 lr:3.1894867893393386e-05 tokens_per_second_per_gpu:2169.2289605961123 
Step 5977 | loss:2.0726184844970703 lr:3.186606071353278e-05 tokens_per_second_per_gpu:2143.0289109021282 
Step 5978 | loss:2.0874099731445312 lr:3.183726408293669e-05 tokens_per_second_per_gpu:2145.187281028882 
Step 5979 | loss:2.046236991882324 lr:3.180847800606374e-05 tokens_per_second_per_gpu:2121.719816927688 
Step 5980 | loss:2.0836992263793945 lr:3.17797024873709e-05 tokens_per_second_per_gpu:2168.628405081034 
Step 5981 | loss:2.0177009105682373 lr:3.175093753131354e-05 tokens_per_second_per_gpu:2113.0324647931307 
Step 5982 | loss:2.093898296356201 lr:3.172218314234538e-05 tokens_per_second_per_gpu:2189.369711285342 
Step 5983 | loss:2.0714128017425537 lr:3.1693439324918515e-05 tokens_per_second_per_gpu:2184.010565130619 
Step 5984 | loss:2.0835273265838623 lr:3.166470608348334e-05 tokens_per_second_per_gpu:2176.654818923454 
Step 5985 | loss:2.0604848861694336 lr:3.163598342248864e-05 tokens_per_second_per_gpu:2163.4491450080372 
Step 5986 | loss:2.0227932929992676 lr:3.1607271346381695e-05 tokens_per_second_per_gpu:2181.52267511011 
Step 5987 | loss:2.1204590797424316 lr:3.157856985960792e-05 tokens_per_second_per_gpu:2174.007991013058 
Step 5988 | loss:2.072237491607666 lr:3.1549878966611245e-05 tokens_per_second_per_gpu:2152.958823445559 
Step 5989 | loss:2.053170680999756 lr:3.1521198671833954e-05 tokens_per_second_per_gpu:2142.6685198374803 
Step 5990 | loss:2.1347522735595703 lr:3.149252897971657e-05 tokens_per_second_per_gpu:2158.597876074408 
Step 5991 | loss:1.998859167098999 lr:3.1463869894698084e-05 tokens_per_second_per_gpu:2166.452759952004 
Step 5992 | loss:2.1030960083007812 lr:3.1435221421215896e-05 tokens_per_second_per_gpu:2150.438866896758 
Step 5993 | loss:2.0815324783325195 lr:3.1406583563705595e-05 tokens_per_second_per_gpu:2174.098997332123 
Step 5994 | loss:2.021967649459839 lr:3.137795632660126e-05 tokens_per_second_per_gpu:2193.5794161354297 
Step 5995 | loss:2.044107675552368 lr:3.1349339714335277e-05 tokens_per_second_per_gpu:2148.092783877477 
Step 5996 | loss:2.1179111003875732 lr:3.132073373133835e-05 tokens_per_second_per_gpu:2189.5996249648974 
Step 5997 | loss:2.059978485107422 lr:3.129213838203964e-05 tokens_per_second_per_gpu:2183.2720353207383 
Step 5998 | loss:2.0330543518066406 lr:3.1263553670866596e-05 tokens_per_second_per_gpu:2175.562906880597 
Step 5999 | loss:2.0232813358306885 lr:3.123497960224498e-05 tokens_per_second_per_gpu:2150.72364877853 
Step 6000 | loss:2.1410672664642334 lr:3.1206416180598995e-05 tokens_per_second_per_gpu:2173.680643146777 
Step 6001 | loss:2.0964860916137695 lr:3.1177863410351126e-05 tokens_per_second_per_gpu:2134.37801662274 
Step 6002 | loss:2.0749075412750244 lr:3.1149321295922243e-05 tokens_per_second_per_gpu:2102.890013807642 
Step 6003 | loss:2.14939022064209 lr:3.1120789841731556e-05 tokens_per_second_per_gpu:2126.716381285586 
Step 6004 | loss:2.075921058654785 lr:3.1092269052196666e-05 tokens_per_second_per_gpu:2127.663188689431 
Step 6005 | loss:2.13618540763855 lr:3.1063758931733414e-05 tokens_per_second_per_gpu:2141.208940920366 
Step 6006 | loss:2.0600972175598145 lr:3.1035259484756094e-05 tokens_per_second_per_gpu:2163.26964484525 
Step 6007 | loss:2.0527355670928955 lr:3.10067707156773e-05 tokens_per_second_per_gpu:2195.18434467372 
Step 6008 | loss:2.0871732234954834 lr:3.0978292628908004e-05 tokens_per_second_per_gpu:2179.7025136493394 
Step 6009 | loss:2.1770572662353516 lr:3.094982522885749e-05 tokens_per_second_per_gpu:2188.7617006218097 
Step 6010 | loss:2.0623292922973633 lr:3.0921368519933425e-05 tokens_per_second_per_gpu:2101.9088459237087 
Step 6011 | loss:2.0797829627990723 lr:3.089292250654175e-05 tokens_per_second_per_gpu:2163.072732473974 
Step 6012 | loss:2.073150157928467 lr:3.086448719308681e-05 tokens_per_second_per_gpu:2146.712276420179 
Step 6013 | loss:2.0507969856262207 lr:3.0836062583971345e-05 tokens_per_second_per_gpu:2150.703432985497 
Step 6014 | loss:2.118439197540283 lr:3.080764868359629e-05 tokens_per_second_per_gpu:2148.928645707897 
Step 6015 | loss:2.0471160411834717 lr:3.0779245496361044e-05 tokens_per_second_per_gpu:2184.5080728168155 
Step 6016 | loss:2.08119535446167 lr:3.075085302666334e-05 tokens_per_second_per_gpu:2158.6191501710023 
Step 6017 | loss:2.0697622299194336 lr:3.072247127889915e-05 tokens_per_second_per_gpu:2178.0222465996785 
Step 6018 | loss:2.051954746246338 lr:3.0694100257462855e-05 tokens_per_second_per_gpu:2182.9256169819205 
Step 6019 | loss:2.052412986755371 lr:3.066573996674728e-05 tokens_per_second_per_gpu:2137.8761538528433 
Step 6020 | loss:2.1111021041870117 lr:3.063739041114339e-05 tokens_per_second_per_gpu:2150.6316580593343 
Step 6021 | loss:2.053439140319824 lr:3.0609051595040595e-05 tokens_per_second_per_gpu:2157.052108370147 
Step 6022 | loss:2.1030189990997314 lr:3.058072352282668e-05 tokens_per_second_per_gpu:2157.279849629364 
Step 6023 | loss:2.025857448577881 lr:3.055240619888763e-05 tokens_per_second_per_gpu:2162.082435912538 
Step 6024 | loss:2.056095600128174 lr:3.0524099627607916e-05 tokens_per_second_per_gpu:2164.99238591764 
Step 6025 | loss:2.0509486198425293 lr:3.0495803813370315e-05 tokens_per_second_per_gpu:2181.766346371799 
Step 6026 | loss:2.054290294647217 lr:3.046751876055581e-05 tokens_per_second_per_gpu:2161.534870148011 
Step 6027 | loss:2.003744602203369 lr:3.043924447354387e-05 tokens_per_second_per_gpu:2182.392225854225 
Step 6028 | loss:2.0386416912078857 lr:3.041098095671223e-05 tokens_per_second_per_gpu:2121.44106210091 
Step 6029 | loss:2.1146368980407715 lr:3.038272821443696e-05 tokens_per_second_per_gpu:2189.9365145473494 
Step 6030 | loss:2.052192211151123 lr:3.0354486251092472e-05 tokens_per_second_per_gpu:2186.108016520999 
Step 6031 | loss:2.0395193099975586 lr:3.0326255071051534e-05 tokens_per_second_per_gpu:2156.153394822383 
Step 6032 | loss:2.0378026962280273 lr:3.029803467868515e-05 tokens_per_second_per_gpu:2113.2691190014325 
Step 6033 | loss:2.0492868423461914 lr:3.0269825078362756e-05 tokens_per_second_per_gpu:2193.045573346315 
Step 6034 | loss:2.0769145488739014 lr:3.0241626274452085e-05 tokens_per_second_per_gpu:2031.516664035183 
Step 6035 | loss:2.0844075679779053 lr:3.0213438271319193e-05 tokens_per_second_per_gpu:2108.1873202637657 
Step 6036 | loss:2.043665885925293 lr:3.0185261073328452e-05 tokens_per_second_per_gpu:2184.8435766184075 
Step 6037 | loss:2.0759315490722656 lr:3.0157094684842614e-05 tokens_per_second_per_gpu:2152.6152570426184 
Step 6038 | loss:2.1017751693725586 lr:3.0128939110222655e-05 tokens_per_second_per_gpu:2152.2382980175403 
Step 6039 | loss:2.1210126876831055 lr:3.0100794353827934e-05 tokens_per_second_per_gpu:2188.321513406785 
Step 6040 | loss:2.0868587493896484 lr:3.007266042001623e-05 tokens_per_second_per_gpu:2190.161608706097 
Step 6041 | loss:2.0663180351257324 lr:3.0044537313143474e-05 tokens_per_second_per_gpu:2190.1512426436916 
Step 6042 | loss:2.088357448577881 lr:3.0016425037564032e-05 tokens_per_second_per_gpu:2161.5497650543184 
Step 6043 | loss:2.0346503257751465 lr:2.9988323597630586e-05 tokens_per_second_per_gpu:2149.736981907835 
Step 6044 | loss:2.096125364303589 lr:2.9960232997694026e-05 tokens_per_second_per_gpu:2099.506605694157 
Step 6045 | loss:2.066322088241577 lr:2.9932153242103744e-05 tokens_per_second_per_gpu:2116.9683073017964 
Step 6046 | loss:2.0729455947875977 lr:2.9904084335207383e-05 tokens_per_second_per_gpu:2117.411966766429 
Step 6047 | loss:2.0542285442352295 lr:2.98760262813508e-05 tokens_per_second_per_gpu:2189.0607079168517 
Step 6048 | loss:2.057199001312256 lr:2.9847979084878318e-05 tokens_per_second_per_gpu:2150.0188059665284 
Step 6049 | loss:2.055093288421631 lr:2.9819942750132534e-05 tokens_per_second_per_gpu:2181.4764721656516 
Step 6050 | loss:2.065135955810547 lr:2.979191728145425e-05 tokens_per_second_per_gpu:2159.6118700649095 
Step 6051 | loss:1.997991919517517 lr:2.9763902683182786e-05 tokens_per_second_per_gpu:2176.3599052602885 
Step 6052 | loss:2.104006290435791 lr:2.9735898959655694e-05 tokens_per_second_per_gpu:2189.6484572700506 
Step 6053 | loss:2.026836395263672 lr:2.970790611520874e-05 tokens_per_second_per_gpu:2186.829676269406 
Step 6054 | loss:2.0017051696777344 lr:2.967992415417613e-05 tokens_per_second_per_gpu:2156.254140167692 
Step 6055 | loss:2.0380301475524902 lr:2.965195308089035e-05 tokens_per_second_per_gpu:2177.34132602233 
Step 6056 | loss:2.104576349258423 lr:2.9623992899682195e-05 tokens_per_second_per_gpu:2185.5764135362338 
Step 6057 | loss:2.097970962524414 lr:2.9596043614880776e-05 tokens_per_second_per_gpu:2177.270031406549 
Step 6058 | loss:2.055436849594116 lr:2.9568105230813547e-05 tokens_per_second_per_gpu:2148.3765896730333 
Step 6059 | loss:2.098428964614868 lr:2.9540177751806186e-05 tokens_per_second_per_gpu:2169.116123598416 
Step 6060 | loss:2.0530757904052734 lr:2.951226118218273e-05 tokens_per_second_per_gpu:2185.6262392427425 
Step 6061 | loss:2.0734975337982178 lr:2.9484355526265638e-05 tokens_per_second_per_gpu:2106.1924595991136 
Step 6062 | loss:2.1033387184143066 lr:2.9456460788375484e-05 tokens_per_second_per_gpu:2163.855672381085 
Step 6063 | loss:2.0978798866271973 lr:2.9428576972831278e-05 tokens_per_second_per_gpu:2156.730780539296 
Step 6064 | loss:2.021944522857666 lr:2.9400704083950335e-05 tokens_per_second_per_gpu:2163.7346405994404 
Step 6065 | loss:2.111790895462036 lr:2.9372842126048185e-05 tokens_per_second_per_gpu:2118.337700365027 
Step 6066 | loss:2.035524845123291 lr:2.9344991103438735e-05 tokens_per_second_per_gpu:2139.2693941648968 
Step 6067 | loss:2.073195219039917 lr:2.9317151020434287e-05 tokens_per_second_per_gpu:2158.994486288392 
Step 6068 | loss:2.036374092102051 lr:2.9289321881345254e-05 tokens_per_second_per_gpu:2168.9679617746096 
Step 6069 | loss:2.0744986534118652 lr:2.926150369048051e-05 tokens_per_second_per_gpu:2189.4193184330734 
Step 6070 | loss:1.997108817100525 lr:2.9233696452147187e-05 tokens_per_second_per_gpu:2157.1588079699573 
Step 6071 | loss:2.076282024383545 lr:2.9205900170650635e-05 tokens_per_second_per_gpu:2182.3317893496696 
Step 6072 | loss:2.1155014038085938 lr:2.917811485029468e-05 tokens_per_second_per_gpu:2102.7494515169687 
Step 6073 | loss:2.101822853088379 lr:2.915034049538137e-05 tokens_per_second_per_gpu:2110.5041545105114 
Step 6074 | loss:2.0311503410339355 lr:2.912257711021096e-05 tokens_per_second_per_gpu:2192.0706743192604 
Step 6075 | loss:2.0907135009765625 lr:2.9094824699082123e-05 tokens_per_second_per_gpu:2188.46435484226 
Step 6076 | loss:2.070066452026367 lr:2.906708326629184e-05 tokens_per_second_per_gpu:2139.953773826329 
Step 6077 | loss:2.084895133972168 lr:2.903935281613527e-05 tokens_per_second_per_gpu:2190.006850373285 
Step 6078 | loss:2.025998592376709 lr:2.901163335290602e-05 tokens_per_second_per_gpu:2145.9109742607884 
Step 6079 | loss:2.0102458000183105 lr:2.8983924880895964e-05 tokens_per_second_per_gpu:2048.9458099985814 
Step 6080 | loss:2.090757369995117 lr:2.895622740439514e-05 tokens_per_second_per_gpu:2176.541736644036 
Step 6081 | loss:2.078367233276367 lr:2.8928540927692038e-05 tokens_per_second_per_gpu:2138.3696048983556 
Step 6082 | loss:2.077200412750244 lr:2.8900865455073388e-05 tokens_per_second_per_gpu:2178.7733758521276 
Step 6083 | loss:2.061729907989502 lr:2.8873200990824224e-05 tokens_per_second_per_gpu:2148.639287943051 
Step 6084 | loss:2.114976406097412 lr:2.8845547539227848e-05 tokens_per_second_per_gpu:2173.079639082876 
Step 6085 | loss:2.0757126808166504 lr:2.8817905104565934e-05 tokens_per_second_per_gpu:2144.942044147497 
Step 6086 | loss:2.0951967239379883 lr:2.879027369111832e-05 tokens_per_second_per_gpu:2060.6478033501403 
Step 6087 | loss:2.024886131286621 lr:2.8762653303163222e-05 tokens_per_second_per_gpu:2189.3747214182704 
Step 6088 | loss:2.0873260498046875 lr:2.8735043944977223e-05 tokens_per_second_per_gpu:2185.1720227441606 
Step 6089 | loss:2.09059476852417 lr:2.8707445620835027e-05 tokens_per_second_per_gpu:2140.2563591677877 
Step 6090 | loss:2.0807368755340576 lr:2.8679858335009745e-05 tokens_per_second_per_gpu:2170.0643736107777 
Step 6091 | loss:2.1459317207336426 lr:2.86522820917728e-05 tokens_per_second_per_gpu:2174.6257441356347 
Step 6092 | loss:2.0941410064697266 lr:2.8624716895393766e-05 tokens_per_second_per_gpu:2180.2078518177937 
Step 6093 | loss:2.0932416915893555 lr:2.8597162750140615e-05 tokens_per_second_per_gpu:2191.5956003761526 
Step 6094 | loss:2.07947039604187 lr:2.856961966027968e-05 tokens_per_second_per_gpu:2188.197696147234 
Step 6095 | loss:2.0166714191436768 lr:2.85420876300754e-05 tokens_per_second_per_gpu:2159.6378040039867 
Step 6096 | loss:2.065533399581909 lr:2.851456666379063e-05 tokens_per_second_per_gpu:2119.362489113115 
Step 6097 | loss:2.042024612426758 lr:2.8487056765686505e-05 tokens_per_second_per_gpu:2124.378148422787 
Step 6098 | loss:2.0370922088623047 lr:2.8459557940022318e-05 tokens_per_second_per_gpu:2166.897748380541 
Step 6099 | loss:2.0319082736968994 lr:2.8432070191055836e-05 tokens_per_second_per_gpu:2130.609775606494 
Step 6100 | loss:2.0227034091949463 lr:2.8404593523043045e-05 tokens_per_second_per_gpu:2131.763505050224 
Step 6101 | loss:2.012556552886963 lr:2.83771279402381e-05 tokens_per_second_per_gpu:2180.8315170568553 
Step 6102 | loss:2.0477981567382812 lr:2.8349673446893597e-05 tokens_per_second_per_gpu:2154.9047062306054 
Step 6103 | loss:2.0875775814056396 lr:2.8322230047260322e-05 tokens_per_second_per_gpu:2135.441305923458 
Step 6104 | loss:2.035372257232666 lr:2.8294797745587386e-05 tokens_per_second_per_gpu:2153.775098189414 
Step 6105 | loss:2.0067200660705566 lr:2.826737654612216e-05 tokens_per_second_per_gpu:2122.0011528954697 
Step 6106 | loss:2.077080726623535 lr:2.8239966453110332e-05 tokens_per_second_per_gpu:2186.904400386388 
Step 6107 | loss:2.097710371017456 lr:2.821256747079579e-05 tokens_per_second_per_gpu:2155.7509740291166 
Step 6108 | loss:2.0677661895751953 lr:2.8185179603420785e-05 tokens_per_second_per_gpu:2178.7360420229056 
Step 6109 | loss:2.06061053276062 lr:2.81578028552258e-05 tokens_per_second_per_gpu:2189.4062864241355 
Step 6110 | loss:2.082712173461914 lr:2.8130437230449624e-05 tokens_per_second_per_gpu:2134.864683827293 
Step 6111 | loss:2.0702457427978516 lr:2.810308273332931e-05 tokens_per_second_per_gpu:2093.621560540049 
Step 6112 | loss:2.047999382019043 lr:2.807573936810023e-05 tokens_per_second_per_gpu:2156.6175470661183 
Step 6113 | loss:2.0122740268707275 lr:2.80484071389959e-05 tokens_per_second_per_gpu:2159.9572920390906 
Step 6114 | loss:2.0393755435943604 lr:2.8021086050248234e-05 tokens_per_second_per_gpu:2159.605238530385 
Step 6115 | loss:2.062647819519043 lr:2.7993776106087476e-05 tokens_per_second_per_gpu:2162.4821115191717 
Step 6116 | loss:2.107365608215332 lr:2.7966477310741956e-05 tokens_per_second_per_gpu:2188.2641325799527 
Step 6117 | loss:2.0926766395568848 lr:2.7939189668438414e-05 tokens_per_second_per_gpu:2173.2755095751527 
Step 6118 | loss:2.154027223587036 lr:2.7911913183401883e-05 tokens_per_second_per_gpu:2052.451210632242 
Step 6119 | loss:2.039126396179199 lr:2.7884647859855494e-05 tokens_per_second_per_gpu:2114.0727571472435 
Step 6120 | loss:2.0719757080078125 lr:2.7857393702020886e-05 tokens_per_second_per_gpu:2151.8500246032463 
Step 6121 | loss:2.0334558486938477 lr:2.783015071411784e-05 tokens_per_second_per_gpu:2140.8706574149573 
Step 6122 | loss:2.0737950801849365 lr:2.780291890036437e-05 tokens_per_second_per_gpu:2158.8027351640353 
Step 6123 | loss:2.0233051776885986 lr:2.7775698264976846e-05 tokens_per_second_per_gpu:2169.6001859422895 
Step 6124 | loss:2.079403877258301 lr:2.7748488812169892e-05 tokens_per_second_per_gpu:2185.29819412647 
Step 6125 | loss:2.096630811691284 lr:2.7721290546156298e-05 tokens_per_second_per_gpu:2181.0898818969445 
Step 6126 | loss:2.0677614212036133 lr:2.7694103471147292e-05 tokens_per_second_per_gpu:2190.249550105146 
Step 6127 | loss:2.0519495010375977 lr:2.76669275913523e-05 tokens_per_second_per_gpu:2161.630296328516 
Step 6128 | loss:2.1095423698425293 lr:2.7639762910978916e-05 tokens_per_second_per_gpu:2182.701128556531 
Step 6129 | loss:2.062243700027466 lr:2.7612609434233126e-05 tokens_per_second_per_gpu:2187.5628120519477 
Step 6130 | loss:2.0202112197875977 lr:2.7585467165319136e-05 tokens_per_second_per_gpu:2166.5997908551194 
Step 6131 | loss:2.036576986312866 lr:2.755833610843941e-05 tokens_per_second_per_gpu:2169.090914571803 
Step 6132 | loss:2.0513627529144287 lr:2.753121626779469e-05 tokens_per_second_per_gpu:2120.6109684760304 
Step 6133 | loss:2.0805084705352783 lr:2.750410764758401e-05 tokens_per_second_per_gpu:2193.4833891691756 
Step 6134 | loss:2.0826005935668945 lr:2.7477010252004566e-05 tokens_per_second_per_gpu:2175.159061462796 
Step 6135 | loss:2.066281795501709 lr:2.744992408525191e-05 tokens_per_second_per_gpu:2085.1799038065224 
Step 6136 | loss:2.079073905944824 lr:2.7422849151519824e-05 tokens_per_second_per_gpu:2151.7089772128024 
Step 6137 | loss:2.098008632659912 lr:2.739578545500038e-05 tokens_per_second_per_gpu:2162.3254743189777 
Step 6138 | loss:2.1088767051696777 lr:2.736873299988385e-05 tokens_per_second_per_gpu:2077.860636159463 
Step 6139 | loss:2.045891761779785 lr:2.734169179035885e-05 tokens_per_second_per_gpu:2158.9147627970146 
Step 6140 | loss:2.105898141860962 lr:2.7314661830612144e-05 tokens_per_second_per_gpu:2189.121916611685 
Step 6141 | loss:2.0253050327301025 lr:2.728764312482881e-05 tokens_per_second_per_gpu:2191.825284987582 
Step 6142 | loss:2.073512554168701 lr:2.726063567719228e-05 tokens_per_second_per_gpu:2172.589690783403 
Step 6143 | loss:2.020333766937256 lr:2.7233639491884067e-05 tokens_per_second_per_gpu:2189.1785571061564 
Step 6144 | loss:2.020921230316162 lr:2.7206654573084046e-05 tokens_per_second_per_gpu:2186.267740067054 
Step 6145 | loss:2.0778756141662598 lr:2.717968092497035e-05 tokens_per_second_per_gpu:2181.6536879466585 
Step 6146 | loss:2.0384111404418945 lr:2.7152718551719282e-05 tokens_per_second_per_gpu:2175.286616627044 
Step 6147 | loss:2.0437710285186768 lr:2.7125767457505514e-05 tokens_per_second_per_gpu:2172.017550911674 
Step 6148 | loss:2.066153049468994 lr:2.7098827646501945e-05 tokens_per_second_per_gpu:2164.1809779634623 
Step 6149 | loss:2.064305543899536 lr:2.707189912287963e-05 tokens_per_second_per_gpu:2190.7386702887 
Step 6150 | loss:2.076462745666504 lr:2.7044981890807987e-05 tokens_per_second_per_gpu:2153.2637625830316 
Step 6151 | loss:2.1061501502990723 lr:2.7018075954454658e-05 tokens_per_second_per_gpu:2169.5989994948272 
Step 6152 | loss:2.060316562652588 lr:2.6991181317985436e-05 tokens_per_second_per_gpu:2167.5598891971167 
Step 6153 | loss:2.0867207050323486 lr:2.6964297985564556e-05 tokens_per_second_per_gpu:2180.210956661647 
Step 6154 | loss:2.0698704719543457 lr:2.6937425961354378e-05 tokens_per_second_per_gpu:2163.76193724089 
Step 6155 | loss:2.0852370262145996 lr:2.6910565249515497e-05 tokens_per_second_per_gpu:2169.4894393877125 
Step 6156 | loss:2.0676472187042236 lr:2.6883715854206804e-05 tokens_per_second_per_gpu:2190.675777902774 
Step 6157 | loss:2.0708844661712646 lr:2.6856877779585432e-05 tokens_per_second_per_gpu:2163.8906110412318 
Step 6158 | loss:2.0418272018432617 lr:2.6830051029806746e-05 tokens_per_second_per_gpu:2167.1749097972333 
Step 6159 | loss:2.0309274196624756 lr:2.680323560902437e-05 tokens_per_second_per_gpu:2176.0520002541484 
Step 6160 | loss:2.060924530029297 lr:2.67764315213902e-05 tokens_per_second_per_gpu:2163.5954217851677 
Step 6161 | loss:2.148519992828369 lr:2.6749638771054298e-05 tokens_per_second_per_gpu:2101.021349535419 
Step 6162 | loss:2.064798355102539 lr:2.6722857362165e-05 tokens_per_second_per_gpu:2163.91454957402 
Step 6163 | loss:2.0622968673706055 lr:2.6696087298869e-05 tokens_per_second_per_gpu:2129.6392181487467 
Step 6164 | loss:2.0579261779785156 lr:2.666932858531107e-05 tokens_per_second_per_gpu:2186.373980236391 
Step 6165 | loss:2.100985288619995 lr:2.66425812256343e-05 tokens_per_second_per_gpu:2150.2534876614295 
Step 6166 | loss:2.0543413162231445 lr:2.661584522398006e-05 tokens_per_second_per_gpu:2113.303376552852 
Step 6167 | loss:2.1154260635375977 lr:2.658912058448787e-05 tokens_per_second_per_gpu:2181.0343336523433 
Step 6168 | loss:2.034885883331299 lr:2.6562407311295512e-05 tokens_per_second_per_gpu:2124.57997391934 
Step 6169 | loss:2.105699300765991 lr:2.6535705408539157e-05 tokens_per_second_per_gpu:2144.9901721924293 
Step 6170 | loss:2.0743677616119385 lr:2.650901488035298e-05 tokens_per_second_per_gpu:2120.236361603454 
Step 6171 | loss:2.0013015270233154 lr:2.6482335730869556e-05 tokens_per_second_per_gpu:2156.827416676594 
Step 6172 | loss:2.082712173461914 lr:2.6455667964219665e-05 tokens_per_second_per_gpu:2138.989403154079 
Step 6173 | loss:2.057943344116211 lr:2.6429011584532237e-05 tokens_per_second_per_gpu:2153.8924590771185 
Step 6174 | loss:2.077035665512085 lr:2.64023665959346e-05 tokens_per_second_per_gpu:2160.252250961556 
Step 6175 | loss:2.093599319458008 lr:2.6375733002552228e-05 tokens_per_second_per_gpu:2170.784707437456 
Step 6176 | loss:2.098414897918701 lr:2.634911080850878e-05 tokens_per_second_per_gpu:2192.865712115766 
Step 6177 | loss:2.0333704948425293 lr:2.632250001792622e-05 tokens_per_second_per_gpu:2189.113187773761 
Step 6178 | loss:2.0898516178131104 lr:2.6295900634924754e-05 tokens_per_second_per_gpu:2176.450939681652 
Step 6179 | loss:2.0574700832366943 lr:2.626931266362277e-05 tokens_per_second_per_gpu:2142.4854272521634 
Step 6180 | loss:2.0373177528381348 lr:2.6242736108136933e-05 tokens_per_second_per_gpu:2143.527276503386 
Step 6181 | loss:2.0591964721679688 lr:2.6216170972582166e-05 tokens_per_second_per_gpu:2185.032563708677 
Step 6182 | loss:2.113541603088379 lr:2.6189617261071496e-05 tokens_per_second_per_gpu:2104.540125865976 
Step 6183 | loss:2.0074622631073 lr:2.6163074977716317e-05 tokens_per_second_per_gpu:2188.3244846268717 
Step 6184 | loss:2.064429759979248 lr:2.6136544126626204e-05 tokens_per_second_per_gpu:2089.5805189918556 
Step 6185 | loss:2.051419973373413 lr:2.6110024711908954e-05 tokens_per_second_per_gpu:2121.4931174716035 
Step 6186 | loss:1.989201307296753 lr:2.608351673767061e-05 tokens_per_second_per_gpu:2172.6009260382616 
Step 6187 | loss:2.0647404193878174 lr:2.605702020801546e-05 tokens_per_second_per_gpu:2096.8477440650313 
Step 6188 | loss:2.0364573001861572 lr:2.603053512704593e-05 tokens_per_second_per_gpu:2167.4698921500662 
Step 6189 | loss:2.093014717102051 lr:2.6004061498862752e-05 tokens_per_second_per_gpu:2095.946756073763 
Step 6190 | loss:2.052614450454712 lr:2.597759932756495e-05 tokens_per_second_per_gpu:2187.2540579010906 
Step 6191 | loss:2.024773597717285 lr:2.595114861724962e-05 tokens_per_second_per_gpu:2153.966140907948 
Step 6192 | loss:2.093230724334717 lr:2.592470937201217e-05 tokens_per_second_per_gpu:2185.6437674630292 
Step 6193 | loss:2.097116708755493 lr:2.589828159594626e-05 tokens_per_second_per_gpu:2093.078119746315 
Step 6194 | loss:2.1112873554229736 lr:2.5871865293143693e-05 tokens_per_second_per_gpu:2181.0235252682605 
Step 6195 | loss:2.100818157196045 lr:2.5845460467694516e-05 tokens_per_second_per_gpu:2181.141124404481 
Step 6196 | loss:2.036105155944824 lr:2.5819067123687113e-05 tokens_per_second_per_gpu:2159.343274014031 
Step 6197 | loss:2.0823051929473877 lr:2.5792685265207927e-05 tokens_per_second_per_gpu:2169.346816079913 
Step 6198 | loss:2.0440378189086914 lr:2.5766314896341702e-05 tokens_per_second_per_gpu:2192.6568878331304 
Step 6199 | loss:2.0857467651367188 lr:2.573995602117144e-05 tokens_per_second_per_gpu:2175.3863494913057 
Step 6200 | loss:2.0725083351135254 lr:2.571360864377823e-05 tokens_per_second_per_gpu:2172.7970864020576 
Step 6201 | loss:2.07985782623291 lr:2.5687272768241553e-05 tokens_per_second_per_gpu:2188.261351306808 
Step 6202 | loss:2.0882697105407715 lr:2.566094839863904e-05 tokens_per_second_per_gpu:2100.5133643977947 
Step 6203 | loss:2.090847969055176 lr:2.5634635539046447e-05 tokens_per_second_per_gpu:2114.7533087529887 
Step 6204 | loss:2.1034207344055176 lr:2.5608334193537863e-05 tokens_per_second_per_gpu:2173.496296438877 
Step 6205 | loss:2.0807135105133057 lr:2.5582044366185574e-05 tokens_per_second_per_gpu:2168.599568799569 
Step 6206 | loss:2.077270030975342 lr:2.5555766061060048e-05 tokens_per_second_per_gpu:2182.7360878636937 
Step 6207 | loss:2.0948002338409424 lr:2.5529499282229996e-05 tokens_per_second_per_gpu:2147.0338065447245 
Step 6208 | loss:2.046170711517334 lr:2.5503244033762364e-05 tokens_per_second_per_gpu:2177.930347996497 
Step 6209 | loss:2.100508213043213 lr:2.5477000319722232e-05 tokens_per_second_per_gpu:2186.5579174939317 
Step 6210 | loss:2.094052791595459 lr:2.5450768144172976e-05 tokens_per_second_per_gpu:2187.3044112288944 
Step 6211 | loss:2.0491113662719727 lr:2.5424547511176156e-05 tokens_per_second_per_gpu:2149.2883591718373 
Step 6212 | loss:2.087346076965332 lr:2.5398338424791547e-05 tokens_per_second_per_gpu:2169.0811663746235 
Step 6213 | loss:2.0122621059417725 lr:2.537214088907712e-05 tokens_per_second_per_gpu:2185.955374860659 
Step 6214 | loss:2.0057790279388428 lr:2.534595490808913e-05 tokens_per_second_per_gpu:2143.7931002641985 
Step 6215 | loss:2.0321640968322754 lr:2.5319780485881907e-05 tokens_per_second_per_gpu:2179.582790628955 
Step 6216 | loss:2.0853614807128906 lr:2.529361762650807e-05 tokens_per_second_per_gpu:2162.9269479512454 
Step 6217 | loss:2.048729419708252 lr:2.526746633401855e-05 tokens_per_second_per_gpu:2142.326614954917 
Step 6218 | loss:2.045651912689209 lr:2.524132661246229e-05 tokens_per_second_per_gpu:2182.143634682979 
Step 6219 | loss:2.1031060218811035 lr:2.521519846588656e-05 tokens_per_second_per_gpu:2193.1301359914364 
Step 6220 | loss:2.097651481628418 lr:2.5189081898336852e-05 tokens_per_second_per_gpu:2183.9511664114357 
Step 6221 | loss:2.07230806350708 lr:2.516297691385673e-05 tokens_per_second_per_gpu:2181.6863734202784 
Step 6222 | loss:2.052520275115967 lr:2.513688351648815e-05 tokens_per_second_per_gpu:2172.4187303199465 
Step 6223 | loss:2.0886504650115967 lr:2.5110801710271204e-05 tokens_per_second_per_gpu:2169.7176510958557 
Step 6224 | loss:2.0463366508483887 lr:2.5084731499244098e-05 tokens_per_second_per_gpu:2163.245278024444 
Step 6225 | loss:2.0535378456115723 lr:2.5058672887443335e-05 tokens_per_second_per_gpu:2131.0548904256116 
Step 6226 | loss:2.086399555206299 lr:2.503262587890365e-05 tokens_per_second_per_gpu:2160.8266235184356 
Step 6227 | loss:2.0502521991729736 lr:2.5006590477657842e-05 tokens_per_second_per_gpu:2115.940833859913 
Step 6228 | loss:2.040058135986328 lr:2.4980566687737095e-05 tokens_per_second_per_gpu:2187.598183609474 
Step 6229 | loss:2.067418336868286 lr:2.4954554513170704e-05 tokens_per_second_per_gpu:2177.0474067960295 
Step 6230 | loss:2.0848958492279053 lr:2.49285539579861e-05 tokens_per_second_per_gpu:2160.8998967069265 
Step 6231 | loss:2.1427359580993652 lr:2.4902565026209014e-05 tokens_per_second_per_gpu:2193.1843323170015 
Step 6232 | loss:2.0446090698242188 lr:2.4876587721863354e-05 tokens_per_second_per_gpu:2180.834824291287 
Step 6233 | loss:2.076362371444702 lr:2.4850622048971216e-05 tokens_per_second_per_gpu:2179.077096606217 
Step 6234 | loss:2.099463939666748 lr:2.4824668011552898e-05 tokens_per_second_per_gpu:2147.8592748085844 
Step 6235 | loss:2.0206642150878906 lr:2.479872561362693e-05 tokens_per_second_per_gpu:2185.9952166961407 
Step 6236 | loss:2.0672783851623535 lr:2.4772794859209935e-05 tokens_per_second_per_gpu:2068.012597512092 
Step 6237 | loss:2.0301971435546875 lr:2.4746875752316846e-05 tokens_per_second_per_gpu:2152.1112700030308 
Step 6238 | loss:2.089446783065796 lr:2.4720968296960744e-05 tokens_per_second_per_gpu:2180.259330958539 
Step 6239 | loss:2.0380940437316895 lr:2.4695072497152917e-05 tokens_per_second_per_gpu:2170.686302772003 
Step 6240 | loss:2.0446414947509766 lr:2.466918835690285e-05 tokens_per_second_per_gpu:2193.8371165407198 
Step 6241 | loss:2.0686964988708496 lr:2.464331588021823e-05 tokens_per_second_per_gpu:2145.289387001275 
Step 6242 | loss:2.0258398056030273 lr:2.461745507110489e-05 tokens_per_second_per_gpu:2178.5173536016464 
Step 6243 | loss:2.062624216079712 lr:2.4591605933566864e-05 tokens_per_second_per_gpu:2141.098169973683 
Step 6244 | loss:2.0305190086364746 lr:2.4565768471606522e-05 tokens_per_second_per_gpu:2188.304523083466 
Step 6245 | loss:2.0797934532165527 lr:2.4539942689224204e-05 tokens_per_second_per_gpu:2182.8075494678556 
Step 6246 | loss:2.0636653900146484 lr:2.4514128590418596e-05 tokens_per_second_per_gpu:2176.5755557578755 
Step 6247 | loss:2.0828607082366943 lr:2.448832617918654e-05 tokens_per_second_per_gpu:2172.8958545473724 
Step 6248 | loss:2.0516510009765625 lr:2.4462535459522974e-05 tokens_per_second_per_gpu:2173.7051543262273 
Step 6249 | loss:2.0203068256378174 lr:2.4436756435421192e-05 tokens_per_second_per_gpu:2154.273751607223 
Step 6250 | loss:2.0350399017333984 lr:2.4410989110872605e-05 tokens_per_second_per_gpu:2158.88982491684 
Step 6251 | loss:2.0636110305786133 lr:2.438523348986673e-05 tokens_per_second_per_gpu:2166.701208268249 
Step 6252 | loss:2.0289323329925537 lr:2.435948957639138e-05 tokens_per_second_per_gpu:2155.327759707705 
Step 6253 | loss:2.0442211627960205 lr:2.4333757374432554e-05 tokens_per_second_per_gpu:2151.226879404468 
Step 6254 | loss:2.161844253540039 lr:2.4308036887974295e-05 tokens_per_second_per_gpu:2176.688648670075 
Step 6255 | loss:2.076545476913452 lr:2.4282328120999032e-05 tokens_per_second_per_gpu:2191.3100663110235 
Step 6256 | loss:2.0445775985717773 lr:2.425663107748729e-05 tokens_per_second_per_gpu:2119.7931377679356 
Step 6257 | loss:2.070507764816284 lr:2.423094576141771e-05 tokens_per_second_per_gpu:2160.6711496917433 
Step 6258 | loss:2.0672383308410645 lr:2.4205272176767225e-05 tokens_per_second_per_gpu:2123.2114257785834 
Step 6259 | loss:2.0015811920166016 lr:2.4179610327510905e-05 tokens_per_second_per_gpu:2173.8104200720154 
Step 6260 | loss:2.0406758785247803 lr:2.4153960217621995e-05 tokens_per_second_per_gpu:2192.495394098325 
Step 6261 | loss:2.09076189994812 lr:2.4128321851071944e-05 tokens_per_second_per_gpu:2173.2021453457833 
Step 6262 | loss:2.006882429122925 lr:2.4102695231830395e-05 tokens_per_second_per_gpu:2164.9815335697162 
Step 6263 | loss:2.058838367462158 lr:2.4077080363865112e-05 tokens_per_second_per_gpu:2147.6647563601505 
Step 6264 | loss:2.079711437225342 lr:2.4051477251142052e-05 tokens_per_second_per_gpu:2075.987791019502 
Step 6265 | loss:2.0531907081604004 lr:2.4025885897625465e-05 tokens_per_second_per_gpu:2129.0508529530516 
Step 6266 | loss:2.0922412872314453 lr:2.400030630727763e-05 tokens_per_second_per_gpu:2138.213307176505 
Step 6267 | loss:2.032532215118408 lr:2.397473848405908e-05 tokens_per_second_per_gpu:2148.457918738112 
Step 6268 | loss:2.077467918395996 lr:2.394918243192854e-05 tokens_per_second_per_gpu:2187.757834260848 
Step 6269 | loss:2.0688915252685547 lr:2.3923638154842844e-05 tokens_per_second_per_gpu:2086.1745335036444 
Step 6270 | loss:2.087501049041748 lr:2.389810565675702e-05 tokens_per_second_per_gpu:2095.6678365149633 
Step 6271 | loss:2.03802490234375 lr:2.387258494162441e-05 tokens_per_second_per_gpu:2176.639998792284 
Step 6272 | loss:2.073580026626587 lr:2.384707601339631e-05 tokens_per_second_per_gpu:2154.0106847725588 
Step 6273 | loss:2.084144353866577 lr:2.3821578876022344e-05 tokens_per_second_per_gpu:2139.868852342033 
Step 6274 | loss:2.119765281677246 lr:2.379609353345028e-05 tokens_per_second_per_gpu:2192.3178511956203 
Step 6275 | loss:1.9819374084472656 lr:2.3770619989625985e-05 tokens_per_second_per_gpu:2185.399486598836 
Step 6276 | loss:2.038273811340332 lr:2.3745158248493625e-05 tokens_per_second_per_gpu:2182.188865439246 
Step 6277 | loss:2.0410971641540527 lr:2.371970831399547e-05 tokens_per_second_per_gpu:2130.9843789723095 
Step 6278 | loss:2.040299415588379 lr:2.3694270190071933e-05 tokens_per_second_per_gpu:2187.962069008355 
Step 6279 | loss:2.055788040161133 lr:2.366884388066164e-05 tokens_per_second_per_gpu:2183.0538233130765 
Step 6280 | loss:2.0702147483825684 lr:2.3643429389701377e-05 tokens_per_second_per_gpu:2181.2642578181203 
Step 6281 | loss:2.0827267169952393 lr:2.361802672112611e-05 tokens_per_second_per_gpu:2164.63886250003 
Step 6282 | loss:2.0984742641448975 lr:2.3592635878868973e-05 tokens_per_second_per_gpu:2184.675458070542 
Step 6283 | loss:2.1318507194519043 lr:2.3567256866861277e-05 tokens_per_second_per_gpu:2149.5817147953444 
Step 6284 | loss:2.1193156242370605 lr:2.3541889689032438e-05 tokens_per_second_per_gpu:2150.375528787842 
Step 6285 | loss:2.0498955249786377 lr:2.3516534349310117e-05 tokens_per_second_per_gpu:2186.2922707914618 
Step 6286 | loss:2.0725040435791016 lr:2.3491190851620104e-05 tokens_per_second_per_gpu:2188.7409614056514 
Step 6287 | loss:2.066865921020508 lr:2.3465859199886375e-05 tokens_per_second_per_gpu:2150.2153153561185 
Step 6288 | loss:2.0310468673706055 lr:2.344053939803106e-05 tokens_per_second_per_gpu:2159.4470887050225 
Step 6289 | loss:2.0646677017211914 lr:2.3415231449974483e-05 tokens_per_second_per_gpu:2155.020218146872 
Step 6290 | loss:2.0568456649780273 lr:2.338993535963505e-05 tokens_per_second_per_gpu:2144.3362325781754 
Step 6291 | loss:2.0643434524536133 lr:2.3364651130929416e-05 tokens_per_second_per_gpu:2188.5279113406646 
Step 6292 | loss:2.03676700592041 lr:2.3339378767772356e-05 tokens_per_second_per_gpu:2183.917547710694 
Step 6293 | loss:2.079056739807129 lr:2.3314118274076857e-05 tokens_per_second_per_gpu:2166.603817634604 
Step 6294 | loss:2.0898046493530273 lr:2.3288869653753996e-05 tokens_per_second_per_gpu:2190.0333896691927 
Step 6295 | loss:2.003201723098755 lr:2.3263632910713097e-05 tokens_per_second_per_gpu:2151.529640928666 
Step 6296 | loss:2.147810935974121 lr:2.323840804886154e-05 tokens_per_second_per_gpu:2174.912194284977 
Step 6297 | loss:2.0824239253997803 lr:2.321319507210492e-05 tokens_per_second_per_gpu:2170.8430850138593 
Step 6298 | loss:2.0067734718322754 lr:2.3187993984347078e-05 tokens_per_second_per_gpu:2126.7210430840014 
Step 6299 | loss:2.051903486251831 lr:2.3162804789489834e-05 tokens_per_second_per_gpu:2132.1687533267163 
Step 6300 | loss:2.0653138160705566 lr:2.313762749143331e-05 tokens_per_second_per_gpu:2120.7059594883617 
Step 6301 | loss:2.1089377403259277 lr:2.311246209407577e-05 tokens_per_second_per_gpu:2180.337740224284 
Step 6302 | loss:2.0289735794067383 lr:2.3087308601313494e-05 tokens_per_second_per_gpu:2035.0949024417205 
Step 6303 | loss:2.0668718814849854 lr:2.3062167017041148e-05 tokens_per_second_per_gpu:2188.705797496802 
Step 6304 | loss:2.059244394302368 lr:2.3037037345151402e-05 tokens_per_second_per_gpu:2096.9898833819075 
Step 6305 | loss:2.048415184020996 lr:2.301191958953508e-05 tokens_per_second_per_gpu:2151.4429777209534 
Step 6306 | loss:2.116575241088867 lr:2.2986813754081216e-05 tokens_per_second_per_gpu:2194.8140837442975 
Step 6307 | loss:2.0540807247161865 lr:2.2961719842676988e-05 tokens_per_second_per_gpu:2047.6570452354906 
Step 6308 | loss:2.033806324005127 lr:2.293663785920771e-05 tokens_per_second_per_gpu:2187.630172721254 
Step 6309 | loss:2.1117262840270996 lr:2.2911567807556854e-05 tokens_per_second_per_gpu:2137.4541139142925 
Step 6310 | loss:2.071786403656006 lr:2.2886509691606084e-05 tokens_per_second_per_gpu:2162.8814324470272 
Step 6311 | loss:2.0548243522644043 lr:2.2861463515235115e-05 tokens_per_second_per_gpu:2192.287662493388 
Step 6312 | loss:2.0654940605163574 lr:2.2836429282321915e-05 tokens_per_second_per_gpu:2154.7714904700706 
Step 6313 | loss:2.045131206512451 lr:2.2811406996742568e-05 tokens_per_second_per_gpu:2182.409054103956 
Step 6314 | loss:2.0725531578063965 lr:2.278639666237129e-05 tokens_per_second_per_gpu:2173.7464800303815 
Step 6315 | loss:2.116492748260498 lr:2.276139828308048e-05 tokens_per_second_per_gpu:2166.7749762730004 
Step 6316 | loss:2.02958345413208 lr:2.2736411862740704e-05 tokens_per_second_per_gpu:2188.8705919977033 
Step 6317 | loss:2.026979923248291 lr:2.271143740522056e-05 tokens_per_second_per_gpu:2068.6669914957265 
Step 6318 | loss:2.053788185119629 lr:2.2686474914386913e-05 tokens_per_second_per_gpu:2112.662513471439 
Step 6319 | loss:2.0690910816192627 lr:2.266152439410475e-05 tokens_per_second_per_gpu:2153.0713075554136 
Step 6320 | loss:2.0430877208709717 lr:2.263658584823717e-05 tokens_per_second_per_gpu:2072.4421503053873 
Step 6321 | loss:2.0834076404571533 lr:2.2611659280645458e-05 tokens_per_second_per_gpu:2173.3430246146318 
Step 6322 | loss:2.1267590522766113 lr:2.2586744695189043e-05 tokens_per_second_per_gpu:2168.5460344439607 
Step 6323 | loss:2.113499641418457 lr:2.2561842095725405e-05 tokens_per_second_per_gpu:2119.8743093808093 
Step 6324 | loss:2.04838228225708 lr:2.2536951486110325e-05 tokens_per_second_per_gpu:2143.43411761906 
Step 6325 | loss:2.068812370300293 lr:2.2512072870197653e-05 tokens_per_second_per_gpu:2182.081583046849 
Step 6326 | loss:2.0770883560180664 lr:2.248720625183932e-05 tokens_per_second_per_gpu:2171.574538559986 
Step 6327 | loss:2.0765621662139893 lr:2.246235163488547e-05 tokens_per_second_per_gpu:2120.814441868088 
Step 6328 | loss:2.1065545082092285 lr:2.243750902318442e-05 tokens_per_second_per_gpu:2183.336669485059 
Step 6329 | loss:2.105107545852661 lr:2.24126784205825e-05 tokens_per_second_per_gpu:2111.584413698526 
Step 6330 | loss:2.0706958770751953 lr:2.238785983092434e-05 tokens_per_second_per_gpu:2189.186419972731 
Step 6331 | loss:2.156562566757202 lr:2.2363053258052634e-05 tokens_per_second_per_gpu:2104.3673579624374 
Step 6332 | loss:2.1294784545898438 lr:2.2338258705808158e-05 tokens_per_second_per_gpu:2132.481163842031 
Step 6333 | loss:2.077585220336914 lr:2.2313476178029913e-05 tokens_per_second_per_gpu:2175.525271528959 
Step 6334 | loss:2.0853042602539062 lr:2.228870567855501e-05 tokens_per_second_per_gpu:2176.4499565822275 
Step 6335 | loss:2.0912551879882812 lr:2.2263947211218694e-05 tokens_per_second_per_gpu:2177.5738725059837 
Step 6336 | loss:2.0556704998016357 lr:2.2239200779854363e-05 tokens_per_second_per_gpu:2171.718376262726 
Step 6337 | loss:2.084174156188965 lr:2.2214466388293553e-05 tokens_per_second_per_gpu:2178.7816501620187 
Step 6338 | loss:2.044983386993408 lr:2.2189744040365866e-05 tokens_per_second_per_gpu:2182.609080229804 
Step 6339 | loss:2.0055322647094727 lr:2.216503373989913e-05 tokens_per_second_per_gpu:2179.9902071865213 
Step 6340 | loss:2.0259346961975098 lr:2.2140335490719276e-05 tokens_per_second_per_gpu:2118.355078137652 
Step 6341 | loss:2.0966153144836426 lr:2.211564929665034e-05 tokens_per_second_per_gpu:2134.3709066718575 
Step 6342 | loss:2.056332588195801 lr:2.209097516151455e-05 tokens_per_second_per_gpu:2178.9577696492283 
Step 6343 | loss:2.0455715656280518 lr:2.206631308913224e-05 tokens_per_second_per_gpu:2161.5856248837144 
Step 6344 | loss:2.076540946960449 lr:2.204166308332183e-05 tokens_per_second_per_gpu:2121.1323302114147 
Step 6345 | loss:2.0441536903381348 lr:2.2017025147899916e-05 tokens_per_second_per_gpu:2173.5778536199696 
Step 6346 | loss:2.0963659286499023 lr:2.1992399286681242e-05 tokens_per_second_per_gpu:2101.1664847085 
Step 6347 | loss:2.0430164337158203 lr:2.1967785503478656e-05 tokens_per_second_per_gpu:2079.2041924638147 
Step 6348 | loss:2.014665126800537 lr:2.194318380210313e-05 tokens_per_second_per_gpu:2160.1989889952197 
Step 6349 | loss:2.040889263153076 lr:2.1918594186363827e-05 tokens_per_second_per_gpu:2179.206278631049 
Step 6350 | loss:2.0790023803710938 lr:2.1894016660067884e-05 tokens_per_second_per_gpu:2151.465414734255 
Step 6351 | loss:2.0169241428375244 lr:2.1869451227020765e-05 tokens_per_second_per_gpu:2128.962053761385 
Step 6352 | loss:2.08593487739563 lr:2.184489789102596e-05 tokens_per_second_per_gpu:2185.5672772327152 
Step 6353 | loss:2.034101963043213 lr:2.1820356655885053e-05 tokens_per_second_per_gpu:2192.6442148553147 
Step 6354 | loss:2.0644242763519287 lr:2.1795827525397806e-05 tokens_per_second_per_gpu:2178.398358257467 
Step 6355 | loss:2.073218822479248 lr:2.177131050336213e-05 tokens_per_second_per_gpu:2186.031938519032 
Step 6356 | loss:2.0457959175109863 lr:2.1746805593573937e-05 tokens_per_second_per_gpu:2183.9527328200625 
Step 6357 | loss:2.1070430278778076 lr:2.172231279982745e-05 tokens_per_second_per_gpu:2125.752605981582 
Step 6358 | loss:2.0266575813293457 lr:2.169783212591491e-05 tokens_per_second_per_gpu:2182.388192021024 
Step 6359 | loss:2.0923943519592285 lr:2.1673363575626627e-05 tokens_per_second_per_gpu:2159.587177460878 
Step 6360 | loss:2.0789880752563477 lr:2.164890715275115e-05 tokens_per_second_per_gpu:2142.0701600221537 
Step 6361 | loss:2.0388245582580566 lr:2.162446286107508e-05 tokens_per_second_per_gpu:2084.821638930028 
Step 6362 | loss:2.111647129058838 lr:2.1600030704383155e-05 tokens_per_second_per_gpu:2151.334638903226 
Step 6363 | loss:2.097644805908203 lr:2.1575610686458246e-05 tokens_per_second_per_gpu:2145.045799488575 
Step 6364 | loss:2.0667829513549805 lr:2.1551202811081362e-05 tokens_per_second_per_gpu:2098.720318719613 
Step 6365 | loss:2.051048755645752 lr:2.1526807082031554e-05 tokens_per_second_per_gpu:2171.41454463519 
Step 6366 | loss:2.094905376434326 lr:2.1502423503086056e-05 tokens_per_second_per_gpu:2149.568498679083 
Step 6367 | loss:2.052730083465576 lr:2.1478052078020217e-05 tokens_per_second_per_gpu:2177.6428563707964 
Step 6368 | loss:2.0848050117492676 lr:2.1453692810607507e-05 tokens_per_second_per_gpu:2174.536136136938 
Step 6369 | loss:2.145284652709961 lr:2.1429345704619487e-05 tokens_per_second_per_gpu:2186.5570972479754 
Step 6370 | loss:2.0945885181427 lr:2.1405010763825882e-05 tokens_per_second_per_gpu:2130.2729473174295 
Step 6371 | loss:2.0881075859069824 lr:2.1380687991994452e-05 tokens_per_second_per_gpu:2177.5398864570802 
Step 6372 | loss:2.126103401184082 lr:2.135637739289115e-05 tokens_per_second_per_gpu:2090.558119805917 
Step 6373 | loss:2.0766327381134033 lr:2.133207897028001e-05 tokens_per_second_per_gpu:2130.5186031282274 
Step 6374 | loss:2.0954127311706543 lr:2.1307792727923192e-05 tokens_per_second_per_gpu:2179.2628361167986 
Step 6375 | loss:2.073298454284668 lr:2.128351866958096e-05 tokens_per_second_per_gpu:2183.2193952052085 
Step 6376 | loss:2.098691940307617 lr:2.125925679901174e-05 tokens_per_second_per_gpu:2181.313833472297 
Step 6377 | loss:2.096111297607422 lr:2.123500711997193e-05 tokens_per_second_per_gpu:2127.5365676695565 
Step 6378 | loss:2.029482841491699 lr:2.121076963621622e-05 tokens_per_second_per_gpu:2156.082189608088 
Step 6379 | loss:2.106842517852783 lr:2.118654435149735e-05 tokens_per_second_per_gpu:2188.864580484626 
Step 6380 | loss:2.0585319995880127 lr:2.116233126956608e-05 tokens_per_second_per_gpu:2172.663980029049 
Step 6381 | loss:2.0316712856292725 lr:2.1138130394171385e-05 tokens_per_second_per_gpu:2140.2156006841487 
Step 6382 | loss:2.028082847595215 lr:2.1113941729060306e-05 tokens_per_second_per_gpu:2016.4911952328057 
Step 6383 | loss:2.0868453979492188 lr:2.1089765277978023e-05 tokens_per_second_per_gpu:2149.960658457854 
Step 6384 | loss:2.073782205581665 lr:2.1065601044667805e-05 tokens_per_second_per_gpu:2174.4041935366326 
Step 6385 | loss:2.065695285797119 lr:2.104144903287104e-05 tokens_per_second_per_gpu:2191.1591974350727 
Step 6386 | loss:2.0342578887939453 lr:2.1017309246327177e-05 tokens_per_second_per_gpu:2183.342876220596 
Step 6387 | loss:2.053626537322998 lr:2.0993181688773832e-05 tokens_per_second_per_gpu:2113.4089336659335 
Step 6388 | loss:2.0600974559783936 lr:2.09690663639467e-05 tokens_per_second_per_gpu:2181.726047036853 
Step 6389 | loss:2.067397117614746 lr:2.09449632755796e-05 tokens_per_second_per_gpu:2178.4928457340116 
Step 6390 | loss:2.0697579383850098 lr:2.0920872427404438e-05 tokens_per_second_per_gpu:2182.677737577105 
Step 6391 | loss:2.132786750793457 lr:2.089679382315125e-05 tokens_per_second_per_gpu:2177.7861043320468 
Step 6392 | loss:2.1156139373779297 lr:2.0872727466548114e-05 tokens_per_second_per_gpu:2031.7524641288344 
Step 6393 | loss:2.0347397327423096 lr:2.084867336132128e-05 tokens_per_second_per_gpu:2168.5228418624447 
Step 6394 | loss:2.071920871734619 lr:2.082463151119507e-05 tokens_per_second_per_gpu:2191.8662937555027 
Step 6395 | loss:2.0872013568878174 lr:2.0800601919891914e-05 tokens_per_second_per_gpu:2183.6338835597785 
Step 6396 | loss:2.068906307220459 lr:2.0776584591132354e-05 tokens_per_second_per_gpu:2167.2470393942835 
Step 6397 | loss:2.0536341667175293 lr:2.0752579528635042e-05 tokens_per_second_per_gpu:2145.4913927781176 
Step 6398 | loss:2.0807347297668457 lr:2.0728586736116627e-05 tokens_per_second_per_gpu:2163.9504819624144 
Step 6399 | loss:2.094766616821289 lr:2.0704606217292067e-05 tokens_per_second_per_gpu:2153.767446021023 
Step 6400 | loss:2.053509473800659 lr:2.0680637975874195e-05 tokens_per_second_per_gpu:2181.617954249578 
Step 6401 | loss:2.0769808292388916 lr:2.0656682015574092e-05 tokens_per_second_per_gpu:2189.6377440595684 
Step 6402 | loss:2.0545730590820312 lr:2.0632738340100876e-05 tokens_per_second_per_gpu:2193.0095556013284 
Step 6403 | loss:2.0661559104919434 lr:2.0608806953161806e-05 tokens_per_second_per_gpu:2158.0542015280153 
Step 6404 | loss:2.0556797981262207 lr:2.0584887858462144e-05 tokens_per_second_per_gpu:2182.0222776319106 
Step 6405 | loss:2.0585885047912598 lr:2.0560981059705363e-05 tokens_per_second_per_gpu:2180.6782129833 
Step 6406 | loss:2.114269971847534 lr:2.053708656059301e-05 tokens_per_second_per_gpu:2124.9059388881915 
Step 6407 | loss:2.116365909576416 lr:2.0513204364824635e-05 tokens_per_second_per_gpu:2179.2494030850326 
Step 6408 | loss:2.032456874847412 lr:2.0489334476097975e-05 tokens_per_second_per_gpu:2188.701783196906 
Step 6409 | loss:2.0113511085510254 lr:2.0465476898108848e-05 tokens_per_second_per_gpu:2188.063246402077 
Step 6410 | loss:2.0831716060638428 lr:2.044163163455114e-05 tokens_per_second_per_gpu:2164.0047535619265 
Step 6411 | loss:2.0907678604125977 lr:2.0417798689116852e-05 tokens_per_second_per_gpu:2121.1351508857883 
Step 6412 | loss:2.034860610961914 lr:2.039397806549608e-05 tokens_per_second_per_gpu:2115.1786439380803 
Step 6413 | loss:2.0728812217712402 lr:2.0370169767376968e-05 tokens_per_second_per_gpu:2116.4757200708973 
Step 6414 | loss:2.031935214996338 lr:2.0346373798445794e-05 tokens_per_second_per_gpu:2188.3747498877224 
Step 6415 | loss:2.0417518615722656 lr:2.0322590162386933e-05 tokens_per_second_per_gpu:2155.117146112539 
Step 6416 | loss:2.1081197261810303 lr:2.029881886288284e-05 tokens_per_second_per_gpu:2153.864100304259 
Step 6417 | loss:2.045600414276123 lr:2.0275059903614036e-05 tokens_per_second_per_gpu:2162.4527167152974 
Step 6418 | loss:2.1046791076660156 lr:2.025131328825919e-05 tokens_per_second_per_gpu:2191.7613694090733 
Step 6419 | loss:2.1285619735717773 lr:2.0227579020494957e-05 tokens_per_second_per_gpu:2186.396351594043 
Step 6420 | loss:2.0959506034851074 lr:2.020385710399618e-05 tokens_per_second_per_gpu:2167.536380445644 
Step 6421 | loss:2.0848288536071777 lr:2.0180147542435758e-05 tokens_per_second_per_gpu:2135.4277186988666 
Step 6422 | loss:1.9959321022033691 lr:2.015645033948467e-05 tokens_per_second_per_gpu:2141.7321648550205 
Step 6423 | loss:2.0852322578430176 lr:2.013276549881197e-05 tokens_per_second_per_gpu:2176.130252682679 
Step 6424 | loss:2.112983226776123 lr:2.0109093024084848e-05 tokens_per_second_per_gpu:2190.2018210709284 
Step 6425 | loss:2.082489490509033 lr:2.008543291896847e-05 tokens_per_second_per_gpu:2060.735159304986 
Step 6426 | loss:2.0247244834899902 lr:2.006178518712626e-05 tokens_per_second_per_gpu:2157.2621862743695 
Step 6427 | loss:2.083354949951172 lr:2.0038149832219545e-05 tokens_per_second_per_gpu:2141.2495385093052 
Step 6428 | loss:2.0920932292938232 lr:2.0014526857907855e-05 tokens_per_second_per_gpu:2180.046266502262 
Step 6429 | loss:2.0895066261291504 lr:1.9990916267848747e-05 tokens_per_second_per_gpu:2191.898655068967 
Step 6430 | loss:2.107682228088379 lr:1.9967318065697915e-05 tokens_per_second_per_gpu:2174.4710037195127 
Step 6431 | loss:2.062526226043701 lr:1.994373225510903e-05 tokens_per_second_per_gpu:2138.5022839027847 
Step 6432 | loss:2.041533946990967 lr:1.992015883973397e-05 tokens_per_second_per_gpu:2159.1344571802556 
Step 6433 | loss:2.1051273345947266 lr:1.989659782322265e-05 tokens_per_second_per_gpu:2166.028769528256 
Step 6434 | loss:2.105099678039551 lr:1.9873049209222994e-05 tokens_per_second_per_gpu:2187.8718184960676 
Step 6435 | loss:2.1109888553619385 lr:1.9849513001381103e-05 tokens_per_second_per_gpu:2190.4500168006016 
Step 6436 | loss:2.065807819366455 lr:1.98259892033411e-05 tokens_per_second_per_gpu:2180.598219366867 
Step 6437 | loss:2.0620784759521484 lr:1.9802477818745224e-05 tokens_per_second_per_gpu:2092.2290603099596 
Step 6438 | loss:2.0992798805236816 lr:1.9778978851233754e-05 tokens_per_second_per_gpu:2185.7088890613604 
Step 6439 | loss:2.0406651496887207 lr:1.97554923044451e-05 tokens_per_second_per_gpu:2145.0494134066585 
Step 6440 | loss:2.069927215576172 lr:1.9732018182015667e-05 tokens_per_second_per_gpu:2170.168792569302 
Step 6441 | loss:2.080469846725464 lr:1.9708556487579997e-05 tokens_per_second_per_gpu:2187.7106224411555 
Step 6442 | loss:2.0286569595336914 lr:1.9685107224770704e-05 tokens_per_second_per_gpu:2186.180736984081 
Step 6443 | loss:2.0881946086883545 lr:1.966167039721846e-05 tokens_per_second_per_gpu:2105.0606237530096 
Step 6444 | loss:2.069779872894287 lr:1.9638246008552018e-05 tokens_per_second_per_gpu:2191.5163667450292 
Step 6445 | loss:2.0968379974365234 lr:1.9614834062398248e-05 tokens_per_second_per_gpu:2188.4167734198436 
Step 6446 | loss:2.1327385902404785 lr:1.9591434562381982e-05 tokens_per_second_per_gpu:2179.1682113547495 
Step 6447 | loss:2.094301462173462 lr:1.9568047512126232e-05 tokens_per_second_per_gpu:2130.9409498100636 
Step 6448 | loss:2.0836055278778076 lr:1.9544672915252028e-05 tokens_per_second_per_gpu:2182.860423967661 
Step 6449 | loss:2.066786289215088 lr:1.95213107753785e-05 tokens_per_second_per_gpu:2169.858509307404 
Step 6450 | loss:2.0450704097747803 lr:1.9497961096122842e-05 tokens_per_second_per_gpu:2177.2625906322214 
Step 6451 | loss:2.0771493911743164 lr:1.947462388110034e-05 tokens_per_second_per_gpu:2168.6535494358554 
Step 6452 | loss:2.087937593460083 lr:1.945129913392424e-05 tokens_per_second_per_gpu:2144.1922284001475 
Step 6453 | loss:2.064976930618286 lr:1.9427986858206036e-05 tokens_per_second_per_gpu:2191.273935347542 
Step 6454 | loss:2.0723443031311035 lr:1.940468705755515e-05 tokens_per_second_per_gpu:2189.9939403390376 
Step 6455 | loss:2.064814805984497 lr:1.938139973557912e-05 tokens_per_second_per_gpu:2156.572520894498 
Step 6456 | loss:2.0231752395629883 lr:1.9358124895883556e-05 tokens_per_second_per_gpu:2183.0536926881523 
Step 6457 | loss:2.088433027267456 lr:1.933486254207216e-05 tokens_per_second_per_gpu:2182.191896344849 
Step 6458 | loss:2.1071505546569824 lr:1.9311612677746605e-05 tokens_per_second_per_gpu:2186.3435300885453 
Step 6459 | loss:1.9764988422393799 lr:1.9288375306506758e-05 tokens_per_second_per_gpu:2170.188620665931 
Step 6460 | loss:2.074613571166992 lr:1.9265150431950496e-05 tokens_per_second_per_gpu:2153.2810045942797 
Step 6461 | loss:2.099020481109619 lr:1.9241938057673704e-05 tokens_per_second_per_gpu:2123.0699130662306 
Step 6462 | loss:2.080514430999756 lr:1.9218738187270413e-05 tokens_per_second_per_gpu:2151.688846632059 
Step 6463 | loss:2.080639362335205 lr:1.9195550824332687e-05 tokens_per_second_per_gpu:2190.0259333644913 
Step 6464 | loss:2.069089889526367 lr:1.917237597245065e-05 tokens_per_second_per_gpu:2164.880139674455 
Step 6465 | loss:2.045301914215088 lr:1.9149213635212503e-05 tokens_per_second_per_gpu:2178.523368190295 
Step 6466 | loss:2.0413217544555664 lr:1.912606381620452e-05 tokens_per_second_per_gpu:2193.6095309846387 
Step 6467 | loss:2.0567359924316406 lr:1.9102926519010966e-05 tokens_per_second_per_gpu:2146.341784900156 
Step 6468 | loss:2.0698328018188477 lr:1.9079801747214244e-05 tokens_per_second_per_gpu:2152.9458294191777 
Step 6469 | loss:2.1120948791503906 lr:1.9056689504394788e-05 tokens_per_second_per_gpu:2155.6773694166327 
Step 6470 | loss:2.0742697715759277 lr:1.90335897941311e-05 tokens_per_second_per_gpu:2157.7748952773336 
Step 6471 | loss:2.0581295490264893 lr:1.9010502619999738e-05 tokens_per_second_per_gpu:2173.4787291997886 
Step 6472 | loss:2.1134419441223145 lr:1.8987427985575344e-05 tokens_per_second_per_gpu:2177.230343235216 
Step 6473 | loss:2.0458106994628906 lr:1.8964365894430548e-05 tokens_per_second_per_gpu:2153.4679726937916 
Step 6474 | loss:2.082794427871704 lr:1.8941316350136097e-05 tokens_per_second_per_gpu:2196.208595731245 
Step 6475 | loss:2.120882272720337 lr:1.891827935626078e-05 tokens_per_second_per_gpu:2171.441736329553 
Step 6476 | loss:2.0312843322753906 lr:1.8895254916371453e-05 tokens_per_second_per_gpu:2132.4397205715345 
Step 6477 | loss:2.158815860748291 lr:1.887224303403302e-05 tokens_per_second_per_gpu:2155.6930306551844 
Step 6478 | loss:2.033651351928711 lr:1.884924371280846e-05 tokens_per_second_per_gpu:2169.96044863982 
Step 6479 | loss:2.0896706581115723 lr:1.8826256956258716e-05 tokens_per_second_per_gpu:2105.318912686632 
Step 6480 | loss:2.101205825805664 lr:1.8803282767942954e-05 tokens_per_second_per_gpu:2156.371473870062 
Step 6481 | loss:2.0467371940612793 lr:1.8780321151418223e-05 tokens_per_second_per_gpu:2180.2996652147954 
Step 6482 | loss:2.0125198364257812 lr:1.8757372110239723e-05 tokens_per_second_per_gpu:2183.85262760649 
Step 6483 | loss:2.0733821392059326 lr:1.873443564796068e-05 tokens_per_second_per_gpu:2134.158684098221 
Step 6484 | loss:2.0669164657592773 lr:1.8711511768132383e-05 tokens_per_second_per_gpu:2186.107276718983 
Step 6485 | loss:2.0288174152374268 lr:1.8688600474304162e-05 tokens_per_second_per_gpu:2153.3300015510135 
Step 6486 | loss:2.090569019317627 lr:1.86657017700234e-05 tokens_per_second_per_gpu:2167.4650820722222 
Step 6487 | loss:2.0785231590270996 lr:1.8642815658835557e-05 tokens_per_second_per_gpu:2047.7067973379528 
Step 6488 | loss:2.1229629516601562 lr:1.8619942144284076e-05 tokens_per_second_per_gpu:2169.258685140508 
Step 6489 | loss:2.081329822540283 lr:1.8597081229910505e-05 tokens_per_second_per_gpu:2168.988931318573 
Step 6490 | loss:2.036083221435547 lr:1.8574232919254453e-05 tokens_per_second_per_gpu:2188.009730983427 
Step 6491 | loss:2.0672783851623535 lr:1.8551397215853518e-05 tokens_per_second_per_gpu:2182.719418166846 
Step 6492 | loss:2.1023850440979004 lr:1.8528574123243402e-05 tokens_per_second_per_gpu:2169.664715224548 
Step 6493 | loss:2.086773633956909 lr:1.8505763644957863e-05 tokens_per_second_per_gpu:2180.3377513519436 
Step 6494 | loss:2.003950357437134 lr:1.8482965784528617e-05 tokens_per_second_per_gpu:2180.3883174534903 
Step 6495 | loss:2.096519947052002 lr:1.8460180545485507e-05 tokens_per_second_per_gpu:2190.5774060584918 
Step 6496 | loss:2.051523208618164 lr:1.843740793135641e-05 tokens_per_second_per_gpu:2180.254246581706 
Step 6497 | loss:2.035554885864258 lr:1.841464794566723e-05 tokens_per_second_per_gpu:2105.721790439731 
Step 6498 | loss:2.0856876373291016 lr:1.8391900591941934e-05 tokens_per_second_per_gpu:2182.896079298307 
Step 6499 | loss:2.1011157035827637 lr:1.8369165873702543e-05 tokens_per_second_per_gpu:2146.4474649819113 
Step 6500 | loss:2.0939855575561523 lr:1.8346443794469025e-05 tokens_per_second_per_gpu:2173.7026238478834 
Step 6501 | loss:2.0257067680358887 lr:1.832373435775958e-05 tokens_per_second_per_gpu:2151.7420832491425 
Step 6502 | loss:2.051800489425659 lr:1.830103756709025e-05 tokens_per_second_per_gpu:2180.2627728687876 
Step 6503 | loss:2.0866026878356934 lr:1.8278353425975237e-05 tokens_per_second_per_gpu:2140.000614813818 
Step 6504 | loss:2.0612874031066895 lr:1.8255681937926762e-05 tokens_per_second_per_gpu:2165.8997827322137 
Step 6505 | loss:2.047013282775879 lr:1.8233023106455104e-05 tokens_per_second_per_gpu:2038.2497077639696 
Step 6506 | loss:2.080474853515625 lr:1.8210376935068475e-05 tokens_per_second_per_gpu:2169.40421986234 
Step 6507 | loss:2.0759458541870117 lr:1.818774342727332e-05 tokens_per_second_per_gpu:2185.272673256462 
Step 6508 | loss:2.034132480621338 lr:1.8165122586573924e-05 tokens_per_second_per_gpu:2188.434205385889 
Step 6509 | loss:2.050947666168213 lr:1.8142514416472744e-05 tokens_per_second_per_gpu:2189.6781498689224 
Step 6510 | loss:2.079005241394043 lr:1.8119918920470224e-05 tokens_per_second_per_gpu:2128.6322786837786 
Step 6511 | loss:2.077039957046509 lr:1.8097336102064853e-05 tokens_per_second_per_gpu:2151.7684499405636 
Step 6512 | loss:2.0869295597076416 lr:1.807476596475316e-05 tokens_per_second_per_gpu:2165.0771488546648 
Step 6513 | loss:2.0632386207580566 lr:1.80522085120297e-05 tokens_per_second_per_gpu:2188.472391113505 
Step 6514 | loss:2.0447938442230225 lr:1.8029663747387104e-05 tokens_per_second_per_gpu:2112.745930330752 
Step 6515 | loss:2.115443468093872 lr:1.8007131674315957e-05 tokens_per_second_per_gpu:2151.311864370955 
Step 6516 | loss:2.0623013973236084 lr:1.798461229630496e-05 tokens_per_second_per_gpu:2153.740675717569 
Step 6517 | loss:2.0620946884155273 lr:1.7962105616840806e-05 tokens_per_second_per_gpu:2165.7462696014163 
Step 6518 | loss:2.0990781784057617 lr:1.7939611639408228e-05 tokens_per_second_per_gpu:2088.465684485062 
Step 6519 | loss:2.081864356994629 lr:1.7917130367490008e-05 tokens_per_second_per_gpu:2176.727598619669 
Step 6520 | loss:2.031456470489502 lr:1.789466180456698e-05 tokens_per_second_per_gpu:2169.567418578708 
Step 6521 | loss:2.0980634689331055 lr:1.7872205954117917e-05 tokens_per_second_per_gpu:2143.4720019068563 
Step 6522 | loss:2.0343267917633057 lr:1.784976281961972e-05 tokens_per_second_per_gpu:2173.819027538796 
Step 6523 | loss:2.068066120147705 lr:1.782733240454728e-05 tokens_per_second_per_gpu:2156.3913528619405 
Step 6524 | loss:2.1083152294158936 lr:1.7804914712373534e-05 tokens_per_second_per_gpu:2184.8727033257446 
Step 6525 | loss:2.085214376449585 lr:1.778250974656944e-05 tokens_per_second_per_gpu:2165.987553135759 
Step 6526 | loss:2.082153797149658 lr:1.7760117510604013e-05 tokens_per_second_per_gpu:2173.727383783387 
Step 6527 | loss:2.0565145015716553 lr:1.7737738007944195e-05 tokens_per_second_per_gpu:2168.704290247822 
Step 6528 | loss:2.084832191467285 lr:1.7715371242055135e-05 tokens_per_second_per_gpu:2145.709075016476 
Step 6529 | loss:2.0391972064971924 lr:1.769301721639982e-05 tokens_per_second_per_gpu:2154.946092954867 
Step 6530 | loss:2.109201431274414 lr:1.7670675934439407e-05 tokens_per_second_per_gpu:2191.967579041685 
Step 6531 | loss:2.097294569015503 lr:1.764834739963299e-05 tokens_per_second_per_gpu:2174.7615769085496 
Step 6532 | loss:2.015547037124634 lr:1.7626031615437777e-05 tokens_per_second_per_gpu:2163.917275279928 
Step 6533 | loss:2.0448861122131348 lr:1.7603728585308856e-05 tokens_per_second_per_gpu:2190.3437820264703 
Step 6534 | loss:2.009181499481201 lr:1.758143831269955e-05 tokens_per_second_per_gpu:2147.838784868139 
Step 6535 | loss:2.0191760063171387 lr:1.7559160801061003e-05 tokens_per_second_per_gpu:2174.552973508204 
Step 6536 | loss:2.082780361175537 lr:1.753689605384249e-05 tokens_per_second_per_gpu:2190.7398006502312 
Step 6537 | loss:2.0634870529174805 lr:1.7514644074491303e-05 tokens_per_second_per_gpu:2192.1547766272615 
Step 6538 | loss:2.0620782375335693 lr:1.749240486645275e-05 tokens_per_second_per_gpu:2161.851602726497 
Step 6539 | loss:2.075723648071289 lr:1.7470178433170136e-05 tokens_per_second_per_gpu:2175.4192601767268 
Step 6540 | loss:2.0525155067443848 lr:1.7447964778084826e-05 tokens_per_second_per_gpu:2096.459855333109 
Step 6541 | loss:2.018589496612549 lr:1.7425763904636196e-05 tokens_per_second_per_gpu:2063.62000767709 
Step 6542 | loss:2.058277130126953 lr:1.7403575816261598e-05 tokens_per_second_per_gpu:2112.9646428856345 
Step 6543 | loss:2.102935791015625 lr:1.738140051639646e-05 tokens_per_second_per_gpu:2173.6355876914704 
Step 6544 | loss:2.0418200492858887 lr:1.735923800847422e-05 tokens_per_second_per_gpu:2161.647429171376 
Step 6545 | loss:2.0717265605926514 lr:1.733708829592633e-05 tokens_per_second_per_gpu:2180.28311689246 
Step 6546 | loss:2.054777145385742 lr:1.7314951382182244e-05 tokens_per_second_per_gpu:2095.383972533755 
Step 6547 | loss:2.0943102836608887 lr:1.7292827270669475e-05 tokens_per_second_per_gpu:2180.882668908178 
Step 6548 | loss:2.0761451721191406 lr:1.727071596481349e-05 tokens_per_second_per_gpu:2184.6558640469157 
Step 6549 | loss:2.0993103981018066 lr:1.7248617468037832e-05 tokens_per_second_per_gpu:2153.271972215224 
Step 6550 | loss:2.089488983154297 lr:1.722653178376403e-05 tokens_per_second_per_gpu:2150.2688605369267 
Step 6551 | loss:2.0432662963867188 lr:1.7204458915411646e-05 tokens_per_second_per_gpu:2187.5852622726993 
Step 6552 | loss:2.0143802165985107 lr:1.7182398866398253e-05 tokens_per_second_per_gpu:2137.8948155658886 
Step 6553 | loss:2.0774126052856445 lr:1.716035164013945e-05 tokens_per_second_per_gpu:2179.191391736748 
Step 6554 | loss:2.1107373237609863 lr:1.7138317240048773e-05 tokens_per_second_per_gpu:2166.8591285701063 
Step 6555 | loss:2.1034140586853027 lr:1.711629566953793e-05 tokens_per_second_per_gpu:2167.9431114224867 
Step 6556 | loss:2.0773839950561523 lr:1.709428693201649e-05 tokens_per_second_per_gpu:2189.3614857353987 
Step 6557 | loss:2.023937702178955 lr:1.7072291030892086e-05 tokens_per_second_per_gpu:2134.5998017992574 
Step 6558 | loss:2.0934200286865234 lr:1.70503079695704e-05 tokens_per_second_per_gpu:2190.574851834555 
Step 6559 | loss:2.0627527236938477 lr:1.7028337751455093e-05 tokens_per_second_per_gpu:2182.8821363524994 
Step 6560 | loss:1.9975192546844482 lr:1.700638037994783e-05 tokens_per_second_per_gpu:2123.1125302814926 
Step 6561 | loss:2.0421016216278076 lr:1.6984435858448334e-05 tokens_per_second_per_gpu:2189.2060114350247 
Step 6562 | loss:2.049659490585327 lr:1.6962504190354246e-05 tokens_per_second_per_gpu:2152.685008669596 
Step 6563 | loss:2.0990025997161865 lr:1.6940585379061302e-05 tokens_per_second_per_gpu:2133.0012295688257 
Step 6564 | loss:2.0621557235717773 lr:1.6918679427963224e-05 tokens_per_second_per_gpu:2189.1203142587206 
Step 6565 | loss:2.0844926834106445 lr:1.6896786340451743e-05 tokens_per_second_per_gpu:2191.55698574363 
Step 6566 | loss:2.078984260559082 lr:1.6874906119916568e-05 tokens_per_second_per_gpu:2185.014604515188 
Step 6567 | loss:2.063084602355957 lr:1.6853038769745467e-05 tokens_per_second_per_gpu:2165.6821521110064 
Step 6568 | loss:2.049673557281494 lr:1.6831184293324208e-05 tokens_per_second_per_gpu:2180.8147516364884 
Step 6569 | loss:2.0412967205047607 lr:1.68093426940365e-05 tokens_per_second_per_gpu:2103.9548494583387 
Step 6570 | loss:2.1211442947387695 lr:1.6787513975264114e-05 tokens_per_second_per_gpu:2149.8510029938634 
Step 6571 | loss:2.117924690246582 lr:1.6765698140386843e-05 tokens_per_second_per_gpu:2169.8485363060613 
Step 6572 | loss:2.080805778503418 lr:1.6743895192782443e-05 tokens_per_second_per_gpu:2193.1499168470086 
Step 6573 | loss:2.008927583694458 lr:1.6722105135826694e-05 tokens_per_second_per_gpu:2182.0943838346416 
Step 6574 | loss:2.057499408721924 lr:1.6700327972893404e-05 tokens_per_second_per_gpu:2135.2422743241987 
Step 6575 | loss:2.1170825958251953 lr:1.6678563707354323e-05 tokens_per_second_per_gpu:2138.40522310567 
Step 6576 | loss:2.074714422225952 lr:1.6656812342579242e-05 tokens_per_second_per_gpu:2143.17477397676 
Step 6577 | loss:2.037540912628174 lr:1.663507388193597e-05 tokens_per_second_per_gpu:2180.887848474723 
Step 6578 | loss:2.0216755867004395 lr:1.661334832879029e-05 tokens_per_second_per_gpu:2190.051207804008 
Step 6579 | loss:2.008037567138672 lr:1.6591635686506002e-05 tokens_per_second_per_gpu:2154.11688556402 
Step 6580 | loss:2.105483055114746 lr:1.6569935958444927e-05 tokens_per_second_per_gpu:2181.606236131069 
Step 6581 | loss:2.0725739002227783 lr:1.654824914796679e-05 tokens_per_second_per_gpu:2187.5219794873897 
Step 6582 | loss:2.0839874744415283 lr:1.6526575258429478e-05 tokens_per_second_per_gpu:2183.092572100586 
Step 6583 | loss:2.062000274658203 lr:1.6504914293188722e-05 tokens_per_second_per_gpu:2068.3048880898327 
Step 6584 | loss:2.048859119415283 lr:1.648326625559834e-05 tokens_per_second_per_gpu:2129.945351748687 
Step 6585 | loss:2.1130430698394775 lr:1.6461631149010114e-05 tokens_per_second_per_gpu:2163.6242720609016 
Step 6586 | loss:2.0531930923461914 lr:1.6440008976773845e-05 tokens_per_second_per_gpu:2159.3563649047132 
Step 6587 | loss:2.0185060501098633 lr:1.6418399742237322e-05 tokens_per_second_per_gpu:2124.206198056587 
Step 6588 | loss:2.0778026580810547 lr:1.6396803448746346e-05 tokens_per_second_per_gpu:2188.916694550575 
Step 6589 | loss:2.0723085403442383 lr:1.637522009964466e-05 tokens_per_second_per_gpu:2153.739629179741 
Step 6590 | loss:2.0157361030578613 lr:1.6353649698274066e-05 tokens_per_second_per_gpu:2132.875782675683 
Step 6591 | loss:2.053574562072754 lr:1.633209224797433e-05 tokens_per_second_per_gpu:2176.130503322127 
Step 6592 | loss:2.026529312133789 lr:1.6310547752083228e-05 tokens_per_second_per_gpu:2167.078963631637 
Step 6593 | loss:2.0419955253601074 lr:1.6289016213936504e-05 tokens_per_second_per_gpu:2190.040629956435 
Step 6594 | loss:2.0468602180480957 lr:1.6267497636867957e-05 tokens_per_second_per_gpu:2121.508407765794 
Step 6595 | loss:2.0478901863098145 lr:1.6245992024209277e-05 tokens_per_second_per_gpu:2135.4733299159434 
Step 6596 | loss:2.1009628772735596 lr:1.6224499379290238e-05 tokens_per_second_per_gpu:2159.649926300534 
Step 6597 | loss:2.110013484954834 lr:1.6203019705438562e-05 tokens_per_second_per_gpu:2131.6671992525003 
Step 6598 | loss:2.1439859867095947 lr:1.6181553005979987e-05 tokens_per_second_per_gpu:2170.719768023694 
Step 6599 | loss:2.0441131591796875 lr:1.6160099284238218e-05 tokens_per_second_per_gpu:2186.2151490764036 
Step 6600 | loss:2.0634875297546387 lr:1.6138658543534968e-05 tokens_per_second_per_gpu:2179.484026378476 
Step 6601 | loss:2.0922040939331055 lr:1.6117230787189952e-05 tokens_per_second_per_gpu:2182.2130635527938 
Step 6602 | loss:2.0522117614746094 lr:1.6095816018520792e-05 tokens_per_second_per_gpu:2192.0999436847237 
Step 6603 | loss:2.0858349800109863 lr:1.607441424084326e-05 tokens_per_second_per_gpu:2152.528396568567 
Step 6604 | loss:2.092698574066162 lr:1.605302545747095e-05 tokens_per_second_per_gpu:2151.3417541293998 
Step 6605 | loss:2.080145835876465 lr:1.603164967171552e-05 tokens_per_second_per_gpu:2167.590358047831 
Step 6606 | loss:2.024094581604004 lr:1.601028688688664e-05 tokens_per_second_per_gpu:2187.6020977598764 
Step 6607 | loss:2.0641369819641113 lr:1.5988937106291935e-05 tokens_per_second_per_gpu:2140.809659901996 
Step 6608 | loss:2.02701473236084 lr:1.5967600333236964e-05 tokens_per_second_per_gpu:2114.950807514266 
Step 6609 | loss:2.047624111175537 lr:1.594627657102541e-05 tokens_per_second_per_gpu:2149.6121181654435 
Step 6610 | loss:2.0358521938323975 lr:1.5924965822958802e-05 tokens_per_second_per_gpu:2173.435615645445 
Step 6611 | loss:2.0547194480895996 lr:1.5903668092336722e-05 tokens_per_second_per_gpu:2147.336018102081 
Step 6612 | loss:2.096015453338623 lr:1.5882383382456723e-05 tokens_per_second_per_gpu:2187.188468426245 
Step 6613 | loss:2.104466199874878 lr:1.586111169661435e-05 tokens_per_second_per_gpu:2190.0313225148075 
Step 6614 | loss:2.069944381713867 lr:1.5839853038103125e-05 tokens_per_second_per_gpu:2186.705381755222 
Step 6615 | loss:2.053098201751709 lr:1.581860741021457e-05 tokens_per_second_per_gpu:2167.8999380108394 
Step 6616 | loss:2.0294601917266846 lr:1.579737481623813e-05 tokens_per_second_per_gpu:2141.00727749513 
Step 6617 | loss:2.0543229579925537 lr:1.57761552594613e-05 tokens_per_second_per_gpu:2179.2921813028847 
Step 6618 | loss:2.0625767707824707 lr:1.575494874316954e-05 tokens_per_second_per_gpu:2192.810191059265 
Step 6619 | loss:2.069324493408203 lr:1.5733755270646256e-05 tokens_per_second_per_gpu:2171.1660308276764 
Step 6620 | loss:2.0979349613189697 lr:1.5712574845172888e-05 tokens_per_second_per_gpu:2128.3535020409277 
Step 6621 | loss:2.0679550170898438 lr:1.569140747002883e-05 tokens_per_second_per_gpu:2172.2413326104133 
Step 6622 | loss:2.083265781402588 lr:1.567025314849142e-05 tokens_per_second_per_gpu:2175.6861235695146 
Step 6623 | loss:2.1080126762390137 lr:1.5649111883836033e-05 tokens_per_second_per_gpu:2029.5854696789347 
Step 6624 | loss:2.0417847633361816 lr:1.562798367933599e-05 tokens_per_second_per_gpu:2187.205767437125 
Step 6625 | loss:2.1015968322753906 lr:1.5606868538262598e-05 tokens_per_second_per_gpu:2162.56589695594 
Step 6626 | loss:2.0628538131713867 lr:1.5585766463885155e-05 tokens_per_second_per_gpu:2079.6527259673862 
Step 6627 | loss:2.1460957527160645 lr:1.55646774594709e-05 tokens_per_second_per_gpu:2188.6755194227508 
Step 6628 | loss:1.9975134134292603 lr:1.5543601528285102e-05 tokens_per_second_per_gpu:2189.1482576317435 
Step 6629 | loss:2.095736503601074 lr:1.5522538673590913e-05 tokens_per_second_per_gpu:2152.543838395049 
Step 6630 | loss:2.07838773727417 lr:1.5501488898649608e-05 tokens_per_second_per_gpu:2171.818932945028 
Step 6631 | loss:2.0734610557556152 lr:1.5480452206720285e-05 tokens_per_second_per_gpu:2178.6103244022665 
Step 6632 | loss:2.1522083282470703 lr:1.54594286010601e-05 tokens_per_second_per_gpu:2189.603636540679 
Step 6633 | loss:2.060814380645752 lr:1.5438418084924154e-05 tokens_per_second_per_gpu:2188.185089568142 
Step 6634 | loss:2.0640406608581543 lr:1.5417420661565584e-05 tokens_per_second_per_gpu:2178.2641141099007 
Step 6635 | loss:2.072368621826172 lr:1.5396436334235354e-05 tokens_per_second_per_gpu:2192.248416971051 
Step 6636 | loss:2.0624747276306152 lr:1.5375465106182596e-05 tokens_per_second_per_gpu:2178.51506206031 
Step 6637 | loss:2.0368409156799316 lr:1.5354506980654238e-05 tokens_per_second_per_gpu:2188.812696097635 
Step 6638 | loss:2.0373952388763428 lr:1.5333561960895282e-05 tokens_per_second_per_gpu:2181.605168917163 
Step 6639 | loss:2.0357651710510254 lr:1.531263005014867e-05 tokens_per_second_per_gpu:2137.695262743779 
Step 6640 | loss:2.0698513984680176 lr:1.5291711251655316e-05 tokens_per_second_per_gpu:2193.7861910272495 
Step 6641 | loss:2.091885566711426 lr:1.5270805568654102e-05 tokens_per_second_per_gpu:2174.913376728239 
Step 6642 | loss:2.048849105834961 lr:1.52499130043819e-05 tokens_per_second_per_gpu:2175.007174517724 
Step 6643 | loss:2.038825511932373 lr:1.5229033562073503e-05 tokens_per_second_per_gpu:2139.3237328119144 
Step 6644 | loss:2.0571441650390625 lr:1.5208167244961712e-05 tokens_per_second_per_gpu:2137.6546485656945 
Step 6645 | loss:2.0161852836608887 lr:1.518731405627728e-05 tokens_per_second_per_gpu:2134.1730079110366 
Step 6646 | loss:2.0479819774627686 lr:1.5166473999248953e-05 tokens_per_second_per_gpu:2180.6404560303536 
Step 6647 | loss:2.0826845169067383 lr:1.5145647077103398e-05 tokens_per_second_per_gpu:2189.920075503436 
Step 6648 | loss:2.054105043411255 lr:1.512483329306532e-05 tokens_per_second_per_gpu:2192.676130759754 
Step 6649 | loss:2.0224251747131348 lr:1.5104032650357281e-05 tokens_per_second_per_gpu:2179.01047400597 
Step 6650 | loss:2.050473690032959 lr:1.5083245152199899e-05 tokens_per_second_per_gpu:2166.0529280276814 
Step 6651 | loss:2.0827274322509766 lr:1.5062470801811735e-05 tokens_per_second_per_gpu:2107.187929421315 
Step 6652 | loss:2.101139545440674 lr:1.5041709602409303e-05 tokens_per_second_per_gpu:2192.5775275110273 
Step 6653 | loss:2.016482353210449 lr:1.5020961557207091e-05 tokens_per_second_per_gpu:2154.9290544990495 
Step 6654 | loss:2.0698609352111816 lr:1.5000226669417528e-05 tokens_per_second_per_gpu:2190.1457151461627 
Step 6655 | loss:2.037008285522461 lr:1.4979504942251065e-05 tokens_per_second_per_gpu:2174.388996575275 
Step 6656 | loss:2.0904338359832764 lr:1.4958796378916007e-05 tokens_per_second_per_gpu:2194.0791947632565 
Step 6657 | loss:2.112947940826416 lr:1.4938100982618763e-05 tokens_per_second_per_gpu:2192.0174364752193 
Step 6658 | loss:2.0241737365722656 lr:1.4917418756563562e-05 tokens_per_second_per_gpu:2173.1157559915787 
Step 6659 | loss:2.0423643589019775 lr:1.4896749703952684e-05 tokens_per_second_per_gpu:2141.226635557292 
Step 6660 | loss:2.0384793281555176 lr:1.487609382798636e-05 tokens_per_second_per_gpu:2191.928846030849 
Step 6661 | loss:2.0195112228393555 lr:1.4855451131862741e-05 tokens_per_second_per_gpu:2158.3561992446444 
Step 6662 | loss:2.0853207111358643 lr:1.4834821618777973e-05 tokens_per_second_per_gpu:2176.0339786643917 
Step 6663 | loss:2.0555882453918457 lr:1.4814205291926175e-05 tokens_per_second_per_gpu:2133.676260992735 
Step 6664 | loss:2.032116174697876 lr:1.4793602154499352e-05 tokens_per_second_per_gpu:2145.2836022941046 
Step 6665 | loss:2.063089370727539 lr:1.4773012209687543e-05 tokens_per_second_per_gpu:2131.411153351283 
Step 6666 | loss:1.975435733795166 lr:1.4752435460678705e-05 tokens_per_second_per_gpu:2145.1743120574215 
Step 6667 | loss:2.059356689453125 lr:1.4731871910658756e-05 tokens_per_second_per_gpu:2143.606666844222 
Step 6668 | loss:2.04994535446167 lr:1.4711321562811597e-05 tokens_per_second_per_gpu:2161.436873948225 
Step 6669 | loss:2.0960521697998047 lr:1.469078442031907e-05 tokens_per_second_per_gpu:2180.9735901488752 
Step 6670 | loss:2.0757293701171875 lr:1.4670260486360931e-05 tokens_per_second_per_gpu:2135.1924759553817 
Step 6671 | loss:2.0357017517089844 lr:1.4649749764114951e-05 tokens_per_second_per_gpu:2082.4272381611627 
Step 6672 | loss:2.1137804985046387 lr:1.4629252256756821e-05 tokens_per_second_per_gpu:2172.27786817072 
Step 6673 | loss:2.0764801502227783 lr:1.4608767967460202e-05 tokens_per_second_per_gpu:2191.336614767035 
Step 6674 | loss:2.01534104347229 lr:1.4588296899396703e-05 tokens_per_second_per_gpu:2174.984067560721 
Step 6675 | loss:2.0835647583007812 lr:1.456783905573591e-05 tokens_per_second_per_gpu:2143.7561485643155 
Step 6676 | loss:2.0581276416778564 lr:1.454739443964529e-05 tokens_per_second_per_gpu:2174.16659336075 
Step 6677 | loss:2.046924591064453 lr:1.452696305429031e-05 tokens_per_second_per_gpu:2122.5577262609236 
Step 6678 | loss:2.104766368865967 lr:1.450654490283445e-05 tokens_per_second_per_gpu:2143.2442345024756 
Step 6679 | loss:2.0561985969543457 lr:1.4486139988439008e-05 tokens_per_second_per_gpu:2159.6041100323737 
Step 6680 | loss:2.127472400665283 lr:1.4465748314263339e-05 tokens_per_second_per_gpu:2162.926433197476 
Step 6681 | loss:2.1355810165405273 lr:1.444536988346471e-05 tokens_per_second_per_gpu:2181.5361838663425 
Step 6682 | loss:2.107290267944336 lr:1.4425004699198341e-05 tokens_per_second_per_gpu:2168.5784026786214 
Step 6683 | loss:2.1184113025665283 lr:1.4404652764617355e-05 tokens_per_second_per_gpu:2158.2805916443986 
Step 6684 | loss:2.028451919555664 lr:1.4384314082872952e-05 tokens_per_second_per_gpu:2146.937221991077 
Step 6685 | loss:2.091770648956299 lr:1.4363988657114124e-05 tokens_per_second_per_gpu:2134.998873909052 
Step 6686 | loss:2.0581188201904297 lr:1.4343676490487912e-05 tokens_per_second_per_gpu:2185.913395849652 
Step 6687 | loss:2.0451900959014893 lr:1.4323377586139276e-05 tokens_per_second_per_gpu:2170.293101463426 
Step 6688 | loss:2.0388453006744385 lr:1.4303091947211101e-05 tokens_per_second_per_gpu:2091.8525567580573 
Step 6689 | loss:2.117689609527588 lr:1.4282819576844264e-05 tokens_per_second_per_gpu:2176.8559789283368 
Step 6690 | loss:2.0710608959198 lr:1.4262560478177567e-05 tokens_per_second_per_gpu:2174.666202332704 
Step 6691 | loss:2.042684316635132 lr:1.424231465434771e-05 tokens_per_second_per_gpu:2179.3933837343416 
Step 6692 | loss:2.0665817260742188 lr:1.422208210848941e-05 tokens_per_second_per_gpu:2138.778370081163 
Step 6693 | loss:2.068448066711426 lr:1.4201862843735292e-05 tokens_per_second_per_gpu:2148.9762461773516 
Step 6694 | loss:2.0453076362609863 lr:1.4181656863215932e-05 tokens_per_second_per_gpu:2181.456697498153 
Step 6695 | loss:2.025789737701416 lr:1.4161464170059846e-05 tokens_per_second_per_gpu:2176.339181115656 
Step 6696 | loss:2.067873239517212 lr:1.4141284767393526e-05 tokens_per_second_per_gpu:2179.436664017716 
Step 6697 | loss:2.043199062347412 lr:1.4121118658341315e-05 tokens_per_second_per_gpu:2192.6157967759445 
Step 6698 | loss:2.0469813346862793 lr:1.4100965846025581e-05 tokens_per_second_per_gpu:2165.777562017626 
Step 6699 | loss:2.0788979530334473 lr:1.4080826333566621e-05 tokens_per_second_per_gpu:2183.596320946034 
Step 6700 | loss:2.069528579711914 lr:1.406070012408266e-05 tokens_per_second_per_gpu:2173.8672467372116 
Step 6701 | loss:2.0792641639709473 lr:1.404058722068986e-05 tokens_per_second_per_gpu:2177.837764618349 
Step 6702 | loss:2.104968547821045 lr:1.4020487626502343e-05 tokens_per_second_per_gpu:2190.6421071084437 
Step 6703 | loss:2.0538692474365234 lr:1.4000401344632119e-05 tokens_per_second_per_gpu:2164.351460837187 
Step 6704 | loss:2.072110652923584 lr:1.3980328378189178e-05 tokens_per_second_per_gpu:2192.9966365728915 
Step 6705 | loss:2.064622402191162 lr:1.396026873028149e-05 tokens_per_second_per_gpu:2151.2380742046453 
Step 6706 | loss:2.061432361602783 lr:1.3940222404014869e-05 tokens_per_second_per_gpu:2193.670382259384 
Step 6707 | loss:2.1175284385681152 lr:1.3920189402493134e-05 tokens_per_second_per_gpu:2176.0905481054306 
Step 6708 | loss:2.062638282775879 lr:1.3900169728818002e-05 tokens_per_second_per_gpu:2167.7601707874737 
Step 6709 | loss:2.096479892730713 lr:1.3880163386089185e-05 tokens_per_second_per_gpu:2199.3649100180314 
Step 6710 | loss:2.1009864807128906 lr:1.3860170377404213e-05 tokens_per_second_per_gpu:2186.576700879774 
Step 6711 | loss:2.081082344055176 lr:1.3840190705858724e-05 tokens_per_second_per_gpu:2171.5498079756044 
Step 6712 | loss:2.0377249717712402 lr:1.3820224374546132e-05 tokens_per_second_per_gpu:2146.9863810011148 
Step 6713 | loss:2.100391387939453 lr:1.3800271386557873e-05 tokens_per_second_per_gpu:2072.1850679144263 
Step 6714 | loss:2.0533084869384766 lr:1.3780331744983277e-05 tokens_per_second_per_gpu:2192.0731172546634 
Step 6715 | loss:2.1487650871276855 lr:1.376040545290963e-05 tokens_per_second_per_gpu:2155.2149069557063 
Step 6716 | loss:2.0487117767333984 lr:1.3740492513422165e-05 tokens_per_second_per_gpu:2171.6395352543195 
Step 6717 | loss:2.0660476684570312 lr:1.3720592929604026e-05 tokens_per_second_per_gpu:2184.117174490258 
Step 6718 | loss:2.072906970977783 lr:1.370070670453626e-05 tokens_per_second_per_gpu:2077.867595831714 
Step 6719 | loss:2.0018434524536133 lr:1.368083384129789e-05 tokens_per_second_per_gpu:2190.5907587015126 
Step 6720 | loss:2.051243305206299 lr:1.366097434296587e-05 tokens_per_second_per_gpu:2192.844663292388 
Step 6721 | loss:2.035782814025879 lr:1.364112821261505e-05 tokens_per_second_per_gpu:2069.891273060619 
Step 6722 | loss:2.0846402645111084 lr:1.362129545331825e-05 tokens_per_second_per_gpu:2124.6679023660267 
Step 6723 | loss:2.116651773452759 lr:1.3601476068146224e-05 tokens_per_second_per_gpu:2156.0184879181093 
Step 6724 | loss:2.0554332733154297 lr:1.3581670060167573e-05 tokens_per_second_per_gpu:2115.833743035577 
Step 6725 | loss:2.0446815490722656 lr:1.3561877432448922e-05 tokens_per_second_per_gpu:2165.1898248060043 
Step 6726 | loss:2.040022850036621 lr:1.3542098188054785e-05 tokens_per_second_per_gpu:2187.8372038612906 
Step 6727 | loss:2.0502681732177734 lr:1.3522332330047604e-05 tokens_per_second_per_gpu:2183.8042446518443 
Step 6728 | loss:2.0266880989074707 lr:1.3502579861487764e-05 tokens_per_second_per_gpu:2129.337692962373 
Step 6729 | loss:2.1105904579162598 lr:1.3482840785433559e-05 tokens_per_second_per_gpu:2170.6205630873133 
Step 6730 | loss:2.1151726245880127 lr:1.3463115104941205e-05 tokens_per_second_per_gpu:2192.7443829006884 
Step 6731 | loss:2.0913124084472656 lr:1.3443402823064832e-05 tokens_per_second_per_gpu:2193.8551860363223 
Step 6732 | loss:2.063218832015991 lr:1.3423703942856592e-05 tokens_per_second_per_gpu:2186.339170654935 
Step 6733 | loss:2.003005027770996 lr:1.340401846736643e-05 tokens_per_second_per_gpu:2178.9471294072196 
Step 6734 | loss:2.068504810333252 lr:1.3384346399642278e-05 tokens_per_second_per_gpu:2180.702110119568 
Step 6735 | loss:2.031902313232422 lr:1.3364687742729986e-05 tokens_per_second_per_gpu:2168.982364016568 
Step 6736 | loss:2.0166943073272705 lr:1.3345042499673377e-05 tokens_per_second_per_gpu:2182.83005269531 
Step 6737 | loss:2.040168285369873 lr:1.332541067351406e-05 tokens_per_second_per_gpu:2098.3347394734556 
Step 6738 | loss:2.095208168029785 lr:1.3305792267291738e-05 tokens_per_second_per_gpu:2187.912015043117 
Step 6739 | loss:2.0757791996002197 lr:1.3286187284043916e-05 tokens_per_second_per_gpu:2176.5648641747002 
Step 6740 | loss:2.105268955230713 lr:1.3266595726806052e-05 tokens_per_second_per_gpu:2145.1718750502223 
Step 6741 | loss:2.0436158180236816 lr:1.3247017598611543e-05 tokens_per_second_per_gpu:2182.817024251247 
Step 6742 | loss:2.1249732971191406 lr:1.322745290249171e-05 tokens_per_second_per_gpu:2139.6939872857024 
Step 6743 | loss:2.0467138290405273 lr:1.3207901641475751e-05 tokens_per_second_per_gpu:2135.3258127722806 
Step 6744 | loss:2.0844616889953613 lr:1.3188363818590854e-05 tokens_per_second_per_gpu:2198.244790968456 
Step 6745 | loss:1.9998366832733154 lr:1.3168839436862045e-05 tokens_per_second_per_gpu:2120.9234491272914 
Step 6746 | loss:2.057749032974243 lr:1.3149328499312308e-05 tokens_per_second_per_gpu:2187.2663081443757 
Step 6747 | loss:2.074179172515869 lr:1.3129831008962568e-05 tokens_per_second_per_gpu:2082.266850615397 
Step 6748 | loss:2.1316795349121094 lr:1.3110346968831643e-05 tokens_per_second_per_gpu:2179.3667904595486 
Step 6749 | loss:2.048154830932617 lr:1.3090876381936268e-05 tokens_per_second_per_gpu:2095.701047709382 
Step 6750 | loss:2.0669970512390137 lr:1.3071419251291106e-05 tokens_per_second_per_gpu:2146.7926787401716 
Step 6751 | loss:2.0943398475646973 lr:1.3051975579908715e-05 tokens_per_second_per_gpu:2125.412436436641 
Step 6752 | loss:2.0000667572021484 lr:1.3032545370799587e-05 tokens_per_second_per_gpu:2188.4635213680995 
Step 6753 | loss:2.0982978343963623 lr:1.3013128626972126e-05 tokens_per_second_per_gpu:2168.4230284563746 
Step 6754 | loss:2.0583646297454834 lr:1.299372535143265e-05 tokens_per_second_per_gpu:2165.250827363985 
Step 6755 | loss:2.019947052001953 lr:1.2974335547185401e-05 tokens_per_second_per_gpu:2197.391879452763 
Step 6756 | loss:2.0448946952819824 lr:1.2954959217232543e-05 tokens_per_second_per_gpu:2186.683655431725 
Step 6757 | loss:2.0593740940093994 lr:1.2935596364574098e-05 tokens_per_second_per_gpu:2191.1046744109617 
Step 6758 | loss:2.049886703491211 lr:1.2916246992208036e-05 tokens_per_second_per_gpu:2157.349188591587 
Step 6759 | loss:2.0512430667877197 lr:1.2896911103130327e-05 tokens_per_second_per_gpu:2119.6301113464947 
Step 6760 | loss:1.9988986253738403 lr:1.2877588700334675e-05 tokens_per_second_per_gpu:2196.234332547193 
Step 6761 | loss:2.010887384414673 lr:1.2858279786812843e-05 tokens_per_second_per_gpu:2138.1819302314498 
Step 6762 | loss:2.08123779296875 lr:1.283898436555444e-05 tokens_per_second_per_gpu:2173.382402159944 
Step 6763 | loss:2.036749839782715 lr:1.2819702439546998e-05 tokens_per_second_per_gpu:2139.022271535602 
Step 6764 | loss:2.041105031967163 lr:1.2800434011775975e-05 tokens_per_second_per_gpu:2162.583438961183 
Step 6765 | loss:2.02953839302063 lr:1.2781179085224736e-05 tokens_per_second_per_gpu:2185.419249956899 
Step 6766 | loss:2.061814308166504 lr:1.2761937662874512e-05 tokens_per_second_per_gpu:2184.0834022222884 
Step 6767 | loss:2.092473030090332 lr:1.2742709747704496e-05 tokens_per_second_per_gpu:2159.7668746961554 
Step 6768 | loss:2.0845770835876465 lr:1.272349534269176e-05 tokens_per_second_per_gpu:2193.373351780145 
Step 6769 | loss:2.013777256011963 lr:1.2704294450811306e-05 tokens_per_second_per_gpu:2090.408293355897 
Step 6770 | loss:2.0654125213623047 lr:1.2685107075036029e-05 tokens_per_second_per_gpu:2183.2735112318887 
Step 6771 | loss:2.1187946796417236 lr:1.2665933218336768e-05 tokens_per_second_per_gpu:2191.7267757807667 
Step 6772 | loss:2.0909972190856934 lr:1.2646772883682168e-05 tokens_per_second_per_gpu:2186.419003883536 
Step 6773 | loss:2.0534350872039795 lr:1.262762607403889e-05 tokens_per_second_per_gpu:2173.5714880468527 
Step 6774 | loss:2.063817024230957 lr:1.260849279237145e-05 tokens_per_second_per_gpu:2191.2989209191733 
Step 6775 | loss:2.080124855041504 lr:1.2589373041642272e-05 tokens_per_second_per_gpu:2187.464919264909 
Step 6776 | loss:2.0415520668029785 lr:1.2570266824811716e-05 tokens_per_second_per_gpu:2177.2072374444974 
Step 6777 | loss:2.0939860343933105 lr:1.2551174144838018e-05 tokens_per_second_per_gpu:2182.0400008860997 
Step 6778 | loss:2.0456113815307617 lr:1.253209500467728e-05 tokens_per_second_per_gpu:2183.3186965672407 
Step 6779 | loss:2.061009407043457 lr:1.2513029407283571e-05 tokens_per_second_per_gpu:2191.7943840567627 
Step 6780 | loss:2.0831360816955566 lr:1.2493977355608888e-05 tokens_per_second_per_gpu:2104.1940728978257 
Step 6781 | loss:2.0553741455078125 lr:1.2474938852603024e-05 tokens_per_second_per_gpu:2165.339066293152 
Step 6782 | loss:2.0378904342651367 lr:1.2455913901213756e-05 tokens_per_second_per_gpu:2188.8778255764514 
Step 6783 | loss:2.055453300476074 lr:1.2436902504386761e-05 tokens_per_second_per_gpu:2181.297138772016 
Step 6784 | loss:2.0471506118774414 lr:1.2417904665065572e-05 tokens_per_second_per_gpu:2152.972242044848 
Step 6785 | loss:2.147735118865967 lr:1.2398920386191615e-05 tokens_per_second_per_gpu:2193.903928668339 
Step 6786 | loss:2.0409023761749268 lr:1.237994967070435e-05 tokens_per_second_per_gpu:2141.290621408799 
Step 6787 | loss:2.0630550384521484 lr:1.2360992521540948e-05 tokens_per_second_per_gpu:2154.8470582312143 
Step 6788 | loss:2.099592685699463 lr:1.2342048941636596e-05 tokens_per_second_per_gpu:2172.4914078404186 
Step 6789 | loss:2.0528383255004883 lr:1.232311893392436e-05 tokens_per_second_per_gpu:2130.7765168517044 
Step 6790 | loss:2.0812153816223145 lr:1.2304202501335183e-05 tokens_per_second_per_gpu:2139.949966659884 
Step 6791 | loss:2.0580272674560547 lr:1.2285299646797943e-05 tokens_per_second_per_gpu:2124.676359953632 
Step 6792 | loss:2.10252046585083 lr:1.226641037323939e-05 tokens_per_second_per_gpu:2191.2906465560054 
Step 6793 | loss:2.0554754734039307 lr:1.224753468358415e-05 tokens_per_second_per_gpu:2178.755541968108 
Step 6794 | loss:2.0609078407287598 lr:1.2228672580754775e-05 tokens_per_second_per_gpu:2183.743107166784 
Step 6795 | loss:2.075450897216797 lr:1.2209824067671727e-05 tokens_per_second_per_gpu:2151.622896284373 
Step 6796 | loss:2.103566884994507 lr:1.219098914725333e-05 tokens_per_second_per_gpu:2168.554609411794 
Step 6797 | loss:2.118647575378418 lr:1.2172167822415815e-05 tokens_per_second_per_gpu:2164.691439654651 
Step 6798 | loss:2.016854763031006 lr:1.2153360096073352e-05 tokens_per_second_per_gpu:2185.1079653935817 
Step 6799 | loss:2.045025587081909 lr:1.2134565971137912e-05 tokens_per_second_per_gpu:2126.8373123752303 
Step 6800 | loss:2.090942621231079 lr:1.2115785450519434e-05 tokens_per_second_per_gpu:2165.5111601069393 
Step 6801 | loss:2.1122422218322754 lr:1.2097018537125737e-05 tokens_per_second_per_gpu:2180.351698198969 
Step 6802 | loss:2.0325417518615723 lr:1.2078265233862517e-05 tokens_per_second_per_gpu:2173.1783831528314 
Step 6803 | loss:2.0818800926208496 lr:1.2059525543633366e-05 tokens_per_second_per_gpu:2135.768283201868 
Step 6804 | loss:2.134904384613037 lr:1.2040799469339815e-05 tokens_per_second_per_gpu:2099.785504928569 
Step 6805 | loss:2.0853166580200195 lr:1.2022087013881189e-05 tokens_per_second_per_gpu:2185.157572085953 
Step 6806 | loss:1.9916152954101562 lr:1.2003388180154761e-05 tokens_per_second_per_gpu:2163.1326610913725 
Step 6807 | loss:2.047659158706665 lr:1.1984702971055772e-05 tokens_per_second_per_gpu:2153.2682060881807 
Step 6808 | loss:2.079285144805908 lr:1.1966031389477194e-05 tokens_per_second_per_gpu:2110.7081897525236 
Step 6809 | loss:2.0367774963378906 lr:1.1947373438310005e-05 tokens_per_second_per_gpu:2169.45777696114 
Step 6810 | loss:2.111764669418335 lr:1.1928729120443071e-05 tokens_per_second_per_gpu:2162.445421020378 
Step 6811 | loss:2.033407211303711 lr:1.191009843876305e-05 tokens_per_second_per_gpu:2137.0429345763228 
Step 6812 | loss:2.0376758575439453 lr:1.1891481396154558e-05 tokens_per_second_per_gpu:2185.6727106684975 
Step 6813 | loss:2.074424982070923 lr:1.1872877995500176e-05 tokens_per_second_per_gpu:2119.462209031925 
Step 6814 | loss:2.076956272125244 lr:1.1854288239680212e-05 tokens_per_second_per_gpu:2193.737664487467 
Step 6815 | loss:2.081484317779541 lr:1.1835712131572974e-05 tokens_per_second_per_gpu:2145.564514520415 
Step 6816 | loss:2.0559351444244385 lr:1.1817149674054618e-05 tokens_per_second_per_gpu:2104.5466893516837 
Step 6817 | loss:2.071810007095337 lr:1.17986008699992e-05 tokens_per_second_per_gpu:2071.126365753279 
Step 6818 | loss:2.132617235183716 lr:1.1780065722278643e-05 tokens_per_second_per_gpu:2109.301202250804 
Step 6819 | loss:2.012911558151245 lr:1.1761544233762789e-05 tokens_per_second_per_gpu:2189.7352080254536 
Step 6820 | loss:2.073300361633301 lr:1.174303640731932e-05 tokens_per_second_per_gpu:2193.047684141465 
Step 6821 | loss:2.0729284286499023 lr:1.172454224581383e-05 tokens_per_second_per_gpu:2111.1109590603946 
Step 6822 | loss:2.098834991455078 lr:1.1706061752109798e-05 tokens_per_second_per_gpu:2149.3112128986468 
Step 6823 | loss:2.0902764797210693 lr:1.168759492906858e-05 tokens_per_second_per_gpu:2130.1864193530764 
Step 6824 | loss:2.036449432373047 lr:1.166914177954942e-05 tokens_per_second_per_gpu:2184.2630676501753 
Step 6825 | loss:2.067983627319336 lr:1.1650702306409467e-05 tokens_per_second_per_gpu:2156.8383188651615 
Step 6826 | loss:2.029386520385742 lr:1.1632276512503681e-05 tokens_per_second_per_gpu:2178.2566147399984 
Step 6827 | loss:2.0796351432800293 lr:1.161386440068497e-05 tokens_per_second_per_gpu:2183.2613965824935 
Step 6828 | loss:2.034618616104126 lr:1.159546597380412e-05 tokens_per_second_per_gpu:2127.7473436411733 
Step 6829 | loss:2.1530070304870605 lr:1.1577081234709763e-05 tokens_per_second_per_gpu:2187.6083273155878 
Step 6830 | loss:2.048097610473633 lr:1.1558710186248444e-05 tokens_per_second_per_gpu:2138.5119285653936 
Step 6831 | loss:2.065741777420044 lr:1.15403528312646e-05 tokens_per_second_per_gpu:2125.2597184800743 
Step 6832 | loss:2.0186517238616943 lr:1.1522009172600468e-05 tokens_per_second_per_gpu:2151.709699782878 
Step 6833 | loss:2.096129894256592 lr:1.1503679213096219e-05 tokens_per_second_per_gpu:2136.588101454412 
Step 6834 | loss:2.0948753356933594 lr:1.1485362955589984e-05 tokens_per_second_per_gpu:2139.3849900039313 
Step 6835 | loss:2.059530258178711 lr:1.1467060402917618e-05 tokens_per_second_per_gpu:2190.47336265505 
Step 6836 | loss:2.0199718475341797 lr:1.1448771557912952e-05 tokens_per_second_per_gpu:2154.814099467529 
Step 6837 | loss:2.0683465003967285 lr:1.1430496423407688e-05 tokens_per_second_per_gpu:2067.755324207969 
Step 6838 | loss:2.0601863861083984 lr:1.1412235002231342e-05 tokens_per_second_per_gpu:2193.66095568016 
Step 6839 | loss:2.077955722808838 lr:1.1393987297211395e-05 tokens_per_second_per_gpu:2181.01345849459 
Step 6840 | loss:2.119983673095703 lr:1.1375753311173166e-05 tokens_per_second_per_gpu:2149.498319055215 
Step 6841 | loss:2.090146541595459 lr:1.1357533046939816e-05 tokens_per_second_per_gpu:2167.307226864619 
Step 6842 | loss:2.0861995220184326 lr:1.1339326507332414e-05 tokens_per_second_per_gpu:2153.3497007818687 
Step 6843 | loss:2.0677413940429688 lr:1.1321133695169927e-05 tokens_per_second_per_gpu:2114.3715309266404 
Step 6844 | loss:2.1173534393310547 lr:1.1302954613269156e-05 tokens_per_second_per_gpu:2145.2106799000308 
Step 6845 | loss:2.080756664276123 lr:1.1284789264444785e-05 tokens_per_second_per_gpu:2169.5592906993643 
Step 6846 | loss:2.097243309020996 lr:1.1266637651509416e-05 tokens_per_second_per_gpu:2119.0821188492987 
Step 6847 | loss:2.081911563873291 lr:1.1248499777273424e-05 tokens_per_second_per_gpu:2166.8791058273696 
Step 6848 | loss:2.0450804233551025 lr:1.1230375644545166e-05 tokens_per_second_per_gpu:2059.1491513338597 
Step 6849 | loss:2.0665993690490723 lr:1.1212265256130793e-05 tokens_per_second_per_gpu:2124.601976851183 
Step 6850 | loss:2.089036464691162 lr:1.1194168614834389e-05 tokens_per_second_per_gpu:2167.5989201342386 
Step 6851 | loss:2.088521957397461 lr:1.1176085723457862e-05 tokens_per_second_per_gpu:2190.978665628159 
Step 6852 | loss:2.113743543624878 lr:1.1158016584801045e-05 tokens_per_second_per_gpu:2174.0231414226396 
Step 6853 | loss:2.0797133445739746 lr:1.1139961201661541e-05 tokens_per_second_per_gpu:2193.795382005457 
Step 6854 | loss:2.0445680618286133 lr:1.1121919576834927e-05 tokens_per_second_per_gpu:2193.0143936997865 
Step 6855 | loss:2.007110834121704 lr:1.1103891713114612e-05 tokens_per_second_per_gpu:2177.7943257197244 
Step 6856 | loss:2.11183500289917 lr:1.1085877613291861e-05 tokens_per_second_per_gpu:2192.314485311694 
Step 6857 | loss:2.1147301197052 lr:1.1067877280155836e-05 tokens_per_second_per_gpu:2133.8936564875958 
Step 6858 | loss:2.0642731189727783 lr:1.1049890716493549e-05 tokens_per_second_per_gpu:2105.997882472237 
Step 6859 | loss:2.0553436279296875 lr:1.1031917925089862e-05 tokens_per_second_per_gpu:2181.691151386375 
Step 6860 | loss:2.073922634124756 lr:1.1013958908727517e-05 tokens_per_second_per_gpu:2139.1700309790594 
Step 6861 | loss:2.0871834754943848 lr:1.099601367018719e-05 tokens_per_second_per_gpu:2180.2967116506575 
Step 6862 | loss:2.0293619632720947 lr:1.0978082212247308e-05 tokens_per_second_per_gpu:2190.522135614665 
Step 6863 | loss:2.1027934551239014 lr:1.0960164537684247e-05 tokens_per_second_per_gpu:2174.5883092269846 
Step 6864 | loss:2.120119333267212 lr:1.0942260649272229e-05 tokens_per_second_per_gpu:2129.791045326707 
Step 6865 | loss:2.05783748626709 lr:1.0924370549783292e-05 tokens_per_second_per_gpu:2161.762654752343 
Step 6866 | loss:2.082160472869873 lr:1.090649424198743e-05 tokens_per_second_per_gpu:2196.8232776825844 
Step 6867 | loss:2.152449369430542 lr:1.0888631728652465e-05 tokens_per_second_per_gpu:2180.7946015388648 
Step 6868 | loss:2.0540313720703125 lr:1.0870783012544027e-05 tokens_per_second_per_gpu:2120.510252340972 
Step 6869 | loss:2.069570779800415 lr:1.0852948096425675e-05 tokens_per_second_per_gpu:2191.687546674426 
Step 6870 | loss:2.0526700019836426 lr:1.0835126983058829e-05 tokens_per_second_per_gpu:2097.8049259738445 
Step 6871 | loss:2.0003833770751953 lr:1.0817319675202698e-05 tokens_per_second_per_gpu:2193.5499981741937 
Step 6872 | loss:2.0290393829345703 lr:1.0799526175614472e-05 tokens_per_second_per_gpu:2127.241416176498 
Step 6873 | loss:2.050447940826416 lr:1.0781746487049138e-05 tokens_per_second_per_gpu:2164.388158849265 
Step 6874 | loss:2.1560025215148926 lr:1.0763980612259517e-05 tokens_per_second_per_gpu:2107.4165702916766 
Step 6875 | loss:2.1424546241760254 lr:1.074622855399633e-05 tokens_per_second_per_gpu:2175.8321387992505 
Step 6876 | loss:2.082200527191162 lr:1.0728490315008155e-05 tokens_per_second_per_gpu:2184.838570977225 
Step 6877 | loss:2.090635061264038 lr:1.0710765898041419e-05 tokens_per_second_per_gpu:2182.03284646937 
Step 6878 | loss:2.043069362640381 lr:1.0693055305840439e-05 tokens_per_second_per_gpu:2187.2110807246863 
Step 6879 | loss:2.047515392303467 lr:1.0675358541147362e-05 tokens_per_second_per_gpu:2190.606838834789 
Step 6880 | loss:2.1182878017425537 lr:1.0657675606702166e-05 tokens_per_second_per_gpu:2145.7138243580685 
Step 6881 | loss:2.060476303100586 lr:1.0640006505242738e-05 tokens_per_second_per_gpu:2094.550092253241 
Step 6882 | loss:2.080772638320923 lr:1.0622351239504857e-05 tokens_per_second_per_gpu:2140.7187269067663 
Step 6883 | loss:2.0725269317626953 lr:1.0604709812222046e-05 tokens_per_second_per_gpu:2174.3736193585464 
Step 6884 | loss:2.0947818756103516 lr:1.0587082226125777e-05 tokens_per_second_per_gpu:2196.8866639187872 
Step 6885 | loss:2.1189541816711426 lr:1.0569468483945366e-05 tokens_per_second_per_gpu:2091.448938045933 
Step 6886 | loss:2.026282787322998 lr:1.055186858840793e-05 tokens_per_second_per_gpu:2155.948427602916 
Step 6887 | loss:2.062891960144043 lr:1.0534282542238494e-05 tokens_per_second_per_gpu:2155.5523907897154 
Step 6888 | loss:2.084385395050049 lr:1.0516710348159985e-05 tokens_per_second_per_gpu:2185.0832276279634 
Step 6889 | loss:2.0377302169799805 lr:1.0499152008893055e-05 tokens_per_second_per_gpu:2176.1945474533422 
Step 6890 | loss:2.0810084342956543 lr:1.0481607527156324e-05 tokens_per_second_per_gpu:2188.0323333945744 
Step 6891 | loss:2.0842676162719727 lr:1.0464076905666221e-05 tokens_per_second_per_gpu:2194.358355312142 
Step 6892 | loss:2.057474374771118 lr:1.0446560147136997e-05 tokens_per_second_per_gpu:2188.4182088585244 
Step 6893 | loss:2.0587615966796875 lr:1.042905725428085e-05 tokens_per_second_per_gpu:2138.3607755086236 
Step 6894 | loss:2.0233969688415527 lr:1.0411568229807756e-05 tokens_per_second_per_gpu:2190.1904424905183 
Step 6895 | loss:2.0570590496063232 lr:1.0394093076425549e-05 tokens_per_second_per_gpu:2174.1813601286863 
Step 6896 | loss:2.0621066093444824 lr:1.0376631796839941e-05 tokens_per_second_per_gpu:2131.7753960740133 
Step 6897 | loss:2.0961289405822754 lr:1.0359184393754474e-05 tokens_per_second_per_gpu:2157.3881588349464 
Step 6898 | loss:2.025449275970459 lr:1.034175086987057e-05 tokens_per_second_per_gpu:2194.3821786703325 
Step 6899 | loss:2.1069397926330566 lr:1.0324331227887462e-05 tokens_per_second_per_gpu:2186.0955522199647 
Step 6900 | loss:2.0843400955200195 lr:1.0306925470502294e-05 tokens_per_second_per_gpu:2095.29887345699 
Step 6901 | loss:2.0768508911132812 lr:1.0289533600409962e-05 tokens_per_second_per_gpu:2171.0005222820837 
Step 6902 | loss:2.0893807411193848 lr:1.0272155620303315e-05 tokens_per_second_per_gpu:2164.1850938359976 
Step 6903 | loss:2.0647926330566406 lr:1.0254791532872987e-05 tokens_per_second_per_gpu:2126.9205568781217 
Step 6904 | loss:2.0691254138946533 lr:1.0237441340807496e-05 tokens_per_second_per_gpu:2162.337906515246 
Step 6905 | loss:2.0219781398773193 lr:1.0220105046793182e-05 tokens_per_second_per_gpu:2191.472500996746 
Step 6906 | loss:2.0213353633880615 lr:1.0202782653514287e-05 tokens_per_second_per_gpu:2179.4105588366774 
Step 6907 | loss:2.0942935943603516 lr:1.0185474163652786e-05 tokens_per_second_per_gpu:2163.760612597124 
Step 6908 | loss:2.0909366607666016 lr:1.0168179579888605e-05 tokens_per_second_per_gpu:2156.749005690933 
Step 6909 | loss:1.9827582836151123 lr:1.015089890489953e-05 tokens_per_second_per_gpu:2181.7319808536417 
Step 6910 | loss:2.0796256065368652 lr:1.0133632141361093e-05 tokens_per_second_per_gpu:2151.5820953005714 
Step 6911 | loss:2.0371286869049072 lr:1.0116379291946754e-05 tokens_per_second_per_gpu:2183.948212599841 
Step 6912 | loss:2.038642406463623 lr:1.009914035932782e-05 tokens_per_second_per_gpu:2187.6682711177787 
Step 6913 | loss:2.061863899230957 lr:1.0081915346173353e-05 tokens_per_second_per_gpu:2196.4382385490526 
Step 6914 | loss:2.0468554496765137 lr:1.0064704255150337e-05 tokens_per_second_per_gpu:2171.415597776359 
Step 6915 | loss:2.0640478134155273 lr:1.0047507088923647e-05 tokens_per_second_per_gpu:2192.185245369639 
Step 6916 | loss:2.076845169067383 lr:1.0030323850155887e-05 tokens_per_second_per_gpu:2194.9139398107336 
Step 6917 | loss:2.1085667610168457 lr:1.0013154541507586e-05 tokens_per_second_per_gpu:2125.2593977808356 
Step 6918 | loss:2.0729281902313232 lr:9.995999165637082e-06 tokens_per_second_per_gpu:2061.7006200503442 
Step 6919 | loss:2.077639102935791 lr:9.97885772520053e-06 tokens_per_second_per_gpu:2158.355387228763 
Step 6920 | loss:2.1002650260925293 lr:9.961730222852005e-06 tokens_per_second_per_gpu:2166.4676331629385 
Step 6921 | loss:2.075011730194092 lr:9.9446166612434e-06 tokens_per_second_per_gpu:2194.4180963634535 
Step 6922 | loss:2.0836315155029297 lr:9.92751704302437e-06 tokens_per_second_per_gpu:2126.105020646039 
Step 6923 | loss:2.0184054374694824 lr:9.910431370842487e-06 tokens_per_second_per_gpu:2162.662462550305 
Step 6924 | loss:2.054182767868042 lr:9.89335964734317e-06 tokens_per_second_per_gpu:2173.728436285066 
Step 6925 | loss:2.1084251403808594 lr:9.876301875169647e-06 tokens_per_second_per_gpu:2185.292529061339 
Step 6926 | loss:2.0494251251220703 lr:9.859258056962983e-06 tokens_per_second_per_gpu:2098.9444672938143 
Step 6927 | loss:2.0772929191589355 lr:9.842228195362114e-06 tokens_per_second_per_gpu:2101.853011028563 
Step 6928 | loss:2.0704705715179443 lr:9.825212293003772e-06 tokens_per_second_per_gpu:2105.3087112651315 
Step 6929 | loss:2.0544540882110596 lr:9.808210352522562e-06 tokens_per_second_per_gpu:2183.923389097974 
Step 6930 | loss:2.0450124740600586 lr:9.791222376550923e-06 tokens_per_second_per_gpu:2172.199452637441 
Step 6931 | loss:2.0860166549682617 lr:9.774248367719108e-06 tokens_per_second_per_gpu:2155.0582335520303 
Step 6932 | loss:2.051391363143921 lr:9.757288328655234e-06 tokens_per_second_per_gpu:2191.401031955859 
Step 6933 | loss:2.0629191398620605 lr:9.740342261985268e-06 tokens_per_second_per_gpu:2178.190330456348 
Step 6934 | loss:2.1215057373046875 lr:9.723410170332959e-06 tokens_per_second_per_gpu:2130.313530704617 
Step 6935 | loss:2.027298927307129 lr:9.706492056319904e-06 tokens_per_second_per_gpu:2144.955390702632 
Step 6936 | loss:2.1078503131866455 lr:9.689587922565624e-06 tokens_per_second_per_gpu:2184.694462777583 
Step 6937 | loss:2.0705621242523193 lr:9.672697771687356e-06 tokens_per_second_per_gpu:2087.6883665116975 
Step 6938 | loss:2.0890464782714844 lr:9.65582160630023e-06 tokens_per_second_per_gpu:2133.5208612312417 
Step 6939 | loss:2.115553379058838 lr:9.638959429017236e-06 tokens_per_second_per_gpu:2175.5929477933387 
Step 6940 | loss:2.020564079284668 lr:9.622111242449106e-06 tokens_per_second_per_gpu:2192.749591825427 
Step 6941 | loss:2.0624732971191406 lr:9.605277049204508e-06 tokens_per_second_per_gpu:2155.4423625584 
Step 6942 | loss:2.054266929626465 lr:9.588456851889927e-06 tokens_per_second_per_gpu:2194.453063861805 
Step 6943 | loss:2.121462106704712 lr:9.57165065310961e-06 tokens_per_second_per_gpu:2099.4769998822167 
Step 6944 | loss:2.0770697593688965 lr:9.554858455465688e-06 tokens_per_second_per_gpu:2157.8879269130584 
Step 6945 | loss:2.0552165508270264 lr:9.538080261558146e-06 tokens_per_second_per_gpu:2133.80070875928 
Step 6946 | loss:2.1092867851257324 lr:9.52131607398471e-06 tokens_per_second_per_gpu:2068.692010936609 
Step 6947 | loss:2.049741744995117 lr:9.504565895341077e-06 tokens_per_second_per_gpu:2133.6038049714007 
Step 6948 | loss:2.0830302238464355 lr:9.487829728220676e-06 tokens_per_second_per_gpu:2160.539702959617 
Step 6949 | loss:2.009096622467041 lr:9.471107575214754e-06 tokens_per_second_per_gpu:2180.7383142513168 
Step 6950 | loss:1.994828701019287 lr:9.454399438912454e-06 tokens_per_second_per_gpu:2188.2859065239813 
Step 6951 | loss:2.0404534339904785 lr:9.437705321900714e-06 tokens_per_second_per_gpu:2191.7670125992754 
Step 6952 | loss:2.0703985691070557 lr:9.421025226764301e-06 tokens_per_second_per_gpu:2180.7440864903 
Step 6953 | loss:2.1251604557037354 lr:9.404359156085818e-06 tokens_per_second_per_gpu:2159.902053513003 
Step 6954 | loss:2.097109794616699 lr:9.38770711244572e-06 tokens_per_second_per_gpu:2197.6299030318046 
Step 6955 | loss:2.066343069076538 lr:9.371069098422214e-06 tokens_per_second_per_gpu:2181.194224193273 
Step 6956 | loss:2.1185975074768066 lr:9.354445116591403e-06 tokens_per_second_per_gpu:2168.0359616602645 
Step 6957 | loss:2.0695114135742188 lr:9.33783516952721e-06 tokens_per_second_per_gpu:2189.0254146883863 
Step 6958 | loss:2.052748680114746 lr:9.321239259801363e-06 tokens_per_second_per_gpu:2185.4000491211855 
Step 6959 | loss:2.0225977897644043 lr:9.30465738998344e-06 tokens_per_second_per_gpu:2190.6285385179563 
Step 6960 | loss:2.074997901916504 lr:9.288089562640844e-06 tokens_per_second_per_gpu:2189.069875855148 
Step 6961 | loss:2.020883083343506 lr:9.271535780338759e-06 tokens_per_second_per_gpu:2170.988168325653 
Step 6962 | loss:2.0603532791137695 lr:9.25499604564023e-06 tokens_per_second_per_gpu:2172.286328346547 
Step 6963 | loss:2.109154462814331 lr:9.238470361106166e-06 tokens_per_second_per_gpu:2133.1546226020696 
Step 6964 | loss:2.059436798095703 lr:9.221958729295221e-06 tokens_per_second_per_gpu:2176.605846159039 
Step 6965 | loss:2.0675811767578125 lr:9.205461152763927e-06 tokens_per_second_per_gpu:2174.7097164402117 
Step 6966 | loss:2.0792880058288574 lr:9.188977634066642e-06 tokens_per_second_per_gpu:2193.120333946228 
Step 6967 | loss:2.1275055408477783 lr:9.172508175755468e-06 tokens_per_second_per_gpu:2196.035661740794 
Step 6968 | loss:2.0648279190063477 lr:9.156052780380464e-06 tokens_per_second_per_gpu:2168.4067952395135 
Step 6969 | loss:2.031266450881958 lr:9.139611450489416e-06 tokens_per_second_per_gpu:2153.852745506197 
Step 6970 | loss:2.066230297088623 lr:9.123184188627943e-06 tokens_per_second_per_gpu:2147.2496697639144 
Step 6971 | loss:2.0884017944335938 lr:9.106770997339498e-06 tokens_per_second_per_gpu:2188.2480524739763 
Step 6972 | loss:2.05824875831604 lr:9.090371879165394e-06 tokens_per_second_per_gpu:2188.4678370381944 
Step 6973 | loss:2.064423084259033 lr:9.073986836644654e-06 tokens_per_second_per_gpu:2102.9337270556953 
Step 6974 | loss:1.979988932609558 lr:9.057615872314252e-06 tokens_per_second_per_gpu:2131.1105004007068 
Step 6975 | loss:2.0056233406066895 lr:9.041258988708945e-06 tokens_per_second_per_gpu:2174.146664256975 
Step 6976 | loss:2.027310848236084 lr:9.024916188361233e-06 tokens_per_second_per_gpu:2155.201922594121 
Step 6977 | loss:2.117061138153076 lr:9.008587473801511e-06 tokens_per_second_per_gpu:2186.413755884289 
Step 6978 | loss:2.0753486156463623 lr:8.992272847557981e-06 tokens_per_second_per_gpu:2189.3313981473075 
Step 6979 | loss:2.129271984100342 lr:8.975972312156666e-06 tokens_per_second_per_gpu:2172.5358102249106 
Step 6980 | loss:2.089837074279785 lr:8.959685870121382e-06 tokens_per_second_per_gpu:2166.2295251668816 
Step 6981 | loss:2.0403106212615967 lr:8.943413523973809e-06 tokens_per_second_per_gpu:2147.50014402709 
Step 6982 | loss:2.05435848236084 lr:8.927155276233379e-06 tokens_per_second_per_gpu:2192.5859687684997 
Step 6983 | loss:2.040637493133545 lr:8.910911129417376e-06 tokens_per_second_per_gpu:2180.874197385216 
Step 6984 | loss:2.0706334114074707 lr:8.894681086040946e-06 tokens_per_second_per_gpu:2192.204631498363 
Step 6985 | loss:2.045498847961426 lr:8.878465148616966e-06 tokens_per_second_per_gpu:2155.654417619926 
Step 6986 | loss:2.0635180473327637 lr:8.862263319656172e-06 tokens_per_second_per_gpu:2107.7090124650667 
Step 6987 | loss:2.0790867805480957 lr:8.846075601667159e-06 tokens_per_second_per_gpu:2195.215069762191 
Step 6988 | loss:2.066239833831787 lr:8.829901997156231e-06 tokens_per_second_per_gpu:2141.47929805741 
Step 6989 | loss:2.08320951461792 lr:8.813742508627576e-06 tokens_per_second_per_gpu:2072.297122140838 
Step 6990 | loss:2.0677828788757324 lr:8.797597138583235e-06 tokens_per_second_per_gpu:2191.8524147115086 
Step 6991 | loss:2.062379837036133 lr:8.781465889522988e-06 tokens_per_second_per_gpu:2181.9791681945353 
Step 6992 | loss:2.0860695838928223 lr:8.765348763944448e-06 tokens_per_second_per_gpu:2187.3596031222046 
Step 6993 | loss:2.0510525703430176 lr:8.749245764343072e-06 tokens_per_second_per_gpu:2167.3269012137403 
Step 6994 | loss:2.0254058837890625 lr:8.733156893212068e-06 tokens_per_second_per_gpu:2194.478452036434 
Step 6995 | loss:2.0442488193511963 lr:8.717082153042534e-06 tokens_per_second_per_gpu:2180.8292784949854 
Step 6996 | loss:2.0560712814331055 lr:8.701021546323352e-06 tokens_per_second_per_gpu:2134.13434215937 
Step 6997 | loss:2.0557212829589844 lr:8.684975075541169e-06 tokens_per_second_per_gpu:2172.8186905683856 
Step 6998 | loss:2.0499186515808105 lr:8.668942743180497e-06 tokens_per_second_per_gpu:2188.248876130245 
Step 6999 | loss:2.147311210632324 lr:8.65292455172364e-06 tokens_per_second_per_gpu:2190.6487454519893 
Step 7000 | loss:2.0181941986083984 lr:8.636920503650713e-06 tokens_per_second_per_gpu:2146.504875817712 
Step 7001 | loss:2.080714225769043 lr:8.620930601439659e-06 tokens_per_second_per_gpu:2211.5616388825624 
Step 7002 | loss:2.0592684745788574 lr:8.604954847566216e-06 tokens_per_second_per_gpu:2100.193836556556 
Step 7003 | loss:2.0882601737976074 lr:8.588993244503907e-06 tokens_per_second_per_gpu:2201.296659981849 
Step 7004 | loss:2.1191906929016113 lr:8.573045794724088e-06 tokens_per_second_per_gpu:2177.7620338586867 
Step 7005 | loss:2.0195555686950684 lr:8.557112500695942e-06 tokens_per_second_per_gpu:2149.8082937712534 
Step 7006 | loss:2.058985948562622 lr:8.541193364886425e-06 tokens_per_second_per_gpu:2169.4341536202037 
Step 7007 | loss:2.0512962341308594 lr:8.525288389760322e-06 tokens_per_second_per_gpu:2164.3545221423824 
Step 7008 | loss:2.0467214584350586 lr:8.509397577780254e-06 tokens_per_second_per_gpu:2132.663064224463 
Step 7009 | loss:2.060624122619629 lr:8.493520931406552e-06 tokens_per_second_per_gpu:2176.6480928578276 
Step 7010 | loss:2.0407605171203613 lr:8.477658453097448e-06 tokens_per_second_per_gpu:2145.141723486302 
Step 7011 | loss:2.086358070373535 lr:8.46181014530898e-06 tokens_per_second_per_gpu:2100.0791398973074 
Step 7012 | loss:2.093421459197998 lr:8.445976010494905e-06 tokens_per_second_per_gpu:2166.6995468795103 
Step 7013 | loss:2.0631942749023438 lr:8.430156051106886e-06 tokens_per_second_per_gpu:2135.236260149246 
Step 7014 | loss:2.1065163612365723 lr:8.41435026959434e-06 tokens_per_second_per_gpu:2195.9812219289465 
Step 7015 | loss:2.080354928970337 lr:8.398558668404478e-06 tokens_per_second_per_gpu:2165.5093184931693 
Step 7016 | loss:2.115285634994507 lr:8.382781249982318e-06 tokens_per_second_per_gpu:2147.703852361173 
Step 7017 | loss:2.15926456451416 lr:8.367018016770767e-06 tokens_per_second_per_gpu:2183.295370658169 
Step 7018 | loss:2.084887742996216 lr:8.351268971210401e-06 tokens_per_second_per_gpu:2189.0682463115186 
Step 7019 | loss:2.0551676750183105 lr:8.335534115739696e-06 tokens_per_second_per_gpu:2111.559881457571 
Step 7020 | loss:1.9800190925598145 lr:8.3198134527949e-06 tokens_per_second_per_gpu:2151.6251067162525 
Step 7021 | loss:2.0563554763793945 lr:8.304106984810022e-06 tokens_per_second_per_gpu:2171.9798199412876 
Step 7022 | loss:2.007351875305176 lr:8.288414714216963e-06 tokens_per_second_per_gpu:2170.0050356103307 
Step 7023 | loss:2.138319253921509 lr:8.272736643445378e-06 tokens_per_second_per_gpu:2167.117391725625 
Step 7024 | loss:2.048222541809082 lr:8.25707277492268e-06 tokens_per_second_per_gpu:2153.580379334476 
Step 7025 | loss:2.1262025833129883 lr:8.241423111074165e-06 tokens_per_second_per_gpu:2193.9902268937353 
Step 7026 | loss:2.114260673522949 lr:8.22578765432287e-06 tokens_per_second_per_gpu:2089.270964590263 
Step 7027 | loss:2.0798721313476562 lr:8.210166407089659e-06 tokens_per_second_per_gpu:2102.471286388339 
Step 7028 | loss:2.04984712600708 lr:8.194559371793187e-06 tokens_per_second_per_gpu:2195.49114718072 
Step 7029 | loss:2.0658936500549316 lr:8.178966550849931e-06 tokens_per_second_per_gpu:2188.416277351028 
Step 7030 | loss:2.076982259750366 lr:8.163387946674117e-06 tokens_per_second_per_gpu:2142.8973263015873 
Step 7031 | loss:2.0685620307922363 lr:8.147823561677815e-06 tokens_per_second_per_gpu:2173.904128897928 
Step 7032 | loss:2.059515953063965 lr:8.132273398270873e-06 tokens_per_second_per_gpu:2101.8342041774677 
Step 7033 | loss:2.028714418411255 lr:8.116737458860945e-06 tokens_per_second_per_gpu:2189.966784751426 
Step 7034 | loss:2.078594446182251 lr:8.101215745853485e-06 tokens_per_second_per_gpu:2092.527520779837 
Step 7035 | loss:2.0790958404541016 lr:8.085708261651748e-06 tokens_per_second_per_gpu:2202.0554771855277 
Step 7036 | loss:2.028320789337158 lr:8.070215008656757e-06 tokens_per_second_per_gpu:2030.7540557154687 
Step 7037 | loss:2.086176633834839 lr:8.054735989267336e-06 tokens_per_second_per_gpu:2111.4739927260453 
Step 7038 | loss:2.091437339782715 lr:8.039271205880184e-06 tokens_per_second_per_gpu:2123.812025584726 
Step 7039 | loss:2.085144519805908 lr:8.02382066088968e-06 tokens_per_second_per_gpu:2141.913437406692 
Step 7040 | loss:2.0180392265319824 lr:8.008384356688058e-06 tokens_per_second_per_gpu:2193.1077677459093 
Step 7041 | loss:2.025015354156494 lr:7.992962295665374e-06 tokens_per_second_per_gpu:2146.240502546944 
Step 7042 | loss:2.0817179679870605 lr:7.977554480209382e-06 tokens_per_second_per_gpu:2158.3578520865885 
Step 7043 | loss:2.0865836143493652 lr:7.962160912705752e-06 tokens_per_second_per_gpu:2101.840456596796 
Step 7044 | loss:2.0887198448181152 lr:7.946781595537889e-06 tokens_per_second_per_gpu:2157.859282038087 
Step 7045 | loss:2.1013705730438232 lr:7.931416531086955e-06 tokens_per_second_per_gpu:2193.222839469623 
Step 7046 | loss:2.042480945587158 lr:7.916065721731958e-06 tokens_per_second_per_gpu:2156.9788640053125 
Step 7047 | loss:2.0624661445617676 lr:7.900729169849708e-06 tokens_per_second_per_gpu:2013.9291793398463 
Step 7048 | loss:2.0617737770080566 lr:7.885406877814716e-06 tokens_per_second_per_gpu:2010.6271728335628 
Step 7049 | loss:2.050994396209717 lr:7.87009884799943e-06 tokens_per_second_per_gpu:2191.837612466543 
Step 7050 | loss:2.01578426361084 lr:7.854805082773986e-06 tokens_per_second_per_gpu:2167.1213211276213 
Step 7051 | loss:1.9901809692382812 lr:7.839525584506314e-06 tokens_per_second_per_gpu:2172.7789372593647 
Step 7052 | loss:2.0977087020874023 lr:7.824260355562174e-06 tokens_per_second_per_gpu:2170.707654747367 
Step 7053 | loss:2.0406365394592285 lr:7.809009398305101e-06 tokens_per_second_per_gpu:2160.960980861066 
Step 7054 | loss:2.0669422149658203 lr:7.793772715096415e-06 tokens_per_second_per_gpu:2172.2621379978473 
Step 7055 | loss:2.04441499710083 lr:7.778550308295241e-06 tokens_per_second_per_gpu:2171.7919181518264 
Step 7056 | loss:2.1003808975219727 lr:7.763342180258493e-06 tokens_per_second_per_gpu:2195.3877744294236 
Step 7057 | loss:2.098196029663086 lr:7.748148333340832e-06 tokens_per_second_per_gpu:2184.0849069763553 
Step 7058 | loss:2.0183539390563965 lr:7.732968769894744e-06 tokens_per_second_per_gpu:2133.711251558144 
Step 7059 | loss:2.0394089221954346 lr:7.717803492270547e-06 tokens_per_second_per_gpu:2157.3299376913355 
Step 7060 | loss:1.99998140335083 lr:7.702652502816254e-06 tokens_per_second_per_gpu:2175.1251321801524 
Step 7061 | loss:2.1014833450317383 lr:7.687515803877731e-06 tokens_per_second_per_gpu:2142.71498833516 
Step 7062 | loss:2.106816291809082 lr:7.672393397798616e-06 tokens_per_second_per_gpu:2121.6963043905384 
Step 7063 | loss:2.140049695968628 lr:7.657285286920313e-06 tokens_per_second_per_gpu:2175.9275404319064 
Step 7064 | loss:2.065964698791504 lr:7.642191473582016e-06 tokens_per_second_per_gpu:2115.7383108862036 
Step 7065 | loss:2.074922561645508 lr:7.6271119601207805e-06 tokens_per_second_per_gpu:2188.4382578482314 
Step 7066 | loss:2.0842080116271973 lr:7.612046748871327e-06 tokens_per_second_per_gpu:2143.6887209255897 
Step 7067 | loss:2.059451103210449 lr:7.596995842166243e-06 tokens_per_second_per_gpu:2165.34636120236 
Step 7068 | loss:2.0568017959594727 lr:7.581959242335901e-06 tokens_per_second_per_gpu:2195.38242265575 
Step 7069 | loss:2.0764894485473633 lr:7.566936951708381e-06 tokens_per_second_per_gpu:2174.03149941325 
Step 7070 | loss:2.08951735496521 lr:7.551928972609656e-06 tokens_per_second_per_gpu:2180.301039641836 
Step 7071 | loss:2.059300422668457 lr:7.536935307363424e-06 tokens_per_second_per_gpu:2172.5891016132646 
Step 7072 | loss:2.113539218902588 lr:7.521955958291149e-06 tokens_per_second_per_gpu:2164.8006456079925 
Step 7073 | loss:2.1273741722106934 lr:7.50699092771211e-06 tokens_per_second_per_gpu:2173.068574430169 
Step 7074 | loss:2.0956239700317383 lr:7.492040217943386e-06 tokens_per_second_per_gpu:2192.2259439354443 
Step 7075 | loss:2.0966649055480957 lr:7.477103831299759e-06 tokens_per_second_per_gpu:2114.079723865352 
Step 7076 | loss:1.980970859527588 lr:7.462181770093912e-06 tokens_per_second_per_gpu:2189.398530562161 
Step 7077 | loss:2.0693516731262207 lr:7.447274036636231e-06 tokens_per_second_per_gpu:2157.791974847562 
Step 7078 | loss:2.0468368530273438 lr:7.43238063323487e-06 tokens_per_second_per_gpu:2150.128003820444 
Step 7079 | loss:2.0510027408599854 lr:7.417501562195805e-06 tokens_per_second_per_gpu:2055.373453382462 
Step 7080 | loss:2.0686144828796387 lr:7.402636825822795e-06 tokens_per_second_per_gpu:2152.1315927631576 
Step 7081 | loss:2.102605104446411 lr:7.387786426417365e-06 tokens_per_second_per_gpu:2153.508815093429 
Step 7082 | loss:2.0079092979431152 lr:7.372950366278808e-06 tokens_per_second_per_gpu:2107.6302997268353 
Step 7083 | loss:2.0446059703826904 lr:7.358128647704243e-06 tokens_per_second_per_gpu:2132.3259613365676 
Step 7084 | loss:2.068465232849121 lr:7.3433212729884796e-06 tokens_per_second_per_gpu:2185.204048412114 
Step 7085 | loss:2.078862190246582 lr:7.328528244424182e-06 tokens_per_second_per_gpu:2190.942222943175 
Step 7086 | loss:2.107306957244873 lr:7.31374956430182e-06 tokens_per_second_per_gpu:2118.377085996812 
Step 7087 | loss:2.1049623489379883 lr:7.29898523490955e-06 tokens_per_second_per_gpu:2139.331309303721 
Step 7088 | loss:2.0669050216674805 lr:7.284235258533357e-06 tokens_per_second_per_gpu:2138.716116276355 
Step 7089 | loss:2.0907554626464844 lr:7.269499637457011e-06 tokens_per_second_per_gpu:2161.9851521247897 
Step 7090 | loss:2.0284152030944824 lr:7.254778373962034e-06 tokens_per_second_per_gpu:2190.6516806826985 
Step 7091 | loss:2.1387927532196045 lr:7.240071470327725e-06 tokens_per_second_per_gpu:2159.6201211035127 
Step 7092 | loss:2.0941271781921387 lr:7.225378928831216e-06 tokens_per_second_per_gpu:2146.8288420660974 
Step 7093 | loss:2.0837655067443848 lr:7.210700751747346e-06 tokens_per_second_per_gpu:2098.812803652295 
Step 7094 | loss:2.0656986236572266 lr:7.196036941348749e-06 tokens_per_second_per_gpu:2181.994496507592 
Step 7095 | loss:1.9648077487945557 lr:7.181387499905867e-06 tokens_per_second_per_gpu:2151.917207956077 
Step 7096 | loss:2.0204503536224365 lr:7.16675242968684e-06 tokens_per_second_per_gpu:2130.1605435755077 
Step 7097 | loss:2.0787391662597656 lr:7.152131732957678e-06 tokens_per_second_per_gpu:2137.6127228761197 
Step 7098 | loss:2.0935583114624023 lr:7.137525411982138e-06 tokens_per_second_per_gpu:2172.4388919514704 
Step 7099 | loss:2.065061092376709 lr:7.122933469021687e-06 tokens_per_second_per_gpu:2195.2231761500807 
Step 7100 | loss:2.108067274093628 lr:7.10835590633564e-06 tokens_per_second_per_gpu:2184.4440274050894 
Step 7101 | loss:2.022550582885742 lr:7.093792726181059e-06 tokens_per_second_per_gpu:2190.609690854903 
Step 7102 | loss:2.02231764793396 lr:7.079243930812774e-06 tokens_per_second_per_gpu:2144.780406520148 
Step 7103 | loss:2.066617012023926 lr:7.064709522483403e-06 tokens_per_second_per_gpu:2181.548007531946 
Step 7104 | loss:2.050154685974121 lr:7.050189503443327e-06 tokens_per_second_per_gpu:2192.1786516403995 
Step 7105 | loss:2.0494136810302734 lr:7.0356838759406905e-06 tokens_per_second_per_gpu:2129.6043850847755 
Step 7106 | loss:2.0547897815704346 lr:7.021192642221408e-06 tokens_per_second_per_gpu:2120.6652883100114 
Step 7107 | loss:2.10214900970459 lr:7.006715804529196e-06 tokens_per_second_per_gpu:2126.4237112259457 
Step 7108 | loss:2.0677170753479004 lr:6.992253365105506e-06 tokens_per_second_per_gpu:2166.479699727006 
Step 7109 | loss:2.061347007751465 lr:6.97780532618959e-06 tokens_per_second_per_gpu:2162.108043391603 
Step 7110 | loss:2.115206480026245 lr:6.963371690018461e-06 tokens_per_second_per_gpu:2174.226691128575 
Step 7111 | loss:2.0264596939086914 lr:6.9489524588268736e-06 tokens_per_second_per_gpu:2128.405952931013 
Step 7112 | loss:2.1177616119384766 lr:6.934547634847377e-06 tokens_per_second_per_gpu:2167.280919551533 
Step 7113 | loss:2.066586971282959 lr:6.9201572203103195e-06 tokens_per_second_per_gpu:2172.4553736031453 
Step 7114 | loss:2.0983524322509766 lr:6.905781217443763e-06 tokens_per_second_per_gpu:2191.831200814661 
Step 7115 | loss:2.0748467445373535 lr:6.891419628473561e-06 tokens_per_second_per_gpu:2103.6179268470214 
Step 7116 | loss:2.1268723011016846 lr:6.877072455623368e-06 tokens_per_second_per_gpu:2177.9781091936647 
Step 7117 | loss:2.0810885429382324 lr:6.8627397011145064e-06 tokens_per_second_per_gpu:2183.5619499092118 
Step 7118 | loss:2.0752296447753906 lr:6.848421367166202e-06 tokens_per_second_per_gpu:2148.219015690798 
Step 7119 | loss:2.026322841644287 lr:6.834117455995359e-06 tokens_per_second_per_gpu:2149.9292193520523 
Step 7120 | loss:2.134949207305908 lr:6.819827969816661e-06 tokens_per_second_per_gpu:2128.7155671049522 
Step 7121 | loss:2.0830862522125244 lr:6.805552910842583e-06 tokens_per_second_per_gpu:2184.040764150153 
Step 7122 | loss:2.071061372756958 lr:6.791292281283346e-06 tokens_per_second_per_gpu:2167.0670169899486 
Step 7123 | loss:2.020712375640869 lr:6.777046083346905e-06 tokens_per_second_per_gpu:2179.5149292463443 
Step 7124 | loss:2.122432231903076 lr:6.762814319239075e-06 tokens_per_second_per_gpu:2117.5550435683535 
Step 7125 | loss:2.104656219482422 lr:6.748596991163359e-06 tokens_per_second_per_gpu:2107.26139285553 
Step 7126 | loss:2.0776147842407227 lr:6.734394101321018e-06 tokens_per_second_per_gpu:2184.268028605568 
Step 7127 | loss:2.0801029205322266 lr:6.720205651911127e-06 tokens_per_second_per_gpu:2160.5699091061965 
Step 7128 | loss:1.9676704406738281 lr:6.706031645130506e-06 tokens_per_second_per_gpu:2162.7852966270566 
Step 7129 | loss:2.094219207763672 lr:6.691872083173711e-06 tokens_per_second_per_gpu:2174.5452677455273 
Step 7130 | loss:2.0175936222076416 lr:6.677726968233111e-06 tokens_per_second_per_gpu:2190.5074128882975 
Step 7131 | loss:2.050323009490967 lr:6.66359630249882e-06 tokens_per_second_per_gpu:2196.4400384602654 
Step 7132 | loss:2.0934317111968994 lr:6.6494800881586664e-06 tokens_per_second_per_gpu:2194.816434974488 
Step 7133 | loss:2.1225664615631104 lr:6.6353783273983e-06 tokens_per_second_per_gpu:2133.914764556988 
Step 7134 | loss:2.1154110431671143 lr:6.621291022401121e-06 tokens_per_second_per_gpu:2173.916199487832 
Step 7135 | loss:2.135688304901123 lr:6.607218175348273e-06 tokens_per_second_per_gpu:2184.8557895323684 
Step 7136 | loss:2.10758113861084 lr:6.59315978841869e-06 tokens_per_second_per_gpu:2138.230415298109 
Step 7137 | loss:2.13443922996521 lr:6.579115863789053e-06 tokens_per_second_per_gpu:2151.4675721969047 
Step 7138 | loss:2.0743298530578613 lr:6.56508640363378e-06 tokens_per_second_per_gpu:2153.4720551457553 
Step 7139 | loss:2.1044039726257324 lr:6.5510714101250535e-06 tokens_per_second_per_gpu:2176.1117174963697 
Step 7140 | loss:2.1113858222961426 lr:6.537070885432906e-06 tokens_per_second_per_gpu:2166.577216864433 
Step 7141 | loss:2.048675298690796 lr:6.52308483172498e-06 tokens_per_second_per_gpu:2190.600492242312 
Step 7142 | loss:2.0494208335876465 lr:6.5091132511667875e-06 tokens_per_second_per_gpu:2136.252947572076 
Step 7143 | loss:2.067347526550293 lr:6.495156145921566e-06 tokens_per_second_per_gpu:2068.311993727801 
Step 7144 | loss:2.060359239578247 lr:6.4812135181502865e-06 tokens_per_second_per_gpu:2171.4890629459096 
Step 7145 | loss:2.0781211853027344 lr:6.467285370011744e-06 tokens_per_second_per_gpu:2077.6695838762307 
Step 7146 | loss:2.01863431930542 lr:6.453371703662436e-06 tokens_per_second_per_gpu:2155.570575313363 
Step 7147 | loss:2.0364203453063965 lr:6.439472521256618e-06 tokens_per_second_per_gpu:2080.5637835163043 
Step 7148 | loss:2.091336250305176 lr:6.425587824946333e-06 tokens_per_second_per_gpu:2141.337997041542 
Step 7149 | loss:2.0398240089416504 lr:6.4117176168813745e-06 tokens_per_second_per_gpu:2161.265516610429 
Step 7150 | loss:2.1010117530822754 lr:6.397861899209245e-06 tokens_per_second_per_gpu:2097.67139649755 
Step 7151 | loss:2.0274550914764404 lr:6.3840206740752864e-06 tokens_per_second_per_gpu:2149.7775198452055 
Step 7152 | loss:2.0931625366210938 lr:6.370193943622549e-06 tokens_per_second_per_gpu:2166.9528727123898 
Step 7153 | loss:2.0118913650512695 lr:6.356381709991821e-06 tokens_per_second_per_gpu:2095.173423371491 
Step 7154 | loss:2.079662799835205 lr:6.34258397532167e-06 tokens_per_second_per_gpu:2190.169669686242 
Step 7155 | loss:2.084214687347412 lr:6.328800741748431e-06 tokens_per_second_per_gpu:2122.6361263997655 
Step 7156 | loss:2.0423033237457275 lr:6.315032011406163e-06 tokens_per_second_per_gpu:2164.9764457443007 
Step 7157 | loss:2.002248764038086 lr:6.301277786426718e-06 tokens_per_second_per_gpu:2183.988581783145 
Step 7158 | loss:2.1085877418518066 lr:6.2875380689396805e-06 tokens_per_second_per_gpu:2188.5142264479073 
Step 7159 | loss:2.073826313018799 lr:6.2738128610723704e-06 tokens_per_second_per_gpu:2111.092921517572 
Step 7160 | loss:2.0726871490478516 lr:6.2601021649498545e-06 tokens_per_second_per_gpu:2184.499738355787 
Step 7161 | loss:2.0805017948150635 lr:6.246405982695047e-06 tokens_per_second_per_gpu:2145.0391645108384 
Step 7162 | loss:2.0842885971069336 lr:6.2327243164284955e-06 tokens_per_second_per_gpu:2172.5995536770606 
Step 7163 | loss:2.1462297439575195 lr:6.21905716826856e-06 tokens_per_second_per_gpu:2110.416877739072 
Step 7164 | loss:2.068213939666748 lr:6.20540454033135e-06 tokens_per_second_per_gpu:2099.46226311876 
Step 7165 | loss:2.0754032135009766 lr:6.191766434730705e-06 tokens_per_second_per_gpu:2155.9150469471065 
Step 7166 | loss:2.0454816818237305 lr:6.178142853578217e-06 tokens_per_second_per_gpu:2172.871699551873 
Step 7167 | loss:2.0676095485687256 lr:6.164533798983307e-06 tokens_per_second_per_gpu:2172.2302598711526 
Step 7168 | loss:2.054226875305176 lr:6.1509392730530136e-06 tokens_per_second_per_gpu:2185.6473988786593 
Step 7169 | loss:2.0627195835113525 lr:6.137359277892218e-06 tokens_per_second_per_gpu:2160.5352071282814 
Step 7170 | loss:2.058812379837036 lr:6.1237938156035404e-06 tokens_per_second_per_gpu:2186.3535019474784 
Step 7171 | loss:2.071889877319336 lr:6.1102428882873094e-06 tokens_per_second_per_gpu:2179.4279891859574 
Step 7172 | loss:2.0535202026367188 lr:6.09670649804166e-06 tokens_per_second_per_gpu:2144.1706171719766 
Step 7173 | loss:2.0955233573913574 lr:6.083184646962448e-06 tokens_per_second_per_gpu:2160.8149382548195 
Step 7174 | loss:2.0453338623046875 lr:6.0696773371432646e-06 tokens_per_second_per_gpu:2143.8713059654506 
Step 7175 | loss:2.0817759037017822 lr:6.056184570675461e-06 tokens_per_second_per_gpu:2129.9014663788153 
Step 7176 | loss:2.062760829925537 lr:6.042706349648153e-06 tokens_per_second_per_gpu:2171.9428084839765 
Step 7177 | loss:2.1020894050598145 lr:6.029242676148194e-06 tokens_per_second_per_gpu:2180.6338431022778 
Step 7178 | loss:2.0840206146240234 lr:6.015793552260162e-06 tokens_per_second_per_gpu:2167.988358365976 
Step 7179 | loss:2.054295063018799 lr:6.0023589800664245e-06 tokens_per_second_per_gpu:2165.2930499263616 
Step 7180 | loss:2.0838749408721924 lr:5.988938961647062e-06 tokens_per_second_per_gpu:2163.9417320720886 
Step 7181 | loss:2.0464112758636475 lr:5.975533499079899e-06 tokens_per_second_per_gpu:2183.124816160133 
Step 7182 | loss:2.0657873153686523 lr:5.962142594440545e-06 tokens_per_second_per_gpu:2057.2626864928384 
Step 7183 | loss:2.1361875534057617 lr:5.948766249802307e-06 tokens_per_second_per_gpu:2163.1245079800256 
Step 7184 | loss:2.077392101287842 lr:5.9354044672362826e-06 tokens_per_second_per_gpu:2161.891365643095 
Step 7185 | loss:2.1180877685546875 lr:5.922057248811308e-06 tokens_per_second_per_gpu:2136.6868679758536 
Step 7186 | loss:2.0273561477661133 lr:5.908724596593906e-06 tokens_per_second_per_gpu:2178.026738360257 
Step 7187 | loss:2.044173240661621 lr:5.895406512648394e-06 tokens_per_second_per_gpu:2087.24155988511 
Step 7188 | loss:2.068150520324707 lr:5.882102999036876e-06 tokens_per_second_per_gpu:2172.3497521529207 
Step 7189 | loss:2.0423500537872314 lr:5.8688140578191055e-06 tokens_per_second_per_gpu:2166.703751284783 
Step 7190 | loss:2.112074851989746 lr:5.8555396910526365e-06 tokens_per_second_per_gpu:2165.931812474365 
Step 7191 | loss:2.1304869651794434 lr:5.842279900792769e-06 tokens_per_second_per_gpu:2180.2340088603855 
Step 7192 | loss:2.0394492149353027 lr:5.829034689092516e-06 tokens_per_second_per_gpu:2182.5558282378793 
Step 7193 | loss:2.0396828651428223 lr:5.81580405800265e-06 tokens_per_second_per_gpu:2183.8383722620815 
Step 7194 | loss:2.1277871131896973 lr:5.802588009571719e-06 tokens_per_second_per_gpu:2175.1295580455153 
Step 7195 | loss:2.0558204650878906 lr:5.789386545845943e-06 tokens_per_second_per_gpu:2194.30907561852 
Step 7196 | loss:2.0695836544036865 lr:5.776199668869331e-06 tokens_per_second_per_gpu:2162.471969713816 
Step 7197 | loss:2.080430030822754 lr:5.76302738068365e-06 tokens_per_second_per_gpu:2191.560926034771 
Step 7198 | loss:2.084929943084717 lr:5.7498696833283236e-06 tokens_per_second_per_gpu:2078.7121799247825 
Step 7199 | loss:2.0524916648864746 lr:5.736726578840635e-06 tokens_per_second_per_gpu:2149.852067814618 
Step 7200 | loss:2.1036229133605957 lr:5.7235980692555314e-06 tokens_per_second_per_gpu:2114.1748911155137 
Step 7201 | loss:2.0700860023498535 lr:5.710484156605689e-06 tokens_per_second_per_gpu:2164.7092535546926 
Step 7202 | loss:2.040530204772949 lr:5.697384842921583e-06 tokens_per_second_per_gpu:2101.6514657798252 
Step 7203 | loss:2.0441970825195312 lr:5.684300130231379e-06 tokens_per_second_per_gpu:2193.920620570217 
Step 7204 | loss:2.0867714881896973 lr:5.671230020561014e-06 tokens_per_second_per_gpu:2165.568378828321 
Step 7205 | loss:2.0200886726379395 lr:5.658174515934134e-06 tokens_per_second_per_gpu:2158.2920183460287 
Step 7206 | loss:2.0599467754364014 lr:5.645133618372167e-06 tokens_per_second_per_gpu:2154.347037876523 
Step 7207 | loss:2.058408260345459 lr:5.632107329894221e-06 tokens_per_second_per_gpu:2156.4947269613253 
Step 7208 | loss:2.066826343536377 lr:5.619095652517181e-06 tokens_per_second_per_gpu:2174.38264599605 
Step 7209 | loss:2.0543041229248047 lr:5.606098588255659e-06 tokens_per_second_per_gpu:2196.2727458254467 
Step 7210 | loss:2.023775577545166 lr:5.593116139122024e-06 tokens_per_second_per_gpu:2189.91670236459 
Step 7211 | loss:2.1140148639678955 lr:5.580148307126343e-06 tokens_per_second_per_gpu:2168.103906751084 
Step 7212 | loss:2.1275880336761475 lr:5.567195094276478e-06 tokens_per_second_per_gpu:2166.211148741996 
Step 7213 | loss:2.0856804847717285 lr:5.554256502577948e-06 tokens_per_second_per_gpu:2171.8293535261696 
Step 7214 | loss:2.1084468364715576 lr:5.541332534034049e-06 tokens_per_second_per_gpu:2174.971490382061 
Step 7215 | loss:2.1197946071624756 lr:5.52842319064587e-06 tokens_per_second_per_gpu:2197.2507461633018 
Step 7216 | loss:2.0699377059936523 lr:5.515528474412135e-06 tokens_per_second_per_gpu:2194.1345895602685 
Step 7217 | loss:2.099221706390381 lr:5.502648387329357e-06 tokens_per_second_per_gpu:2195.5769370100725 
Step 7218 | loss:2.067995548248291 lr:5.4897829313917955e-06 tokens_per_second_per_gpu:2150.7069991475846 
Step 7219 | loss:2.0525593757629395 lr:5.4769321085913925e-06 tokens_per_second_per_gpu:2183.1385290069734 
Step 7220 | loss:2.0514724254608154 lr:5.4640959209178774e-06 tokens_per_second_per_gpu:2159.502779623543 
Step 7221 | loss:2.053135871887207 lr:5.4512743703587165e-06 tokens_per_second_per_gpu:2153.833924764784 
Step 7222 | loss:2.05703067779541 lr:5.438467458899043e-06 tokens_per_second_per_gpu:2101.635745747534 
Step 7223 | loss:2.005340576171875 lr:5.425675188521784e-06 tokens_per_second_per_gpu:2184.962901042843 
Step 7224 | loss:2.077932834625244 lr:5.412897561207597e-06 tokens_per_second_per_gpu:2165.789249635314 
Step 7225 | loss:2.056352138519287 lr:5.400134578934824e-06 tokens_per_second_per_gpu:2151.033653207694 
Step 7226 | loss:2.0842537879943848 lr:5.387386243679615e-06 tokens_per_second_per_gpu:2124.613587301914 
Step 7227 | loss:2.127532720565796 lr:5.374652557415793e-06 tokens_per_second_per_gpu:2173.4457667340976 
Step 7228 | loss:2.03096342086792 lr:5.361933522114926e-06 tokens_per_second_per_gpu:2122.7094599410275 
Step 7229 | loss:2.0370540618896484 lr:5.349229139746325e-06 tokens_per_second_per_gpu:2195.3620899967477 
Step 7230 | loss:2.01939058303833 lr:5.3365394122770195e-06 tokens_per_second_per_gpu:2161.829105235115 
Step 7231 | loss:2.071828842163086 lr:5.32386434167178e-06 tokens_per_second_per_gpu:2191.6183910358754 
Step 7232 | loss:2.062300205230713 lr:5.311203929893105e-06 tokens_per_second_per_gpu:2070.578023680812 
Step 7233 | loss:2.1122918128967285 lr:5.298558178901236e-06 tokens_per_second_per_gpu:2156.004980233069 
Step 7234 | loss:2.0555708408355713 lr:5.285927090654097e-06 tokens_per_second_per_gpu:2126.247072574476 
Step 7235 | loss:2.0448250770568848 lr:5.2733106671074e-06 tokens_per_second_per_gpu:2193.072569468445 
Step 7236 | loss:2.0391712188720703 lr:5.2607089102145516e-06 tokens_per_second_per_gpu:2123.119051900271 
Step 7237 | loss:2.0534751415252686 lr:5.248121821926699e-06 tokens_per_second_per_gpu:2175.670120041013 
Step 7238 | loss:2.04740571975708 lr:5.23554940419273e-06 tokens_per_second_per_gpu:2106.2459462567704 
Step 7239 | loss:2.0312600135803223 lr:5.222991658959253e-06 tokens_per_second_per_gpu:2210.6806862850935 
Step 7240 | loss:2.0679893493652344 lr:5.2104485881705575e-06 tokens_per_second_per_gpu:2197.4744929685135 
Step 7241 | loss:2.0625734329223633 lr:5.197920193768724e-06 tokens_per_second_per_gpu:2197.6315119914966 
Step 7242 | loss:2.053560733795166 lr:5.185406477693578e-06 tokens_per_second_per_gpu:2179.5389309983498 
Step 7243 | loss:2.0337018966674805 lr:5.172907441882591e-06 tokens_per_second_per_gpu:2182.5830361644557 
Step 7244 | loss:2.1144115924835205 lr:5.1604230882710155e-06 tokens_per_second_per_gpu:2160.73266248351 
Step 7245 | loss:2.0326967239379883 lr:5.147953418791829e-06 tokens_per_second_per_gpu:2168.233507056683 
Step 7246 | loss:2.103545665740967 lr:5.135498435375685e-06 tokens_per_second_per_gpu:2176.4385045791983 
Step 7247 | loss:2.0203964710235596 lr:5.123058139951065e-06 tokens_per_second_per_gpu:2120.991070521586 
Step 7248 | loss:2.043369770050049 lr:5.110632534444093e-06 tokens_per_second_per_gpu:2190.4753045749817 
Step 7249 | loss:2.1190524101257324 lr:5.0982216207786205e-06 tokens_per_second_per_gpu:2158.147368605057 
Step 7250 | loss:2.0677826404571533 lr:5.085825400876265e-06 tokens_per_second_per_gpu:2135.3658179039417 
Step 7251 | loss:2.0947582721710205 lr:5.073443876656359e-06 tokens_per_second_per_gpu:2160.6948621548904 
Step 7252 | loss:2.0108652114868164 lr:5.061077050035912e-06 tokens_per_second_per_gpu:2175.3043830751676 
Step 7253 | loss:2.098740339279175 lr:5.048724922929726e-06 tokens_per_second_per_gpu:2196.6134429458184 
Step 7254 | loss:2.0662171840667725 lr:5.0363874972503055e-06 tokens_per_second_per_gpu:2165.8842518865026 
Step 7255 | loss:2.104774236679077 lr:5.024064774907844e-06 tokens_per_second_per_gpu:2197.3525826662353 
Step 7256 | loss:2.084092140197754 lr:5.0117567578102935e-06 tokens_per_second_per_gpu:2118.4325093606008 
Step 7257 | loss:2.069958209991455 lr:4.999463447863317e-06 tokens_per_second_per_gpu:2196.4347231728766 
Step 7258 | loss:2.075854539871216 lr:4.987184846970317e-06 tokens_per_second_per_gpu:2175.327077785887 
Step 7259 | loss:2.1145715713500977 lr:4.9749209570323805e-06 tokens_per_second_per_gpu:2192.2921335527994 
Step 7260 | loss:2.0701394081115723 lr:4.96267177994838e-06 tokens_per_second_per_gpu:2184.3433994220454 
Step 7261 | loss:2.044865369796753 lr:4.950437317614831e-06 tokens_per_second_per_gpu:2186.7820924697958 
Step 7262 | loss:2.047337532043457 lr:4.938217571926007e-06 tokens_per_second_per_gpu:2172.7368819369035 
Step 7263 | loss:2.0559961795806885 lr:4.926012544773962e-06 tokens_per_second_per_gpu:2186.128184839344 
Step 7264 | loss:2.081340789794922 lr:4.91382223804836e-06 tokens_per_second_per_gpu:2178.685081753245 
Step 7265 | loss:2.037161350250244 lr:4.90164665363666e-06 tokens_per_second_per_gpu:2151.07081955909 
Step 7266 | loss:2.0885214805603027 lr:4.8894857934240425e-06 tokens_per_second_per_gpu:2190.6940310687164 
Step 7267 | loss:2.097597599029541 lr:4.877339659293367e-06 tokens_per_second_per_gpu:2175.026125357072 
Step 7268 | loss:2.0640718936920166 lr:4.865208253125208e-06 tokens_per_second_per_gpu:2179.0741038472916 
Step 7269 | loss:2.0856986045837402 lr:4.853091576797964e-06 tokens_per_second_per_gpu:2161.584419852741 
Step 7270 | loss:2.0173726081848145 lr:4.840989632187609e-06 tokens_per_second_per_gpu:2159.2606782944335 
Step 7271 | loss:2.08103084564209 lr:4.828902421167913e-06 tokens_per_second_per_gpu:2187.475525100806 
Step 7272 | loss:2.043475866317749 lr:4.8168299456103905e-06 tokens_per_second_per_gpu:2192.8053965787994 
Step 7273 | loss:2.0431296825408936 lr:4.804772207384178e-06 tokens_per_second_per_gpu:2160.321412822034 
Step 7274 | loss:2.091073751449585 lr:4.79272920835625e-06 tokens_per_second_per_gpu:2142.588618092959 
Step 7275 | loss:2.1206860542297363 lr:4.780700950391215e-06 tokens_per_second_per_gpu:2178.250516351199 
Step 7276 | loss:2.1229569911956787 lr:4.768687435351415e-06 tokens_per_second_per_gpu:2195.9815301013527 
Step 7277 | loss:2.0855870246887207 lr:4.75668866509692e-06 tokens_per_second_per_gpu:2113.664237983022 
Step 7278 | loss:2.0564184188842773 lr:4.74470464148552e-06 tokens_per_second_per_gpu:2185.0643069677394 
Step 7279 | loss:2.074831485748291 lr:4.73273536637272e-06 tokens_per_second_per_gpu:2108.0391225536887 
Step 7280 | loss:2.084865093231201 lr:4.720780841611738e-06 tokens_per_second_per_gpu:2184.410348768994 
Step 7281 | loss:2.059478759765625 lr:4.708841069053516e-06 tokens_per_second_per_gpu:2136.314769982019 
Step 7282 | loss:2.0449962615966797 lr:4.696916050546685e-06 tokens_per_second_per_gpu:2170.871738328054 
Step 7283 | loss:2.0667009353637695 lr:4.685005787937613e-06 tokens_per_second_per_gpu:2163.7399090948766 
Step 7284 | loss:2.027442455291748 lr:4.673110283070381e-06 tokens_per_second_per_gpu:2112.4469413607053 
Step 7285 | loss:2.0435593128204346 lr:4.661229537786804e-06 tokens_per_second_per_gpu:2174.399076121239 
Step 7286 | loss:1.9951364994049072 lr:4.649363553926367e-06 tokens_per_second_per_gpu:2158.6808987159898 
Step 7287 | loss:2.073727607727051 lr:4.637512333326333e-06 tokens_per_second_per_gpu:2190.769312565765 
Step 7288 | loss:2.0917141437530518 lr:4.6256758778216e-06 tokens_per_second_per_gpu:2169.6298697892753 
Step 7289 | loss:2.1075925827026367 lr:4.613854189244837e-06 tokens_per_second_per_gpu:2177.785832693446 
Step 7290 | loss:2.072462320327759 lr:4.602047269426413e-06 tokens_per_second_per_gpu:2169.071470566519 
Step 7291 | loss:2.0162060260772705 lr:4.590255120194409e-06 tokens_per_second_per_gpu:2174.3632796801016 
Step 7292 | loss:2.1308960914611816 lr:4.57847774337462e-06 tokens_per_second_per_gpu:2145.963198493933 
Step 7293 | loss:2.1114301681518555 lr:4.566715140790567e-06 tokens_per_second_per_gpu:2150.1190180060275 
Step 7294 | loss:2.085723876953125 lr:4.554967314263436e-06 tokens_per_second_per_gpu:2186.715220056987 
Step 7295 | loss:2.0691347122192383 lr:4.543234265612151e-06 tokens_per_second_per_gpu:2118.6071693432896 
Step 7296 | loss:2.0763754844665527 lr:4.531515996653413e-06 tokens_per_second_per_gpu:2176.1480733875105 
Step 7297 | loss:1.9825302362442017 lr:4.519812509201527e-06 tokens_per_second_per_gpu:2198.7755814684992 
Step 7298 | loss:2.1076676845550537 lr:4.508123805068565e-06 tokens_per_second_per_gpu:2173.9129544453162 
Step 7299 | loss:2.0442605018615723 lr:4.496449886064335e-06 tokens_per_second_per_gpu:2161.170578194387 
Step 7300 | loss:2.0958900451660156 lr:4.4847907539962705e-06 tokens_per_second_per_gpu:2151.3744387961865 
Step 7301 | loss:2.092195510864258 lr:4.473146410669615e-06 tokens_per_second_per_gpu:2163.5259113118386 
Step 7302 | loss:2.0674426555633545 lr:4.461516857887271e-06 tokens_per_second_per_gpu:2175.6593023120336 
Step 7303 | loss:2.0418732166290283 lr:4.449902097449843e-06 tokens_per_second_per_gpu:2188.1281430718677 
Step 7304 | loss:2.1227407455444336 lr:4.438302131155658e-06 tokens_per_second_per_gpu:2114.5566799611347 
Step 7305 | loss:2.033600330352783 lr:4.42671696080077e-06 tokens_per_second_per_gpu:2177.521393404518 
Step 7306 | loss:2.041292428970337 lr:4.415146588178909e-06 tokens_per_second_per_gpu:2200.586046373292 
Step 7307 | loss:2.0803961753845215 lr:4.403591015081532e-06 tokens_per_second_per_gpu:2186.244350108728 
Step 7308 | loss:2.0317649841308594 lr:4.392050243297829e-06 tokens_per_second_per_gpu:2175.1467402938883 
Step 7309 | loss:2.036418914794922 lr:4.380524274614639e-06 tokens_per_second_per_gpu:2177.9024779143742 
Step 7310 | loss:2.075470447540283 lr:4.369013110816555e-06 tokens_per_second_per_gpu:2133.366722563905 
Step 7311 | loss:2.0335240364074707 lr:4.357516753685864e-06 tokens_per_second_per_gpu:2155.1474630320313 
Step 7312 | loss:2.0403566360473633 lr:4.346035205002563e-06 tokens_per_second_per_gpu:2169.543055191376 
Step 7313 | loss:2.1284682750701904 lr:4.334568466544364e-06 tokens_per_second_per_gpu:2112.6251971938864 
Step 7314 | loss:2.0825469493865967 lr:4.323116540086669e-06 tokens_per_second_per_gpu:2116.9372494363483 
Step 7315 | loss:2.095381736755371 lr:4.311679427402582e-06 tokens_per_second_per_gpu:2187.975202353882 
Step 7316 | loss:2.078518867492676 lr:4.300257130262941e-06 tokens_per_second_per_gpu:2169.530905521149 
Step 7317 | loss:2.0654451847076416 lr:4.288849650436267e-06 tokens_per_second_per_gpu:2190.249859812869 
Step 7318 | loss:2.0425519943237305 lr:4.277456989688799e-06 tokens_per_second_per_gpu:2195.9682295338393 
Step 7319 | loss:2.079066276550293 lr:4.266079149784475e-06 tokens_per_second_per_gpu:2160.0946319050295 
Step 7320 | loss:2.0695667266845703 lr:4.254716132484959e-06 tokens_per_second_per_gpu:2191.8537032762015 
Step 7321 | loss:2.066087245941162 lr:4.243367939549558e-06 tokens_per_second_per_gpu:2180.3949932247106 
Step 7322 | loss:2.1008734703063965 lr:4.232034572735355e-06 tokens_per_second_per_gpu:2163.9448313723456 
Step 7323 | loss:2.0245866775512695 lr:4.220716033797134e-06 tokens_per_second_per_gpu:2094.509484208736 
Step 7324 | loss:2.10239839553833 lr:4.209412324487316e-06 tokens_per_second_per_gpu:2162.820248835789 
Step 7325 | loss:2.0860509872436523 lr:4.198123446556079e-06 tokens_per_second_per_gpu:2178.9171621078203 
Step 7326 | loss:2.0936899185180664 lr:4.186849401751325e-06 tokens_per_second_per_gpu:2144.4859351923133 
Step 7327 | loss:2.0199151039123535 lr:4.175590191818568e-06 tokens_per_second_per_gpu:2192.1163372671444 
Step 7328 | loss:2.060727596282959 lr:4.164345818501136e-06 tokens_per_second_per_gpu:2180.3265043168253 
Step 7329 | loss:2.061108350753784 lr:4.153116283540015e-06 tokens_per_second_per_gpu:2163.935348264682 
Step 7330 | loss:2.072803020477295 lr:4.141901588673857e-06 tokens_per_second_per_gpu:2195.6147448595084 
Step 7331 | loss:2.1094703674316406 lr:4.1307017356390535e-06 tokens_per_second_per_gpu:2138.7468533029423 
Step 7332 | loss:2.0720813274383545 lr:4.119516726169703e-06 tokens_per_second_per_gpu:2141.0056972432726 
Step 7333 | loss:2.0511794090270996 lr:4.108346561997589e-06 tokens_per_second_per_gpu:2031.7135722368039 
Step 7334 | loss:2.0081162452697754 lr:4.097191244852194e-06 tokens_per_second_per_gpu:2190.733961948323 
Step 7335 | loss:2.0683934688568115 lr:4.086050776460748e-06 tokens_per_second_per_gpu:2156.7627131671215 
Step 7336 | loss:2.0619494915008545 lr:4.074925158548093e-06 tokens_per_second_per_gpu:2187.896231620543 
Step 7337 | loss:2.134979724884033 lr:4.06381439283684e-06 tokens_per_second_per_gpu:2067.783641328857 
Step 7338 | loss:2.064607620239258 lr:4.0527184810472905e-06 tokens_per_second_per_gpu:2189.033218652553 
Step 7339 | loss:2.0488176345825195 lr:4.041637424897438e-06 tokens_per_second_per_gpu:2080.1561536809495 
Step 7340 | loss:2.0955538749694824 lr:4.030571226102975e-06 tokens_per_second_per_gpu:2183.4404991938363 
Step 7341 | loss:2.0775058269500732 lr:4.01951988637731e-06 tokens_per_second_per_gpu:2190.5278889234874 
Step 7342 | loss:2.0289058685302734 lr:4.008483407431496e-06 tokens_per_second_per_gpu:2169.8885949540568 
Step 7343 | loss:2.0379891395568848 lr:3.997461790974355e-06 tokens_per_second_per_gpu:2198.0135527869893 
Step 7344 | loss:2.1122231483459473 lr:3.986455038712378e-06 tokens_per_second_per_gpu:2193.9926985315665 
Step 7345 | loss:2.0372772216796875 lr:3.9754631523497455e-06 tokens_per_second_per_gpu:2181.614232286145 
Step 7346 | loss:2.0198116302490234 lr:3.964486133588341e-06 tokens_per_second_per_gpu:2178.5037657574017 
Step 7347 | loss:2.1056771278381348 lr:3.953523984127783e-06 tokens_per_second_per_gpu:2092.9581014230616 
Step 7348 | loss:2.107013702392578 lr:3.942576705665291e-06 tokens_per_second_per_gpu:2190.5438346302894 
Step 7349 | loss:2.028987407684326 lr:3.931644299895909e-06 tokens_per_second_per_gpu:2160.44682606324 
Step 7350 | loss:2.064713716506958 lr:3.920726768512295e-06 tokens_per_second_per_gpu:2151.857632410743 
Step 7351 | loss:2.068939447402954 lr:3.909824113204807e-06 tokens_per_second_per_gpu:2114.6257891061923 
Step 7352 | loss:2.0485568046569824 lr:3.898936335661541e-06 tokens_per_second_per_gpu:2190.7603368629248 
Step 7353 | loss:2.077512264251709 lr:3.888063437568257e-06 tokens_per_second_per_gpu:2140.4259580664148 
Step 7354 | loss:2.0840678215026855 lr:3.877205420608399e-06 tokens_per_second_per_gpu:2190.1178605498258 
Step 7355 | loss:2.0755090713500977 lr:3.866362286463154e-06 tokens_per_second_per_gpu:2177.1096315490463 
Step 7356 | loss:1.9901249408721924 lr:3.855534036811392e-06 tokens_per_second_per_gpu:2174.9593024660844 
Step 7357 | loss:2.0950024127960205 lr:3.844720673329616e-06 tokens_per_second_per_gpu:2174.919273694989 
Step 7358 | loss:2.052686929702759 lr:3.833922197692108e-06 tokens_per_second_per_gpu:2158.164575567411 
Step 7359 | loss:2.0351433753967285 lr:3.823138611570798e-06 tokens_per_second_per_gpu:2168.666986585083 
Step 7360 | loss:2.107799530029297 lr:3.812369916635328e-06 tokens_per_second_per_gpu:2146.946545307092 
Step 7361 | loss:2.1351816654205322 lr:3.8016161145530303e-06 tokens_per_second_per_gpu:2171.403425331913 
Step 7362 | loss:2.0956974029541016 lr:3.7908772069889407e-06 tokens_per_second_per_gpu:2188.830703693381 
Step 7363 | loss:2.072442054748535 lr:3.78015319560574e-06 tokens_per_second_per_gpu:2159.367388174735 
Step 7364 | loss:2.0982375144958496 lr:3.7694440820638776e-06 tokens_per_second_per_gpu:2123.107995508739 
Step 7365 | loss:2.0733561515808105 lr:3.758749868021427e-06 tokens_per_second_per_gpu:2140.4434099079335 
Step 7366 | loss:2.098541736602783 lr:3.7480705551342198e-06 tokens_per_second_per_gpu:2183.6886677255725 
Step 7367 | loss:2.02498722076416 lr:3.737406145055733e-06 tokens_per_second_per_gpu:2116.578221362136 
Step 7368 | loss:2.107304573059082 lr:3.7267566394371567e-06 tokens_per_second_per_gpu:2181.0669573143314 
Step 7369 | loss:2.09201717376709 lr:3.7161220399273498e-06 tokens_per_second_per_gpu:2188.915362818634 
Step 7370 | loss:2.076387882232666 lr:3.7055023481728955e-06 tokens_per_second_per_gpu:2193.844070443725 
Step 7371 | loss:2.1147379875183105 lr:3.6948975658180563e-06 tokens_per_second_per_gpu:2182.1953778016505 
Step 7372 | loss:2.1218924522399902 lr:3.684307694504774e-06 tokens_per_second_per_gpu:2181.1357870079037 
Step 7373 | loss:2.012929916381836 lr:3.6737327358726925e-06 tokens_per_second_per_gpu:2193.7335412582397 
Step 7374 | loss:2.102308750152588 lr:3.6631726915591693e-06 tokens_per_second_per_gpu:2141.0552276643884 
Step 7375 | loss:2.0750555992126465 lr:3.6526275631991846e-06 tokens_per_second_per_gpu:2193.727944032491 
Step 7376 | loss:2.0851778984069824 lr:3.6420973524254998e-06 tokens_per_second_per_gpu:2172.977336505844 
Step 7377 | loss:2.0183498859405518 lr:3.631582060868499e-06 tokens_per_second_per_gpu:2077.8336712939654 
Step 7378 | loss:2.0904998779296875 lr:3.6210816901562803e-06 tokens_per_second_per_gpu:2155.817991784474 
Step 7379 | loss:2.016463279724121 lr:3.610596241914621e-06 tokens_per_second_per_gpu:2203.528619267523 
Step 7380 | loss:2.05167555809021 lr:3.6001257177670113e-06 tokens_per_second_per_gpu:2168.949444974402 
Step 7381 | loss:2.0794291496276855 lr:3.589670119334609e-06 tokens_per_second_per_gpu:2187.1056822376563 
Step 7382 | loss:2.141242504119873 lr:3.5792294482362655e-06 tokens_per_second_per_gpu:2144.57088027624 
Step 7383 | loss:2.109895706176758 lr:3.5688037060885413e-06 tokens_per_second_per_gpu:2189.6048860852866 
Step 7384 | loss:2.029167652130127 lr:3.5583928945056464e-06 tokens_per_second_per_gpu:2202.5997986936427 
Step 7385 | loss:2.06712007522583 lr:3.5479970150994913e-06 tokens_per_second_per_gpu:2151.6327371205807 
Step 7386 | loss:1.9955477714538574 lr:3.53761606947971e-06 tokens_per_second_per_gpu:2193.1003575261047 
Step 7387 | loss:2.0866641998291016 lr:3.5272500592535727e-06 tokens_per_second_per_gpu:2093.0004504225653 
Step 7388 | loss:2.0676732063293457 lr:3.516898986026085e-06 tokens_per_second_per_gpu:2190.5930909388703 
Step 7389 | loss:2.0750885009765625 lr:3.5065628513999195e-06 tokens_per_second_per_gpu:2185.8481728933994 
Step 7390 | loss:2.071934223175049 lr:3.4962416569753966e-06 tokens_per_second_per_gpu:2146.222364511219 
Step 7391 | loss:2.0752012729644775 lr:3.4859354043505933e-06 tokens_per_second_per_gpu:2170.654251863627 
Step 7392 | loss:2.089939832687378 lr:3.475644095121222e-06 tokens_per_second_per_gpu:2163.493470819272 
Step 7393 | loss:2.0566365718841553 lr:3.465367730880709e-06 tokens_per_second_per_gpu:2194.715151125067 
Step 7394 | loss:2.003695249557495 lr:3.455106313220158e-06 tokens_per_second_per_gpu:2109.672893533327 
Step 7395 | loss:2.090817928314209 lr:3.4448598437283653e-06 tokens_per_second_per_gpu:2182.137991617963 
Step 7396 | loss:2.067699432373047 lr:3.434628323991773e-06 tokens_per_second_per_gpu:2168.6273516987358 
Step 7397 | loss:2.059061050415039 lr:3.42441175559457e-06 tokens_per_second_per_gpu:2159.4879957171065 
Step 7398 | loss:2.006899356842041 lr:3.41421014011859e-06 tokens_per_second_per_gpu:2201.1277532460504 
Step 7399 | loss:2.0200252532958984 lr:3.40402347914337e-06 tokens_per_second_per_gpu:2151.56719320203 
Step 7400 | loss:2.056002616882324 lr:3.393851774246104e-06 tokens_per_second_per_gpu:2172.5431814084727 
Step 7401 | loss:2.072831392288208 lr:3.383695027001721e-06 tokens_per_second_per_gpu:2182.010723406895 
Step 7402 | loss:2.1400346755981445 lr:3.373553238982763e-06 tokens_per_second_per_gpu:2180.9115515415715 
Step 7403 | loss:2.094838857650757 lr:3.3634264117595294e-06 tokens_per_second_per_gpu:2196.197366848981 
Step 7404 | loss:2.102221965789795 lr:3.353314546899966e-06 tokens_per_second_per_gpu:2132.6707879206206 
Step 7405 | loss:2.0260777473449707 lr:3.3432176459696985e-06 tokens_per_second_per_gpu:2123.2699299261963 
Step 7406 | loss:2.0692291259765625 lr:3.3331357105320316e-06 tokens_per_second_per_gpu:2170.559820622842 
Step 7407 | loss:2.05598783493042 lr:3.3230687421479833e-06 tokens_per_second_per_gpu:2169.270551733138 
Step 7408 | loss:2.0467193126678467 lr:3.313016742376218e-06 tokens_per_second_per_gpu:2130.0607745194066 
Step 7409 | loss:2.0503482818603516 lr:3.3029797127731133e-06 tokens_per_second_per_gpu:2167.402550807901 
Step 7410 | loss:2.0362048149108887 lr:3.2929576548927253e-06 tokens_per_second_per_gpu:2160.5080139837514 
Step 7411 | loss:2.116474151611328 lr:3.2829505702867467e-06 tokens_per_second_per_gpu:2190.17161934427 
Step 7412 | loss:2.0642857551574707 lr:3.272958460504616e-06 tokens_per_second_per_gpu:2178.471025457972 
Step 7413 | loss:2.0343472957611084 lr:3.262981327093417e-06 tokens_per_second_per_gpu:2188.799700543821 
Step 7414 | loss:2.0800626277923584 lr:3.2530191715979153e-06 tokens_per_second_per_gpu:2145.761201209656 
Step 7415 | loss:2.0760927200317383 lr:3.243071995560576e-06 tokens_per_second_per_gpu:2164.587352393271 
Step 7416 | loss:2.1039958000183105 lr:3.2331398005215342e-06 tokens_per_second_per_gpu:2164.8840376151898 
Step 7417 | loss:2.104891061782837 lr:3.223222588018582e-06 tokens_per_second_per_gpu:2176.009920291344 
Step 7418 | loss:2.086911201477051 lr:3.2133203595872353e-06 tokens_per_second_per_gpu:2167.5381954384457 
Step 7419 | loss:2.039412498474121 lr:3.2034331167606567e-06 tokens_per_second_per_gpu:2135.325550631258 
Step 7420 | loss:2.042090892791748 lr:3.193560861069711e-06 tokens_per_second_per_gpu:2099.2674810978333 
Step 7421 | loss:2.079312801361084 lr:3.1837035940429304e-06 tokens_per_second_per_gpu:2129.6289511369955 
Step 7422 | loss:2.131054401397705 lr:3.1738613172065278e-06 tokens_per_second_per_gpu:2184.0194525379 
Step 7423 | loss:2.103665351867676 lr:3.1640340320843733e-06 tokens_per_second_per_gpu:2162.7814903051553 
Step 7424 | loss:2.1064605712890625 lr:3.1542217401980824e-06 tokens_per_second_per_gpu:2191.834073211303 
Step 7425 | loss:2.076005458831787 lr:3.1444244430668734e-06 tokens_per_second_per_gpu:2135.7859031989733 
Step 7426 | loss:2.086301326751709 lr:3.1346421422076664e-06 tokens_per_second_per_gpu:2187.9340466526282 
Step 7427 | loss:2.087615966796875 lr:3.124874839135095e-06 tokens_per_second_per_gpu:2159.805769379738 
Step 7428 | loss:2.0656638145446777 lr:3.1151225353614367e-06 tokens_per_second_per_gpu:2157.9282283915313 
Step 7429 | loss:2.0549356937408447 lr:3.1053852323966293e-06 tokens_per_second_per_gpu:2154.054904434344 
Step 7430 | loss:2.006216526031494 lr:3.095662931748333e-06 tokens_per_second_per_gpu:2159.6537024142963 
Step 7431 | loss:2.0656087398529053 lr:3.0859556349218666e-06 tokens_per_second_per_gpu:2145.9757110682312 
Step 7432 | loss:2.048539161682129 lr:3.076263343420216e-06 tokens_per_second_per_gpu:2189.1483717864585 
Step 7433 | loss:2.0636539459228516 lr:3.0665860587440478e-06 tokens_per_second_per_gpu:2126.151184324371 
Step 7434 | loss:2.0232834815979004 lr:3.0569237823917074e-06 tokens_per_second_per_gpu:2185.2609498305997 
Step 7435 | loss:2.1006736755371094 lr:3.047276515859232e-06 tokens_per_second_per_gpu:2166.2533903147605 
Step 7436 | loss:2.0920701026916504 lr:3.0376442606403044e-06 tokens_per_second_per_gpu:2094.1384754272044 
Step 7437 | loss:1.9988826513290405 lr:3.0280270182263094e-06 tokens_per_second_per_gpu:2166.574360236568 
Step 7438 | loss:2.0425124168395996 lr:3.0184247901062888e-06 tokens_per_second_per_gpu:2181.1625831027054 
Step 7439 | loss:2.048769950866699 lr:3.008837577766965e-06 tokens_per_second_per_gpu:2139.319642768175 
Step 7440 | loss:2.088029623031616 lr:2.9992653826927508e-06 tokens_per_second_per_gpu:2180.918640620423 
Step 7441 | loss:2.0664801597595215 lr:2.9897082063657156e-06 tokens_per_second_per_gpu:2170.152312819438 
Step 7442 | loss:2.0947842597961426 lr:2.9801660502656094e-06 tokens_per_second_per_gpu:2092.196494086848 
Step 7443 | loss:2.0571188926696777 lr:2.970638915869861e-06 tokens_per_second_per_gpu:2142.0304426788985 
Step 7444 | loss:2.1221394538879395 lr:2.9611268046535466e-06 tokens_per_second_per_gpu:2169.755891450281 
Step 7445 | loss:2.045323371887207 lr:2.951629718089466e-06 tokens_per_second_per_gpu:2193.8100623163905 
Step 7446 | loss:2.0779666900634766 lr:2.942147657648053e-06 tokens_per_second_per_gpu:2186.6709501048053 
Step 7447 | loss:2.163893222808838 lr:2.932680624797424e-06 tokens_per_second_per_gpu:2199.1479607853353 
Step 7448 | loss:2.058133125305176 lr:2.923228621003382e-06 tokens_per_second_per_gpu:2176.8925643469515 
Step 7449 | loss:2.0641984939575195 lr:2.9137916477293913e-06 tokens_per_second_per_gpu:2193.7715795835375 
Step 7450 | loss:2.059657573699951 lr:2.9043697064365715e-06 tokens_per_second_per_gpu:2156.6254064778755 
Step 7451 | loss:2.058770179748535 lr:2.894962798583756e-06 tokens_per_second_per_gpu:2162.9856254601536 
Step 7452 | loss:2.118358612060547 lr:2.8855709256274234e-06 tokens_per_second_per_gpu:2118.677177275641 
Step 7453 | loss:2.0402512550354004 lr:2.876194089021722e-06 tokens_per_second_per_gpu:2188.7521629671164 
Step 7454 | loss:2.1167471408843994 lr:2.8668322902184907e-06 tokens_per_second_per_gpu:2191.357370559221 
Step 7455 | loss:2.0698933601379395 lr:2.8574855306672256e-06 tokens_per_second_per_gpu:2166.749215772421 
Step 7456 | loss:2.11871337890625 lr:2.8481538118150684e-06 tokens_per_second_per_gpu:2197.8719013872346 
Step 7457 | loss:2.1127820014953613 lr:2.8388371351069086e-06 tokens_per_second_per_gpu:2175.0908502600155 
Step 7458 | loss:2.115933895111084 lr:2.8295355019852366e-06 tokens_per_second_per_gpu:2191.2206446850455 
Step 7459 | loss:2.0535950660705566 lr:2.8202489138902333e-06 tokens_per_second_per_gpu:2166.4550292585755 
Step 7460 | loss:2.042358160018921 lr:2.810977372259749e-06 tokens_per_second_per_gpu:2168.311906352833 
Step 7461 | loss:2.0817008018493652 lr:2.8017208785293235e-06 tokens_per_second_per_gpu:2064.2465503478916 
Step 7462 | loss:2.063803195953369 lr:2.792479434132134e-06 tokens_per_second_per_gpu:2141.425817825636 
Step 7463 | loss:2.184359312057495 lr:2.7832530404990566e-06 tokens_per_second_per_gpu:2195.2919294128214 
Step 7464 | loss:2.068696975708008 lr:2.774041699058638e-06 tokens_per_second_per_gpu:2162.1378888709933 
Step 7465 | loss:2.0995686054229736 lr:2.7648454112370602e-06 tokens_per_second_per_gpu:2078.378887310017 
Step 7466 | loss:2.0970048904418945 lr:2.755664178458195e-06 tokens_per_second_per_gpu:2160.134368240721 
Step 7467 | loss:2.084195852279663 lr:2.7464980021435937e-06 tokens_per_second_per_gpu:2187.8367886281603 
Step 7468 | loss:2.1167807579040527 lr:2.737346883712466e-06 tokens_per_second_per_gpu:2199.1851748774193 
Step 7469 | loss:2.0356945991516113 lr:2.7282108245817006e-06 tokens_per_second_per_gpu:2169.5804897431904 
Step 7470 | loss:2.133150100708008 lr:2.7190898261658326e-06 tokens_per_second_per_gpu:2193.5692065804806 
Step 7471 | loss:2.106630802154541 lr:2.709983889877077e-06 tokens_per_second_per_gpu:2193.198310689264 
Step 7472 | loss:2.054144859313965 lr:2.7008930171253277e-06 tokens_per_second_per_gpu:2193.2943690754437 
Step 7473 | loss:2.0435969829559326 lr:2.691817209318126e-06 tokens_per_second_per_gpu:2164.0179132959693 
Step 7474 | loss:2.058103561401367 lr:2.682756467860692e-06 tokens_per_second_per_gpu:2164.081170456294 
Step 7475 | loss:2.0420010089874268 lr:2.673710794155915e-06 tokens_per_second_per_gpu:2180.1461522109157 
Step 7476 | loss:2.118457794189453 lr:2.6646801896043518e-06 tokens_per_second_per_gpu:2199.5092176788294 
Step 7477 | loss:2.1084141731262207 lr:2.6556646556042064e-06 tokens_per_second_per_gpu:2173.882228677353 
Step 7478 | loss:2.0902652740478516 lr:2.646664193551396e-06 tokens_per_second_per_gpu:2194.312040478841 
Step 7479 | loss:2.0362439155578613 lr:2.6376788048394384e-06 tokens_per_second_per_gpu:2177.8931186236555 
Step 7480 | loss:2.078932285308838 lr:2.628708490859577e-06 tokens_per_second_per_gpu:2138.1217841818884 
Step 7481 | loss:2.0084455013275146 lr:2.6197532530006785e-06 tokens_per_second_per_gpu:2171.9653433758394 
Step 7482 | loss:2.0723700523376465 lr:2.6108130926493114e-06 tokens_per_second_per_gpu:2141.3317267150883 
Step 7483 | loss:2.057772636413574 lr:2.6018880111896903e-06 tokens_per_second_per_gpu:2199.1058411545782 
Step 7484 | loss:2.0610079765319824 lr:2.592978010003688e-06 tokens_per_second_per_gpu:2118.98667248293 
Step 7485 | loss:2.1290764808654785 lr:2.584083090470857e-06 tokens_per_second_per_gpu:2172.5541510895036 
Step 7486 | loss:2.0824508666992188 lr:2.5752032539684058e-06 tokens_per_second_per_gpu:2138.0511695495898 
Step 7487 | loss:2.095975399017334 lr:2.566338501871213e-06 tokens_per_second_per_gpu:2173.6562961743984 
Step 7488 | loss:2.0424318313598633 lr:2.5574888355518135e-06 tokens_per_second_per_gpu:2179.4004171482093 
Step 7489 | loss:2.053121328353882 lr:2.5486542563804117e-06 tokens_per_second_per_gpu:2083.176965992697 
Step 7490 | loss:2.0573155879974365 lr:2.5398347657248912e-06 tokens_per_second_per_gpu:2171.56335051366 
Step 7491 | loss:2.0689024925231934 lr:2.531030364950782e-06 tokens_per_second_per_gpu:2184.098252613464 
Step 7492 | loss:2.1013989448547363 lr:2.5222410554212707e-06 tokens_per_second_per_gpu:2190.0944578526037 
Step 7493 | loss:2.0663671493530273 lr:2.5134668384972138e-06 tokens_per_second_per_gpu:2161.8996053549863 
Step 7494 | loss:2.096038341522217 lr:2.504707715537147e-06 tokens_per_second_per_gpu:2159.663898567238 
Step 7495 | loss:2.0424866676330566 lr:2.4959636878972514e-06 tokens_per_second_per_gpu:2195.5041908258513 
Step 7496 | loss:2.1522140502929688 lr:2.487234756931378e-06 tokens_per_second_per_gpu:2192.3083688506345 
Step 7497 | loss:1.985400676727295 lr:2.4785209239910458e-06 tokens_per_second_per_gpu:2134.7378775334173 
Step 7498 | loss:1.9716284275054932 lr:2.469822190425397e-06 tokens_per_second_per_gpu:2161.820509395218 
Step 7499 | loss:2.045621395111084 lr:2.4611385575813107e-06 tokens_per_second_per_gpu:2199.226297246478 
Step 7500 | loss:2.053420066833496 lr:2.452470026803244e-06 tokens_per_second_per_gpu:2185.8945203463154 
Step 7501 | loss:2.0551156997680664 lr:2.4438165994333907e-06 tokens_per_second_per_gpu:2179.8573405283414 
Step 7502 | loss:2.0656185150146484 lr:2.435178276811556e-06 tokens_per_second_per_gpu:2185.008327839238 
Step 7503 | loss:2.1140758991241455 lr:2.4265550602752262e-06 tokens_per_second_per_gpu:2186.5622598255854 
Step 7504 | loss:2.0921339988708496 lr:2.417946951159522e-06 tokens_per_second_per_gpu:2195.0447889654024 
Step 7505 | loss:2.017218589782715 lr:2.4093539507972996e-06 tokens_per_second_per_gpu:2145.5768389984714 
Step 7506 | loss:2.0858097076416016 lr:2.4007760605189724e-06 tokens_per_second_per_gpu:2193.7340037536096 
Step 7507 | loss:2.045302152633667 lr:2.392213281652689e-06 tokens_per_second_per_gpu:2194.373496093109 
Step 7508 | loss:2.023289203643799 lr:2.3836656155242444e-06 tokens_per_second_per_gpu:2189.135574305637 
Step 7509 | loss:2.088752269744873 lr:2.375133063457058e-06 tokens_per_second_per_gpu:2095.3735991551825 
Step 7510 | loss:2.0718846321105957 lr:2.3666156267722616e-06 tokens_per_second_per_gpu:2089.003366858749 
Step 7511 | loss:2.0109164714813232 lr:2.358113306788601e-06 tokens_per_second_per_gpu:2184.478200794559 
Step 7512 | loss:2.121535301208496 lr:2.349626104822533e-06 tokens_per_second_per_gpu:2136.333859374989 
Step 7513 | loss:2.066715955734253 lr:2.341154022188097e-06 tokens_per_second_per_gpu:2156.265148754199 
Step 7514 | loss:2.0586955547332764 lr:2.3326970601970644e-06 tokens_per_second_per_gpu:2131.7675473252393 
Step 7515 | loss:1.996685266494751 lr:2.324255220158833e-06 tokens_per_second_per_gpu:2186.2587029772685 
Step 7516 | loss:2.133639335632324 lr:2.3158285033804682e-06 tokens_per_second_per_gpu:2139.4009499840663 
Step 7517 | loss:2.0746030807495117 lr:2.307416911166671e-06 tokens_per_second_per_gpu:2186.9220521005773 
Step 7518 | loss:2.07142972946167 lr:2.299020444819844e-06 tokens_per_second_per_gpu:2186.5194887816097 
Step 7519 | loss:2.0462560653686523 lr:2.2906391056400024e-06 tokens_per_second_per_gpu:2192.131793955513 
Step 7520 | loss:2.030832290649414 lr:2.2822728949248527e-06 tokens_per_second_per_gpu:2137.667023658419 
Step 7521 | loss:2.094355344772339 lr:2.2739218139697373e-06 tokens_per_second_per_gpu:2190.651696951761 
Step 7522 | loss:2.059544563293457 lr:2.265585864067665e-06 tokens_per_second_per_gpu:2077.4447541347117 
Step 7523 | loss:2.13289737701416 lr:2.257265046509305e-06 tokens_per_second_per_gpu:2171.51507897909 
Step 7524 | loss:2.0884461402893066 lr:2.2489593625829918e-06 tokens_per_second_per_gpu:2167.5832864599565 
Step 7525 | loss:2.0119025707244873 lr:2.2406688135746757e-06 tokens_per_second_per_gpu:2150.3658244276353 
Step 7526 | loss:2.0736188888549805 lr:2.232393400768018e-06 tokens_per_second_per_gpu:2119.8948702664247 
Step 7527 | loss:2.038205623626709 lr:2.2241331254443054e-06 tokens_per_second_per_gpu:2170.7300524897187 
Step 7528 | loss:2.0898404121398926 lr:2.215887988882481e-06 tokens_per_second_per_gpu:2193.24566041812 
Step 7529 | loss:2.0514450073242188 lr:2.2076579923591578e-06 tokens_per_second_per_gpu:2187.5259412971172 
Step 7530 | loss:2.073312759399414 lr:2.1994431371485935e-06 tokens_per_second_per_gpu:2198.227617717875 
Step 7531 | loss:2.0924806594848633 lr:2.1912434245226933e-06 tokens_per_second_per_gpu:2105.016243419031 
Step 7532 | loss:2.118131160736084 lr:2.183058855751052e-06 tokens_per_second_per_gpu:2156.3853099866587 
Step 7533 | loss:2.115767002105713 lr:2.1748894321008794e-06 tokens_per_second_per_gpu:2193.0180986170503 
Step 7534 | loss:1.9983700513839722 lr:2.1667351548370517e-06 tokens_per_second_per_gpu:2131.0177363127905 
Step 7535 | loss:2.0467209815979004 lr:2.158596025222126e-06 tokens_per_second_per_gpu:2145.145223094586 
Step 7536 | loss:2.026960849761963 lr:2.150472044516294e-06 tokens_per_second_per_gpu:2157.6604147871444 
Step 7537 | loss:2.064405679702759 lr:2.142363213977383e-06 tokens_per_second_per_gpu:2185.4020611705323 
Step 7538 | loss:2.087080955505371 lr:2.1342695348609e-06 tokens_per_second_per_gpu:2169.8108990745227 
Step 7539 | loss:2.018237590789795 lr:2.12619100842002e-06 tokens_per_second_per_gpu:2151.4351991678686 
Step 7540 | loss:2.087247371673584 lr:2.1181276359055202e-06 tokens_per_second_per_gpu:2194.477062427678 
Step 7541 | loss:2.0527844429016113 lr:2.1100794185658803e-06 tokens_per_second_per_gpu:2196.2235291940297 
Step 7542 | loss:2.0703797340393066 lr:2.102046357647214e-06 tokens_per_second_per_gpu:2191.398852344115 
Step 7543 | loss:2.0927255153656006 lr:2.094028454393282e-06 tokens_per_second_per_gpu:2179.2642601686293 
Step 7544 | loss:2.0403048992156982 lr:2.086025710045525e-06 tokens_per_second_per_gpu:2114.1236783273275 
Step 7545 | loss:2.0451321601867676 lr:2.078038125843007e-06 tokens_per_second_per_gpu:2194.604891470137 
Step 7546 | loss:2.0929107666015625 lr:2.0700657030224503e-06 tokens_per_second_per_gpu:2151.727915856211 
Step 7547 | loss:2.1069841384887695 lr:2.0621084428182445e-06 tokens_per_second_per_gpu:2195.28717942026 
Step 7548 | loss:2.035785675048828 lr:2.0541663464624163e-06 tokens_per_second_per_gpu:2196.449027492385 
Step 7549 | loss:2.0773534774780273 lr:2.0462394151846476e-06 tokens_per_second_per_gpu:2152.083287436847 
Step 7550 | loss:2.120990514755249 lr:2.0383276502122793e-06 tokens_per_second_per_gpu:2193.3191881968282 
Step 7551 | loss:2.029906749725342 lr:2.0304310527703206e-06 tokens_per_second_per_gpu:2190.285991192284 
Step 7552 | loss:2.0728955268859863 lr:2.022549624081371e-06 tokens_per_second_per_gpu:2176.12645215501 
Step 7553 | loss:2.0619301795959473 lr:2.014683365365755e-06 tokens_per_second_per_gpu:2117.1983954911625 
Step 7554 | loss:2.1223366260528564 lr:2.0068322778414083e-06 tokens_per_second_per_gpu:2190.923357829195 
Step 7555 | loss:2.0470635890960693 lr:1.998996362723904e-06 tokens_per_second_per_gpu:2120.1618092253057 
Step 7556 | loss:2.0838780403137207 lr:1.9911756212265153e-06 tokens_per_second_per_gpu:2161.699814706183 
Step 7557 | loss:2.110116958618164 lr:1.9833700545601187e-06 tokens_per_second_per_gpu:2157.3673618353514 
Step 7558 | loss:2.040095329284668 lr:1.975579663933269e-06 tokens_per_second_per_gpu:2198.2128049633898 
Step 7559 | loss:2.086193561553955 lr:1.967804450552169e-06 tokens_per_second_per_gpu:2163.75383026538 
Step 7560 | loss:2.0387511253356934 lr:1.9600444156206542e-06 tokens_per_second_per_gpu:2193.673785729718 
Step 7561 | loss:2.050691604614258 lr:1.9522995603402205e-06 tokens_per_second_per_gpu:2193.1995521021686 
Step 7562 | loss:2.118360996246338 lr:1.944569885910008e-06 tokens_per_second_per_gpu:2140.8817939684504 
Step 7563 | loss:2.0594494342803955 lr:1.9368553935268264e-06 tokens_per_second_per_gpu:2068.057061825864 
Step 7564 | loss:2.012660026550293 lr:1.9291560843851086e-06 tokens_per_second_per_gpu:2200.3426454930764 
Step 7565 | loss:2.0371687412261963 lr:1.921471959676957e-06 tokens_per_second_per_gpu:2162.854220439159 
Step 7566 | loss:2.1109418869018555 lr:1.91380302059212e-06 tokens_per_second_per_gpu:2192.5658705743717 
Step 7567 | loss:2.0701446533203125 lr:1.9061492683179694e-06 tokens_per_second_per_gpu:2170.654920111249 
Step 7568 | loss:2.0776665210723877 lr:1.8985107040395467e-06 tokens_per_second_per_gpu:2082.64586914941 
Step 7569 | loss:2.049365997314453 lr:1.8908873289395613e-06 tokens_per_second_per_gpu:2055.6274289020494 
Step 7570 | loss:2.0629868507385254 lr:1.8832791441983355e-06 tokens_per_second_per_gpu:2195.6899432999944 
Step 7571 | loss:2.0131494998931885 lr:1.8756861509938606e-06 tokens_per_second_per_gpu:2175.47855581835 
Step 7572 | loss:2.0305042266845703 lr:1.8681083505017738e-06 tokens_per_second_per_gpu:2148.7705078142517 
Step 7573 | loss:2.1178014278411865 lr:1.8605457438953477e-06 tokens_per_second_per_gpu:2195.7381564393 
Step 7574 | loss:2.1405110359191895 lr:1.8529983323455013e-06 tokens_per_second_per_gpu:2194.068406102481 
Step 7575 | loss:2.089388370513916 lr:1.8454661170208222e-06 tokens_per_second_per_gpu:2106.4072616955245 
Step 7576 | loss:2.071322441101074 lr:1.8379490990875215e-06 tokens_per_second_per_gpu:2160.3642052177506 
Step 7577 | loss:2.015622615814209 lr:1.8304472797094796e-06 tokens_per_second_per_gpu:2176.800774193427 
Step 7578 | loss:2.039670944213867 lr:1.822960660048223e-06 tokens_per_second_per_gpu:2141.133639805359 
Step 7579 | loss:2.0682947635650635 lr:1.815489241262891e-06 tokens_per_second_per_gpu:2193.86043704545 
Step 7580 | loss:2.038029193878174 lr:1.8080330245103139e-06 tokens_per_second_per_gpu:2179.8271662134744 
Step 7581 | loss:2.050116539001465 lr:1.8005920109449237e-06 tokens_per_second_per_gpu:2164.299319518855 
Step 7582 | loss:2.0580544471740723 lr:1.7931662017188433e-06 tokens_per_second_per_gpu:2148.299081707482 
Step 7583 | loss:2.0934267044067383 lr:1.7857555979818085e-06 tokens_per_second_per_gpu:2161.1602191125908 
Step 7584 | loss:2.032047986984253 lr:1.7783602008812239e-06 tokens_per_second_per_gpu:2124.307586013724 
Step 7585 | loss:2.120602607727051 lr:1.7709800115621066e-06 tokens_per_second_per_gpu:2176.2727098225855 
Step 7586 | loss:2.08933687210083 lr:1.7636150311671763e-06 tokens_per_second_per_gpu:2117.8213443159893 
Step 7587 | loss:2.075819730758667 lr:1.7562652608367313e-06 tokens_per_second_per_gpu:2198.3268557192923 
Step 7588 | loss:2.058577299118042 lr:1.7489307017087508e-06 tokens_per_second_per_gpu:2173.1298361060294 
Step 7589 | loss:2.039238452911377 lr:1.7416113549188485e-06 tokens_per_second_per_gpu:2192.2392768355135 
Step 7590 | loss:2.1147396564483643 lr:1.7343072216003176e-06 tokens_per_second_per_gpu:2172.207856364101 
Step 7591 | loss:2.0356690883636475 lr:1.7270183028840314e-06 tokens_per_second_per_gpu:2158.314138982502 
Step 7592 | loss:2.11276912689209 lr:1.719744599898576e-06 tokens_per_second_per_gpu:2157.492630787559 
Step 7593 | loss:2.032017707824707 lr:1.7124861137701175e-06 tokens_per_second_per_gpu:2188.073712780548 
Step 7594 | loss:2.120711326599121 lr:1.7052428456225011e-06 tokens_per_second_per_gpu:2190.6458991055133 
Step 7595 | loss:2.0372118949890137 lr:1.6980147965772296e-06 tokens_per_second_per_gpu:2192.79020097595 
Step 7596 | loss:2.052661895751953 lr:1.6908019677534193e-06 tokens_per_second_per_gpu:2195.0178673761043 
Step 7597 | loss:2.0691866874694824 lr:1.683604360267843e-06 tokens_per_second_per_gpu:2182.65361216632 
Step 7598 | loss:2.106018543243408 lr:1.6764219752349097e-06 tokens_per_second_per_gpu:2182.7159627448978 
Step 7599 | loss:2.0214476585388184 lr:1.6692548137666963e-06 tokens_per_second_per_gpu:2172.2991967081193 
Step 7600 | loss:2.0745620727539062 lr:1.662102876972882e-06 tokens_per_second_per_gpu:2187.630278172976 
Step 7601 | loss:1.9974044561386108 lr:1.654966165960825e-06 tokens_per_second_per_gpu:2175.053233228147 
Step 7602 | loss:2.0489630699157715 lr:1.6478446818354975e-06 tokens_per_second_per_gpu:2177.3240900162796 
Step 7603 | loss:2.072378158569336 lr:1.6407384256995285e-06 tokens_per_second_per_gpu:2150.2241388022762 
Step 7604 | loss:2.1210758686065674 lr:1.6336473986532042e-06 tokens_per_second_per_gpu:2197.6037986545884 
Step 7605 | loss:2.0650057792663574 lr:1.6265716017944354e-06 tokens_per_second_per_gpu:2073.046310293988 
Step 7606 | loss:2.0291707515716553 lr:1.6195110362187572e-06 tokens_per_second_per_gpu:2199.0912748181076 
Step 7607 | loss:2.0367603302001953 lr:1.6124657030193835e-06 tokens_per_second_per_gpu:2166.2132275376393 
Step 7608 | loss:2.0512635707855225 lr:1.605435603287153e-06 tokens_per_second_per_gpu:2174.4666431565356 
Step 7609 | loss:2.100050926208496 lr:1.5984207381105288e-06 tokens_per_second_per_gpu:2143.835769518424 
Step 7610 | loss:2.079319477081299 lr:1.5914211085756415e-06 tokens_per_second_per_gpu:2191.3058003209267 
Step 7611 | loss:2.055579662322998 lr:1.5844367157662577e-06 tokens_per_second_per_gpu:2159.7172567590474 
Step 7612 | loss:2.0521299839019775 lr:1.577467560763779e-06 tokens_per_second_per_gpu:2151.2988424074474 
Step 7613 | loss:2.0425572395324707 lr:1.5705136446472424e-06 tokens_per_second_per_gpu:2132.434723652102 
Step 7614 | loss:2.0428361892700195 lr:1.563574968493331e-06 tokens_per_second_per_gpu:2105.424797051861 
Step 7615 | loss:2.0933873653411865 lr:1.5566515333763743e-06 tokens_per_second_per_gpu:2190.024390553622 
Step 7616 | loss:2.1047492027282715 lr:1.549743340368337e-06 tokens_per_second_per_gpu:2120.3252142974357 
Step 7617 | loss:2.0855178833007812 lr:1.5428503905388082e-06 tokens_per_second_per_gpu:2162.4259559226793 
Step 7618 | loss:2.072340965270996 lr:1.535972684955056e-06 tokens_per_second_per_gpu:2118.145981585598 
Step 7619 | loss:2.0444390773773193 lr:1.529110224681951e-06 tokens_per_second_per_gpu:2156.1178088925476 
Step 7620 | loss:2.130751609802246 lr:1.5222630107820214e-06 tokens_per_second_per_gpu:2020.8789847154462 
Step 7621 | loss:2.0861992835998535 lr:1.5154310443154184e-06 tokens_per_second_per_gpu:2187.1467941674036 
Step 7622 | loss:2.0862364768981934 lr:1.5086143263399522e-06 tokens_per_second_per_gpu:2145.6742345168773 
Step 7623 | loss:2.0658154487609863 lr:1.5018128579110669e-06 tokens_per_second_per_gpu:2173.7690146753384 
Step 7624 | loss:2.088348388671875 lr:1.4950266400818424e-06 tokens_per_second_per_gpu:2156.8392594024463 
Step 7625 | loss:2.074429512023926 lr:1.4882556739029941e-06 tokens_per_second_per_gpu:2144.552027396624 
Step 7626 | loss:2.009946823120117 lr:1.4814999604228829e-06 tokens_per_second_per_gpu:2118.8406198686025 
Step 7627 | loss:2.100135087966919 lr:1.4747595006874948e-06 tokens_per_second_per_gpu:2165.6245192631945 
Step 7628 | loss:2.048534870147705 lr:1.4680342957404836e-06 tokens_per_second_per_gpu:2199.8993944220715 
Step 7629 | loss:2.088805913925171 lr:1.461324346623094e-06 tokens_per_second_per_gpu:2121.903487713775 
Step 7630 | loss:2.0881009101867676 lr:1.4546296543742622e-06 tokens_per_second_per_gpu:2157.586742720166 
Step 7631 | loss:2.115962028503418 lr:1.447950220030514e-06 tokens_per_second_per_gpu:2182.335959693686 
Step 7632 | loss:2.042872428894043 lr:1.4412860446260557e-06 tokens_per_second_per_gpu:2128.0884346304665 
Step 7633 | loss:2.0951976776123047 lr:1.434637129192684e-06 tokens_per_second_per_gpu:2199.0304524276394 
Step 7634 | loss:2.116302013397217 lr:1.4280034747598868e-06 tokens_per_second_per_gpu:2124.3454140676654 
Step 7635 | loss:2.0590925216674805 lr:1.4213850823547426e-06 tokens_per_second_per_gpu:2199.073069179365 
Step 7636 | loss:2.0478854179382324 lr:1.4147819530019978e-06 tokens_per_second_per_gpu:2154.0306634778144 
Step 7637 | loss:2.0710883140563965 lr:1.408194087724013e-06 tokens_per_second_per_gpu:2199.1907667412597 
Step 7638 | loss:2.05989670753479 lr:1.401621487540794e-06 tokens_per_second_per_gpu:2160.628648541924 
Step 7639 | loss:2.055619955062866 lr:1.3950641534699937e-06 tokens_per_second_per_gpu:2161.642284935805 
Step 7640 | loss:2.0892131328582764 lr:1.3885220865269e-06 tokens_per_second_per_gpu:2178.0257922518426 
Step 7641 | loss:2.0960516929626465 lr:1.3819952877244135e-06 tokens_per_second_per_gpu:2114.3405018432063 
Step 7642 | loss:2.0487074851989746 lr:1.3754837580730928e-06 tokens_per_second_per_gpu:2156.233399860892 
Step 7643 | loss:2.0611062049865723 lr:1.3689874985811202e-06 tokens_per_second_per_gpu:2141.7391067711874 
Step 7644 | loss:2.052002429962158 lr:1.3625065102543244e-06 tokens_per_second_per_gpu:2187.1192112277163 
Step 7645 | loss:2.0598549842834473 lr:1.3560407940961696e-06 tokens_per_second_per_gpu:2190.1971744853554 
Step 7646 | loss:2.026275157928467 lr:1.3495903511077545e-06 tokens_per_second_per_gpu:2134.849317274036 
Step 7647 | loss:2.0163803100585938 lr:1.343155182287792e-06 tokens_per_second_per_gpu:2179.8737983329306 
Step 7648 | loss:2.0385994911193848 lr:1.3367352886326622e-06 tokens_per_second_per_gpu:2178.3912161117946 
Step 7649 | loss:2.030646800994873 lr:1.3303306711363594e-06 tokens_per_second_per_gpu:2174.072110085841 
Step 7650 | loss:2.0293006896972656 lr:1.3239413307905125e-06 tokens_per_second_per_gpu:2192.8598056539704 
Step 7651 | loss:2.0187203884124756 lr:1.3175672685844076e-06 tokens_per_second_per_gpu:2192.12386604936 
Step 7652 | loss:2.0331521034240723 lr:1.3112084855049333e-06 tokens_per_second_per_gpu:2147.2499671993755 
Step 7653 | loss:2.0593857765197754 lr:1.3048649825366466e-06 tokens_per_second_per_gpu:2196.285480903773 
Step 7654 | loss:2.1005959510803223 lr:1.298536760661695e-06 tokens_per_second_per_gpu:2184.348787091203 
Step 7655 | loss:2.073261022567749 lr:1.2922238208599168e-06 tokens_per_second_per_gpu:2185.399265924863 
Step 7656 | loss:2.1032791137695312 lr:1.2859261641087195e-06 tokens_per_second_per_gpu:2182.1266908125635 
Step 7657 | loss:2.0083096027374268 lr:1.2796437913832004e-06 tokens_per_second_per_gpu:2179.8905061228693 
Step 7658 | loss:2.0653762817382812 lr:1.2733767036560484e-06 tokens_per_second_per_gpu:2058.390907754592 
Step 7659 | loss:2.039886951446533 lr:1.2671249018976206e-06 tokens_per_second_per_gpu:2113.6316176158753 
Step 7660 | loss:2.065833806991577 lr:1.260888387075887e-06 tokens_per_second_per_gpu:2195.5183345790997 
Step 7661 | loss:2.112806797027588 lr:1.254667160156453e-06 tokens_per_second_per_gpu:2193.3942477217997 
Step 7662 | loss:2.095371723175049 lr:1.2484612221025593e-06 tokens_per_second_per_gpu:2095.9859523052755 
Step 7663 | loss:2.048262357711792 lr:1.2422705738750816e-06 tokens_per_second_per_gpu:2190.9761885997227 
Step 7664 | loss:2.0402655601501465 lr:1.2360952164325311e-06 tokens_per_second_per_gpu:2196.1954955859164 
Step 7665 | loss:2.0627942085266113 lr:1.2299351507310319e-06 tokens_per_second_per_gpu:2159.062861548641 
Step 7666 | loss:2.042508602142334 lr:1.2237903777243542e-06 tokens_per_second_per_gpu:2194.7416051477344 
Step 7667 | loss:2.1127946376800537 lr:1.2176608983639258e-06 tokens_per_second_per_gpu:2196.697733607211 
Step 7668 | loss:2.1252799034118652 lr:1.2115467135987546e-06 tokens_per_second_per_gpu:2183.567365486154 
Step 7669 | loss:2.083350658416748 lr:1.2054478243755274e-06 tokens_per_second_per_gpu:2175.2226252631153 
Step 7670 | loss:2.0887155532836914 lr:1.1993642316385223e-06 tokens_per_second_per_gpu:2195.5018762823565 
Step 7671 | loss:2.055263042449951 lr:1.193295936329686e-06 tokens_per_second_per_gpu:2172.121771217565 
Step 7672 | loss:2.0908844470977783 lr:1.1872429393885775e-06 tokens_per_second_per_gpu:2194.066004383566 
Step 7673 | loss:2.08990740776062 lr:1.1812052417523921e-06 tokens_per_second_per_gpu:2157.6672408745967 
Step 7674 | loss:2.136488199234009 lr:1.1751828443559377e-06 tokens_per_second_per_gpu:2196.095324683416 
Step 7675 | loss:2.0247411727905273 lr:1.16917574813169e-06 tokens_per_second_per_gpu:2198.5050770715884 
Step 7676 | loss:2.1443028450012207 lr:1.1631839540097277e-06 tokens_per_second_per_gpu:2174.927762827829 
Step 7677 | loss:2.084629535675049 lr:1.1572074629177643e-06 tokens_per_second_per_gpu:2185.84865215126 
Step 7678 | loss:2.1043620109558105 lr:1.1512462757811593e-06 tokens_per_second_per_gpu:2178.4420410968173 
Step 7679 | loss:2.1326980590820312 lr:1.1453003935228746e-06 tokens_per_second_per_gpu:2197.460127891204 
Step 7680 | loss:2.08461332321167 lr:1.139369817063529e-06 tokens_per_second_per_gpu:2180.736907044439 
Step 7681 | loss:2.0206515789031982 lr:1.1334545473213554e-06 tokens_per_second_per_gpu:2185.810585356662 
Step 7682 | loss:2.0555076599121094 lr:1.1275545852122427e-06 tokens_per_second_per_gpu:2183.2769577688537 
Step 7683 | loss:2.121015787124634 lr:1.1216699316496494e-06 tokens_per_second_per_gpu:2171.2196432127034 
Step 7684 | loss:1.9740245342254639 lr:1.1158005875447465e-06 tokens_per_second_per_gpu:2171.620471053317 
Step 7685 | loss:2.064990997314453 lr:1.1099465538062627e-06 tokens_per_second_per_gpu:2163.9277324745253 
Step 7686 | loss:2.1027631759643555 lr:1.104107831340595e-06 tokens_per_second_per_gpu:2197.482204766366 
Step 7687 | loss:2.1115047931671143 lr:1.098284421051765e-06 tokens_per_second_per_gpu:2180.0746138889494 
Step 7688 | loss:2.0311169624328613 lr:1.0924763238414183e-06 tokens_per_second_per_gpu:2196.287626336621 
Step 7689 | loss:2.0783066749572754 lr:1.086683540608824e-06 tokens_per_second_per_gpu:2179.5041392458465 
Step 7690 | loss:2.0842156410217285 lr:1.0809060722508756e-06 tokens_per_second_per_gpu:2187.8616199876087 
Step 7691 | loss:2.104825496673584 lr:1.075143919662136e-06 tokens_per_second_per_gpu:2161.8343592394062 
Step 7692 | loss:2.0828018188476562 lr:1.0693970837347356e-06 tokens_per_second_per_gpu:2149.635622964478 
Step 7693 | loss:2.026503562927246 lr:1.0636655653584849e-06 tokens_per_second_per_gpu:2169.9275264091143 
Step 7694 | loss:2.0935487747192383 lr:1.0579493654208073e-06 tokens_per_second_per_gpu:2156.8149512371233 
Step 7695 | loss:2.075740337371826 lr:1.0522484848067171e-06 tokens_per_second_per_gpu:2202.799428878018 
Step 7696 | loss:2.0280609130859375 lr:1.0465629243989195e-06 tokens_per_second_per_gpu:2111.3337071716323 
Step 7697 | loss:2.101423740386963 lr:1.04089268507771e-06 tokens_per_second_per_gpu:2195.0083455801964 
Step 7698 | loss:2.041019916534424 lr:1.035237767721009e-06 tokens_per_second_per_gpu:2195.252658853073 
Step 7699 | loss:2.0060982704162598 lr:1.0295981732043824e-06 tokens_per_second_per_gpu:2190.2193802381325 
Step 7700 | loss:2.0469119548797607 lr:1.0239739024010208e-06 tokens_per_second_per_gpu:2127.2461290586034 
Step 7701 | loss:2.0299336910247803 lr:1.0183649561817277e-06 tokens_per_second_per_gpu:2187.2365150921187 
Step 7702 | loss:2.023141622543335 lr:1.0127713354149305e-06 tokens_per_second_per_gpu:2194.0478843068145 
Step 7703 | loss:2.078507900238037 lr:1.0071930409667363e-06 tokens_per_second_per_gpu:2176.2508854713333 
Step 7704 | loss:2.1039888858795166 lr:1.0016300737007989e-06 tokens_per_second_per_gpu:2108.462493811894 
Step 7705 | loss:2.0368030071258545 lr:9.960824344784736e-07 tokens_per_second_per_gpu:2180.234945387822 
Step 7706 | loss:2.1063408851623535 lr:9.905501241586734e-07 tokens_per_second_per_gpu:2195.5706581557893 
Step 7707 | loss:2.0837488174438477 lr:9.85033143598013e-07 tokens_per_second_per_gpu:2188.807838154793 
Step 7708 | loss:1.9656115770339966 lr:9.79531493650654e-07 tokens_per_second_per_gpu:2149.053469052555 
Step 7709 | loss:2.0540757179260254 lr:9.740451751684475e-07 tokens_per_second_per_gpu:2175.0536773287904 
Step 7710 | loss:1.9643073081970215 lr:9.68574189000837e-07 tokens_per_second_per_gpu:2198.2199971206837 
Step 7711 | loss:2.0477113723754883 lr:9.631185359949113e-07 tokens_per_second_per_gpu:2190.7408767501556 
Step 7712 | loss:2.0558342933654785 lr:9.576782169953725e-07 tokens_per_second_per_gpu:2173.99196177035 
Step 7713 | loss:2.063678741455078 lr:9.522532328445466e-07 tokens_per_second_per_gpu:2185.0334758603985 
Step 7714 | loss:2.1113500595092773 lr:9.468435843823953e-07 tokens_per_second_per_gpu:2171.8849737641945 
Step 7715 | loss:2.08127498626709 lr:9.41449272446504e-07 tokens_per_second_per_gpu:2147.391962032478 
Step 7716 | loss:2.170927047729492 lr:9.360702978720825e-07 tokens_per_second_per_gpu:2156.070686472738 
Step 7717 | loss:2.082003593444824 lr:9.307066614919535e-07 tokens_per_second_per_gpu:2199.6340199283345 
Step 7718 | loss:2.0532712936401367 lr:9.25358364136586e-07 tokens_per_second_per_gpu:2167.7665981003547 
Step 7719 | loss:2.0796658992767334 lr:9.200254066340508e-07 tokens_per_second_per_gpu:2164.7697989984053 
Step 7720 | loss:2.079031467437744 lr:9.147077898100653e-07 tokens_per_second_per_gpu:2166.2041533459424 
Step 7721 | loss:2.0982108116149902 lr:9.094055144879821e-07 tokens_per_second_per_gpu:2199.537266614259 
Step 7722 | loss:2.1407082080841064 lr:9.04118581488722e-07 tokens_per_second_per_gpu:2147.5657401539306 
Step 7723 | loss:2.095201253890991 lr:8.988469916308861e-07 tokens_per_second_per_gpu:2145.3970890300097 
Step 7724 | loss:2.0260157585144043 lr:8.93590745730688e-07 tokens_per_second_per_gpu:2161.6470391159514 
Step 7725 | loss:2.1396255493164062 lr:8.883498446019544e-07 tokens_per_second_per_gpu:2154.111334293434 
Step 7726 | loss:2.060335636138916 lr:8.831242890561253e-07 tokens_per_second_per_gpu:2131.752356512221 
Step 7727 | loss:2.0797600746154785 lr:8.779140799023089e-07 tokens_per_second_per_gpu:2184.593271117665 
Step 7728 | loss:2.0488739013671875 lr:8.727192179471822e-07 tokens_per_second_per_gpu:2196.9289658984962 
Step 7729 | loss:2.047792434692383 lr:8.675397039950795e-07 tokens_per_second_per_gpu:2193.075396776283 
Step 7730 | loss:2.0153768062591553 lr:8.623755388479593e-07 tokens_per_second_per_gpu:2168.168518714447 
Step 7731 | loss:2.1080756187438965 lr:8.572267233053933e-07 tokens_per_second_per_gpu:2189.824515540977 
Step 7732 | loss:2.0452637672424316 lr:8.520932581645769e-07 tokens_per_second_per_gpu:2197.7625217563213 
Step 7733 | loss:2.083904504776001 lr:8.469751442203299e-07 tokens_per_second_per_gpu:2130.336505618472 
Step 7734 | loss:2.079935073852539 lr:8.418723822650964e-07 tokens_per_second_per_gpu:2087.5677301953947 
Step 7735 | loss:2.065518856048584 lr:8.367849730889443e-07 tokens_per_second_per_gpu:2179.45187083521 
Step 7736 | loss:2.071359634399414 lr:8.317129174795657e-07 tokens_per_second_per_gpu:2149.723717221064 
Step 7737 | loss:2.0544538497924805 lr:8.266562162222769e-07 tokens_per_second_per_gpu:2177.2441604414507 
Step 7738 | loss:2.0588769912719727 lr:8.21614870100007e-07 tokens_per_second_per_gpu:2159.407458860813 
Step 7739 | loss:2.0824673175811768 lr:8.165888798933097e-07 tokens_per_second_per_gpu:2186.880127568619 
Step 7740 | loss:2.0337347984313965 lr:8.115782463803733e-07 tokens_per_second_per_gpu:2145.037726483308 
Step 7741 | loss:2.0570337772369385 lr:8.065829703369998e-07 tokens_per_second_per_gpu:2189.0727291134563 
Step 7742 | loss:2.1143417358398438 lr:8.016030525366147e-07 tokens_per_second_per_gpu:2138.713950199052 
Step 7743 | loss:2.0494513511657715 lr:7.966384937502569e-07 tokens_per_second_per_gpu:2171.0875345742675 
Step 7744 | loss:2.0202081203460693 lr:7.916892947466004e-07 tokens_per_second_per_gpu:2146.419141950362 
Step 7745 | loss:2.048670768737793 lr:7.867554562919433e-07 tokens_per_second_per_gpu:2053.3443372337438 
Step 7746 | loss:2.056934356689453 lr:7.818369791501856e-07 tokens_per_second_per_gpu:2184.0121048215115 
Step 7747 | loss:2.0626473426818848 lr:7.769338640828739e-07 tokens_per_second_per_gpu:2189.6417806275485 
Step 7748 | loss:2.1656124591827393 lr:7.720461118491673e-07 tokens_per_second_per_gpu:2162.0880427556544 
Step 7749 | loss:2.0683112144470215 lr:7.671737232058163e-07 tokens_per_second_per_gpu:2164.9060732386 
Step 7750 | loss:2.1029672622680664 lr:7.623166989072394e-07 tokens_per_second_per_gpu:2145.7960498055286 
Step 7751 | loss:2.0557591915130615 lr:7.574750397054576e-07 tokens_per_second_per_gpu:2168.679161845484 
Step 7752 | loss:2.0377626419067383 lr:7.526487463501041e-07 tokens_per_second_per_gpu:2159.8239908538453 
Step 7753 | loss:2.0606608390808105 lr:7.478378195884372e-07 tokens_per_second_per_gpu:2140.815022092747 
Step 7754 | loss:2.0362672805786133 lr:7.430422601653497e-07 tokens_per_second_per_gpu:2151.5621270163133 
Step 7755 | loss:2.1006953716278076 lr:7.382620688233366e-07 tokens_per_second_per_gpu:2112.717543424627 
Step 7756 | loss:2.0679140090942383 lr:7.334972463025059e-07 tokens_per_second_per_gpu:2167.3002605978386 
Step 7757 | loss:2.0013484954833984 lr:7.287477933406339e-07 tokens_per_second_per_gpu:2196.437050712022 
Step 7758 | loss:2.063964366912842 lr:7.24013710673066e-07 tokens_per_second_per_gpu:2194.0873779377325 
Step 7759 | loss:2.086686611175537 lr:7.192949990327935e-07 tokens_per_second_per_gpu:2105.7644145130266 
Step 7760 | loss:2.086271286010742 lr:7.145916591504098e-07 tokens_per_second_per_gpu:2119.6286309894044 
Step 7761 | loss:2.012397050857544 lr:7.099036917541324e-07 tokens_per_second_per_gpu:2150.7355558714175 
Step 7762 | loss:2.102534770965576 lr:7.052310975698362e-07 tokens_per_second_per_gpu:2189.8178315151026 
Step 7763 | loss:2.101015329360962 lr:7.005738773209647e-07 tokens_per_second_per_gpu:2110.845499723488 
Step 7764 | loss:2.0869574546813965 lr:6.959320317285856e-07 tokens_per_second_per_gpu:2120.776295387674 
Step 7765 | loss:2.0751075744628906 lr:6.91305561511435e-07 tokens_per_second_per_gpu:2202.424885078704 
Step 7766 | loss:2.038160800933838 lr:6.866944673858066e-07 tokens_per_second_per_gpu:2169.0629551646443 
Step 7767 | loss:2.0649919509887695 lr:6.820987500656629e-07 tokens_per_second_per_gpu:2190.1786652144397 
Step 7768 | loss:2.0716729164123535 lr:6.775184102625564e-07 tokens_per_second_per_gpu:2159.739899946604 
Step 7769 | loss:2.0601494312286377 lr:6.729534486856648e-07 tokens_per_second_per_gpu:2179.7540944238826 
Step 7770 | loss:2.1003692150115967 lr:6.684038660417891e-07 tokens_per_second_per_gpu:2162.5712263936375 
Step 7771 | loss:2.039790630340576 lr:6.638696630353436e-07 tokens_per_second_per_gpu:2175.421310158256 
Step 7772 | loss:2.117990016937256 lr:6.593508403683668e-07 tokens_per_second_per_gpu:2172.025164873836 
Step 7773 | loss:2.0399985313415527 lr:6.548473987405101e-07 tokens_per_second_per_gpu:2183.727540598293 
Step 7774 | loss:2.0960781574249268 lr:6.503593388490603e-07 tokens_per_second_per_gpu:2150.4537702522853 
Step 7775 | loss:2.1365556716918945 lr:6.458866613889059e-07 tokens_per_second_per_gpu:2185.7829436604648 
Step 7776 | loss:2.0381064414978027 lr:6.414293670525484e-07 tokens_per_second_per_gpu:2149.3914655212934 
Step 7777 | loss:2.0780673027038574 lr:6.369874565301026e-07 tokens_per_second_per_gpu:2049.0682833779247 
Step 7778 | loss:2.0392708778381348 lr:6.325609305093516e-07 tokens_per_second_per_gpu:2138.1475990052477 
Step 7779 | loss:2.0197410583496094 lr:6.281497896756361e-07 tokens_per_second_per_gpu:2135.749419223807 
Step 7780 | loss:2.1283841133117676 lr:6.23754034711943e-07 tokens_per_second_per_gpu:2088.928740644602 
Step 7781 | loss:2.111238718032837 lr:6.193736662988725e-07 tokens_per_second_per_gpu:2189.6164427948543 
Step 7782 | loss:2.07059907913208 lr:6.150086851146486e-07 tokens_per_second_per_gpu:2164.655263488771 
Step 7783 | loss:2.0670249462127686 lr:6.106590918350863e-07 tokens_per_second_per_gpu:2150.9572852336373 
Step 7784 | loss:2.020507335662842 lr:6.063248871336691e-07 tokens_per_second_per_gpu:2194.3008846747457 
Step 7785 | loss:2.0790493488311768 lr:6.02006071681449e-07 tokens_per_second_per_gpu:2182.3009500039557 
Step 7786 | loss:2.089035987854004 lr:5.977026461471136e-07 tokens_per_second_per_gpu:2076.9906201446 
Step 7787 | loss:2.0629420280456543 lr:5.934146111969741e-07 tokens_per_second_per_gpu:2157.1925751513245 
Step 7788 | loss:2.0262365341186523 lr:5.89141967494955e-07 tokens_per_second_per_gpu:2197.739800954836 
Step 7789 | loss:2.0572762489318848 lr:5.848847157025827e-07 tokens_per_second_per_gpu:2017.7049160010858 
Step 7790 | loss:2.081768274307251 lr:5.80642856479019e-07 tokens_per_second_per_gpu:2168.84947946846 
Step 7791 | loss:2.0527565479278564 lr:5.764163904810382e-07 tokens_per_second_per_gpu:2175.5874097262954 
Step 7792 | loss:2.0520663261413574 lr:5.722053183630283e-07 tokens_per_second_per_gpu:2191.279932546936 
Step 7793 | loss:2.0548324584960938 lr:5.680096407769897e-07 tokens_per_second_per_gpu:2151.6806201605145 
Step 7794 | loss:2.0806565284729004 lr:5.638293583725584e-07 tokens_per_second_per_gpu:2143.1882592473044 
Step 7795 | loss:2.1106953620910645 lr:5.596644717969612e-07 tokens_per_second_per_gpu:2141.1922924251194 
Step 7796 | loss:1.9839991331100464 lr:5.5551498169506e-07 tokens_per_second_per_gpu:2111.9529461693132 
Step 7797 | loss:2.0889625549316406 lr:5.513808887093186e-07 tokens_per_second_per_gpu:2197.474338514652 
Step 7798 | loss:2.0535192489624023 lr:5.47262193479825e-07 tokens_per_second_per_gpu:2168.1379872287325 
Step 7799 | loss:2.072732448577881 lr:5.431588966442802e-07 tokens_per_second_per_gpu:2175.5579739904056 
Step 7800 | loss:2.1019296646118164 lr:5.390709988380094e-07 tokens_per_second_per_gpu:2197.7751439025647 
Step 7801 | loss:2.1138978004455566 lr:5.349985006939506e-07 tokens_per_second_per_gpu:2191.8142005766813 
Step 7802 | loss:2.05198335647583 lr:5.309414028426441e-07 tokens_per_second_per_gpu:2174.2752310669734 
Step 7803 | loss:2.0529251098632812 lr:5.268997059122538e-07 tokens_per_second_per_gpu:2166.63283119675 
Step 7804 | loss:2.0597524642944336 lr:5.228734105285682e-07 tokens_per_second_per_gpu:2147.7683819097474 
Step 7805 | loss:2.052220344543457 lr:5.188625173149886e-07 tokens_per_second_per_gpu:2193.2492026056652 
Step 7806 | loss:2.1118054389953613 lr:5.148670268925071e-07 tokens_per_second_per_gpu:2188.3458918444026 
Step 7807 | loss:2.0045862197875977 lr:5.108869398797733e-07 tokens_per_second_per_gpu:2187.620552772185 
Step 7808 | loss:2.0686593055725098 lr:5.069222568930166e-07 tokens_per_second_per_gpu:2173.840089662865 
Step 7809 | loss:2.0607545375823975 lr:5.029729785460902e-07 tokens_per_second_per_gpu:2100.5187151180507 
Step 7810 | loss:2.061384439468384 lr:4.990391054504717e-07 tokens_per_second_per_gpu:2180.7719822267095 
Step 7811 | loss:2.069809913635254 lr:4.951206382152518e-07 tokens_per_second_per_gpu:2162.924897051855 
Step 7812 | loss:2.0108184814453125 lr:4.91217577447134e-07 tokens_per_second_per_gpu:2144.993067482025 
Step 7813 | loss:2.059354305267334 lr:4.873299237504125e-07 tokens_per_second_per_gpu:2062.3952393985915 
Step 7814 | loss:2.005751371383667 lr:4.834576777270394e-07 tokens_per_second_per_gpu:2190.5479474589188 
Step 7815 | loss:2.0869359970092773 lr:4.796008399765572e-07 tokens_per_second_per_gpu:2189.7618213460773 
Step 7816 | loss:2.066898822784424 lr:4.7575941109612167e-07 tokens_per_second_per_gpu:2157.0453056948913 
Step 7817 | loss:2.0671799182891846 lr:4.7193339168050133e-07 tokens_per_second_per_gpu:2197.3615187607347 
Step 7818 | loss:2.0760140419006348 lr:4.6812278232208906e-07 tokens_per_second_per_gpu:2160.9419035861506 
Step 7819 | loss:2.079051971435547 lr:4.643275836108796e-07 tokens_per_second_per_gpu:2192.9662082510067 
Step 7820 | loss:2.0738377571105957 lr:4.6054779613450283e-07 tokens_per_second_per_gpu:2191.862711772745 
Step 7821 | loss:1.9942982196807861 lr:4.5678342047817954e-07 tokens_per_second_per_gpu:2146.9312266310276 
Step 7822 | loss:2.0328896045684814 lr:4.5303445722474357e-07 tokens_per_second_per_gpu:2195.1648695435074 
Step 7823 | loss:2.128619909286499 lr:4.4930090695466387e-07 tokens_per_second_per_gpu:2191.575500463315 
Step 7824 | loss:2.0166704654693604 lr:4.4558277024601134e-07 tokens_per_second_per_gpu:2186.8626713735393 
Step 7825 | loss:2.0682990550994873 lr:4.4188004767445887e-07 tokens_per_second_per_gpu:2160.6325112713907 
Step 7826 | loss:2.053447723388672 lr:4.3819273981331454e-07 tokens_per_second_per_gpu:2136.7140955565183 
Step 7827 | loss:2.0521373748779297 lr:4.3452084723347717e-07 tokens_per_second_per_gpu:2178.750165465968 
Step 7828 | loss:2.078202724456787 lr:4.3086437050349206e-07 tokens_per_second_per_gpu:2197.1490962080316 
Step 7829 | loss:2.086359977722168 lr:4.2722331018947293e-07 tokens_per_second_per_gpu:2185.689824745976 
Step 7830 | loss:2.084139347076416 lr:4.2359766685518e-07 tokens_per_second_per_gpu:2195.910943707115 
Step 7831 | loss:2.099061965942383 lr:4.199874410619753e-07 tokens_per_second_per_gpu:2169.73306392493 
Step 7832 | loss:2.075277805328369 lr:4.1639263336884506e-07 tokens_per_second_per_gpu:2180.3379170016783 
Step 7833 | loss:1.962296962738037 lr:4.1281324433235515e-07 tokens_per_second_per_gpu:2143.6548180629707 
Step 7834 | loss:2.084874153137207 lr:4.0924927450671777e-07 tokens_per_second_per_gpu:2087.747188186662 
Step 7835 | loss:2.13305926322937 lr:4.057007244437583e-07 tokens_per_second_per_gpu:2202.3860383819697 
Step 7836 | loss:2.0396275520324707 lr:4.0216759469289266e-07 tokens_per_second_per_gpu:2174.586705116807 
Step 7837 | loss:2.1340012550354004 lr:3.9864988580116113e-07 tokens_per_second_per_gpu:2137.1693320226673 
Step 7838 | loss:2.146209716796875 lr:3.951475983132058e-07 tokens_per_second_per_gpu:2187.287598804173 
Step 7839 | loss:2.0924859046936035 lr:3.91660732771304e-07 tokens_per_second_per_gpu:2168.4098107509108 
Step 7840 | loss:2.0652389526367188 lr:3.88189289715335e-07 tokens_per_second_per_gpu:2186.24591048232 
Step 7841 | loss:2.037111759185791 lr:3.847332696827688e-07 tokens_per_second_per_gpu:2176.601054267502 
Step 7842 | loss:2.018392562866211 lr:3.8129267320872184e-07 tokens_per_second_per_gpu:2153.3041740605936 
Step 7843 | loss:2.079550266265869 lr:3.778675008258903e-07 tokens_per_second_per_gpu:2178.824901866201 
Step 7844 | loss:2.13417387008667 lr:3.744577530646165e-07 tokens_per_second_per_gpu:2142.3264169462095 
Step 7845 | loss:2.0976696014404297 lr:3.7106343045282264e-07 tokens_per_second_per_gpu:2180.334001466477 
Step 7846 | loss:2.030163288116455 lr:3.6768453351605503e-07 tokens_per_second_per_gpu:2158.0330442912823 
Step 7847 | loss:2.087559700012207 lr:3.6432106277748404e-07 tokens_per_second_per_gpu:2192.20497617509 
Step 7848 | loss:2.0729970932006836 lr:3.6097301875787084e-07 tokens_per_second_per_gpu:2177.6166473311782 
Step 7849 | loss:2.0286335945129395 lr:3.576404019756008e-07 tokens_per_second_per_gpu:2029.4170488611337 
Step 7850 | loss:2.0765628814697266 lr:3.5432321294666114e-07 tokens_per_second_per_gpu:2191.699528227822 
Step 7851 | loss:2.1097640991210938 lr:3.510214521846744e-07 tokens_per_second_per_gpu:2153.703552962136 
Step 7852 | loss:2.0907974243164062 lr:3.4773512020083167e-07 tokens_per_second_per_gpu:2190.876208381955 
Step 7853 | loss:2.0467395782470703 lr:3.444642175039814e-07 tokens_per_second_per_gpu:2123.897458265545 
Step 7854 | loss:2.071221351623535 lr:3.4120874460054077e-07 tokens_per_second_per_gpu:2123.49368578226 
Step 7855 | loss:2.0923361778259277 lr:3.379687019945732e-07 tokens_per_second_per_gpu:2126.943244687753 
Step 7856 | loss:2.0785953998565674 lr:3.347440901877441e-07 tokens_per_second_per_gpu:2180.6307656555005 
Step 7857 | loss:2.12882661819458 lr:3.3153490967930965e-07 tokens_per_second_per_gpu:2173.2894783949546 
Step 7858 | loss:2.056515693664551 lr:3.283411609661613e-07 tokens_per_second_per_gpu:2089.7954459497278 
Step 7859 | loss:2.082185745239258 lr:3.2516284454278123e-07 tokens_per_second_per_gpu:2145.6891311773375 
Step 7860 | loss:2.094808578491211 lr:3.219999609012869e-07 tokens_per_second_per_gpu:2091.691546273512 
Step 7861 | loss:2.0653128623962402 lr:3.1885251053137556e-07 tokens_per_second_per_gpu:2198.7809576404247 
Step 7862 | loss:2.101325511932373 lr:3.157204939203795e-07 tokens_per_second_per_gpu:2170.8138739379083 
Step 7863 | loss:2.0677919387817383 lr:3.126039115532331e-07 tokens_per_second_per_gpu:2190.624408598052 
Step 7864 | loss:2.0365264415740967 lr:3.0950276391247257e-07 tokens_per_second_per_gpu:2191.296124847695 
Step 7865 | loss:2.036055564880371 lr:3.064170514782694e-07 tokens_per_second_per_gpu:2190.1422901943406 
Step 7866 | loss:2.0709168910980225 lr:3.033467747283858e-07 tokens_per_second_per_gpu:2181.0444892585047 
Step 7867 | loss:2.011615037918091 lr:3.002919341381749e-07 tokens_per_second_per_gpu:2187.5488443821605 
Step 7868 | loss:2.041851043701172 lr:2.9725253018064726e-07 tokens_per_second_per_gpu:2183.265754497236 
Step 7869 | loss:2.0763955116271973 lr:2.9422856332637083e-07 tokens_per_second_per_gpu:2195.4316216967286 
Step 7870 | loss:2.0651192665100098 lr:2.912200340435711e-07 tokens_per_second_per_gpu:2178.0787724467423 
Step 7871 | loss:2.096428632736206 lr:2.882269427980644e-07 tokens_per_second_per_gpu:2157.6200194234225 
Step 7872 | loss:2.1198339462280273 lr:2.8524929005326885e-07 tokens_per_second_per_gpu:2198.3132902400075 
Step 7873 | loss:2.0689687728881836 lr:2.8228707627020457e-07 tokens_per_second_per_gpu:2166.8143292893124 
Step 7874 | loss:2.0321059226989746 lr:2.7934030190753804e-07 tokens_per_second_per_gpu:2190.7890995399625 
Step 7875 | loss:2.0337772369384766 lr:2.764089674215042e-07 tokens_per_second_per_gpu:2132.4443527824883 
Step 7876 | loss:2.053192138671875 lr:2.734930732659735e-07 tokens_per_second_per_gpu:2189.4563488004037 
Step 7877 | loss:2.1007423400878906 lr:2.7059261989241805e-07 tokens_per_second_per_gpu:2174.197648679795 
Step 7878 | loss:2.105733871459961 lr:2.67707607749923e-07 tokens_per_second_per_gpu:2195.9032923122154 
Step 7879 | loss:2.1225087642669678 lr:2.6483803728516445e-07 tokens_per_second_per_gpu:2175.7346346064137 
Step 7880 | loss:2.0883944034576416 lr:2.619839089424536e-07 tokens_per_second_per_gpu:2190.5199314373826 
Step 7881 | loss:2.033461332321167 lr:2.591452231636926e-07 tokens_per_second_per_gpu:2187.6647804023432 
Step 7882 | loss:2.0218124389648438 lr:2.563219803884076e-07 tokens_per_second_per_gpu:2171.109014352212 
Step 7883 | loss:2.044778823852539 lr:2.535141810537156e-07 tokens_per_second_per_gpu:2158.952309102612 
Step 7884 | loss:2.09440279006958 lr:2.507218255943467e-07 tokens_per_second_per_gpu:2186.806368590199 
Step 7885 | loss:2.0467448234558105 lr:2.479449144426549e-07 tokens_per_second_per_gpu:2194.8610835650247 
Step 7886 | loss:2.068546772003174 lr:2.451834480285964e-07 tokens_per_second_per_gpu:2141.6894722078323 
Step 7887 | loss:2.080386161804199 lr:2.424374267797291e-07 tokens_per_second_per_gpu:2177.364286229404 
Step 7888 | loss:2.028754234313965 lr:2.3970685112121304e-07 tokens_per_second_per_gpu:2078.438450796839 
Step 7889 | loss:2.112196922302246 lr:2.3699172147584326e-07 tokens_per_second_per_gpu:2140.5761604547765 
Step 7890 | loss:2.118748664855957 lr:2.342920382639835e-07 tokens_per_second_per_gpu:2164.349625179655 
Step 7891 | loss:2.0722367763519287 lr:2.3160780190365494e-07 tokens_per_second_per_gpu:2198.683660972667 
Step 7892 | loss:2.1081600189208984 lr:2.289390128104474e-07 tokens_per_second_per_gpu:2183.1376177490642 
Step 7893 | loss:2.0556812286376953 lr:2.2628567139758582e-07 tokens_per_second_per_gpu:2181.8679216319647 
Step 7894 | loss:2.072902202606201 lr:2.236477780758639e-07 tokens_per_second_per_gpu:2178.424686397356 
Step 7895 | loss:2.0360121726989746 lr:2.2102533325373264e-07 tokens_per_second_per_gpu:2131.6031208720547 
Step 7896 | loss:2.0653836727142334 lr:2.1841833733722284e-07 tokens_per_second_per_gpu:2194.259045890443 
Step 7897 | loss:2.0687403678894043 lr:2.1582679072997826e-07 tokens_per_second_per_gpu:2185.841133574871 
Step 7898 | loss:2.070319652557373 lr:2.1325069383324458e-07 tokens_per_second_per_gpu:2176.371111815174 
Step 7899 | loss:2.078878402709961 lr:2.106900470458917e-07 tokens_per_second_per_gpu:2182.300934889841 
Step 7900 | loss:2.035440683364868 lr:2.0814485076439128e-07 tokens_per_second_per_gpu:2199.4749169937745 
Step 7901 | loss:2.072822332382202 lr:2.0561510538280592e-07 tokens_per_second_per_gpu:2137.427269817926 
Step 7902 | loss:2.034519672393799 lr:2.0310081129283341e-07 tokens_per_second_per_gpu:2198.035946128321 
Step 7903 | loss:2.0920705795288086 lr:2.0060196888375127e-07 tokens_per_second_per_gpu:2004.4598769328825 
Step 7904 | loss:2.062326192855835 lr:1.9811857854247217e-07 tokens_per_second_per_gpu:2165.1929183008724 
Step 7905 | loss:2.043839931488037 lr:1.956506406534886e-07 tokens_per_second_per_gpu:2192.6652737597315 
Step 7906 | loss:2.1082968711853027 lr:1.9319815559892817e-07 tokens_per_second_per_gpu:2111.9834243826963 
Step 7907 | loss:2.051508903503418 lr:1.907611237584983e-07 tokens_per_second_per_gpu:2153.1154120635883 
Step 7908 | loss:2.0530178546905518 lr:1.8833954550954158e-07 tokens_per_second_per_gpu:2191.283982973251 
Step 7909 | loss:2.075611114501953 lr:1.859334212269803e-07 tokens_per_second_per_gpu:2191.8507206074937 
Step 7910 | loss:2.093573570251465 lr:1.8354275128337205e-07 tokens_per_second_per_gpu:2138.6114465872133 
Step 7911 | loss:2.0828943252563477 lr:1.8116753604885406e-07 tokens_per_second_per_gpu:2156.2001913918366 
Step 7912 | loss:2.054910898208618 lr:1.7880777589119878e-07 tokens_per_second_per_gpu:2198.4063325697916 
Step 7913 | loss:2.0524330139160156 lr:1.7646347117575846e-07 tokens_per_second_per_gpu:2186.896094713803 
Step 7914 | loss:2.0741500854492188 lr:1.7413462226550936e-07 tokens_per_second_per_gpu:2104.1387145390886 
Step 7915 | loss:2.12558650970459 lr:1.7182122952101865e-07 tokens_per_second_per_gpu:2185.247254349348 
Step 7916 | loss:2.0895192623138428 lr:1.6952329330049977e-07 tokens_per_second_per_gpu:2118.953977505526 
Step 7917 | loss:2.1025636196136475 lr:1.672408139597126e-07 tokens_per_second_per_gpu:2196.739846142904 
Step 7918 | loss:2.1070351600646973 lr:1.6497379185208551e-07 tokens_per_second_per_gpu:2123.959660299756 
Step 7919 | loss:2.0366456508636475 lr:1.6272222732860442e-07 tokens_per_second_per_gpu:2119.4234613583935 
Step 7920 | loss:2.052919864654541 lr:1.604861207378794e-07 tokens_per_second_per_gpu:2172.115636518569 
Step 7921 | loss:2.118385076522827 lr:1.5826547242614454e-07 tokens_per_second_per_gpu:2192.6028147312363 
Step 7922 | loss:2.0143818855285645 lr:1.5606028273722484e-07 tokens_per_second_per_gpu:2124.1333166039676 
Step 7923 | loss:2.1316919326782227 lr:1.5387055201254718e-07 tokens_per_second_per_gpu:2147.3476322785195 
Step 7924 | loss:2.081681728363037 lr:1.5169628059114037e-07 tokens_per_second_per_gpu:2200.459281146768 
Step 7925 | loss:2.1161623001098633 lr:1.4953746880966845e-07 tokens_per_second_per_gpu:2178.154026138673 
Step 7926 | loss:2.076427459716797 lr:1.4739411700237516e-07 tokens_per_second_per_gpu:2196.23036067095 
Step 7927 | loss:2.0797762870788574 lr:1.4526622550111723e-07 tokens_per_second_per_gpu:2156.488954502009 
Step 7928 | loss:2.042781352996826 lr:1.4315379463535339e-07 tokens_per_second_per_gpu:2138.696868898178 
Step 7929 | loss:2.0689797401428223 lr:1.410568247321553e-07 tokens_per_second_per_gpu:2166.079502371475 
Step 7930 | loss:2.10434889793396 lr:1.3897531611620773e-07 tokens_per_second_per_gpu:2179.7682086580226 
Step 7931 | loss:2.0448718070983887 lr:1.3690926910979728e-07 tokens_per_second_per_gpu:2190.724505256219 
Step 7932 | loss:2.049556255340576 lr:1.3485868403280145e-07 tokens_per_second_per_gpu:2182.2940583019645 
Step 7933 | loss:2.0583724975585938 lr:1.3282356120271068e-07 tokens_per_second_per_gpu:2164.2198458220814 
Step 7934 | loss:2.0162806510925293 lr:1.3080390093463957e-07 tokens_per_second_per_gpu:2197.927965321005 
Step 7935 | loss:2.0801968574523926 lr:1.2879970354129357e-07 tokens_per_second_per_gpu:2165.2487097225558 
Step 7936 | loss:2.041195869445801 lr:1.2681096933296887e-07 tokens_per_second_per_gpu:2160.6123128424533 
Step 7937 | loss:2.0712080001831055 lr:1.2483769861759699e-07 tokens_per_second_per_gpu:2197.8714526200906 
Step 7938 | loss:2.045501232147217 lr:1.2287989170070014e-07 tokens_per_second_per_gpu:2180.76171284846 
Step 7939 | loss:2.063741445541382 lr:1.2093754888541365e-07 tokens_per_second_per_gpu:2108.5527031864463 
Step 7940 | loss:2.065598964691162 lr:1.1901067047246361e-07 tokens_per_second_per_gpu:2179.768238542969 
Step 7941 | loss:2.0282819271087646 lr:1.1709925676018918e-07 tokens_per_second_per_gpu:2180.238161741958 
Step 7942 | loss:1.9660862684249878 lr:1.152033080445536e-07 tokens_per_second_per_gpu:2192.9491233011163 
Step 7943 | loss:2.0473713874816895 lr:1.1332282461908872e-07 tokens_per_second_per_gpu:2157.673982607525 
Step 7944 | loss:2.0034523010253906 lr:1.1145780677496164e-07 tokens_per_second_per_gpu:2195.6006185277024 
Step 7945 | loss:2.088564157485962 lr:1.0960825480093029e-07 tokens_per_second_per_gpu:2191.2688852715546 
Step 7946 | loss:2.1029181480407715 lr:1.0777416898337666e-07 tokens_per_second_per_gpu:2176.479513720875 
Step 7947 | loss:2.1025094985961914 lr:1.0595554960626253e-07 tokens_per_second_per_gpu:2135.7443203955954 
Step 7948 | loss:2.0769920349121094 lr:1.0415239695116264e-07 tokens_per_second_per_gpu:2155.8694528655114 
Step 7949 | loss:2.0978312492370605 lr:1.0236471129727588e-07 tokens_per_second_per_gpu:2173.6509491291463 
Step 7950 | loss:2.0869979858398438 lr:1.0059249292138084e-07 tokens_per_second_per_gpu:2153.917152458078 
Step 7951 | loss:2.0596914291381836 lr:9.883574209788027e-08 tokens_per_second_per_gpu:2195.225635440655 
Step 7952 | loss:2.084141731262207 lr:9.709445909876769e-08 tokens_per_second_per_gpu:2183.2900700273462 
Step 7953 | loss:2.0456337928771973 lr:9.536864419366076e-08 tokens_per_second_per_gpu:2107.017987543969 
Step 7954 | loss:2.0992655754089355 lr:9.365829764974576e-08 tokens_per_second_per_gpu:2143.6803309037678 
Step 7955 | loss:2.065232753753662 lr:9.19634197318553e-08 tokens_per_second_per_gpu:2138.4754444966948 
Step 7956 | loss:2.056286334991455 lr:9.028401070241276e-08 tokens_per_second_per_gpu:2187.423368407543 
Step 7957 | loss:2.032912254333496 lr:8.862007082143242e-08 tokens_per_second_per_gpu:2181.088876647428 
Step 7958 | loss:2.0685129165649414 lr:8.69716003465415e-08 tokens_per_second_per_gpu:2141.7880193113015 
Step 7959 | loss:2.1383016109466553 lr:8.533859953299139e-08 tokens_per_second_per_gpu:2188.1645183432906 
Step 7960 | loss:2.124276638031006 lr:8.372106863360208e-08 tokens_per_second_per_gpu:2179.1282186092535 
Step 7961 | loss:2.131450891494751 lr:8.211900789882876e-08 tokens_per_second_per_gpu:2193.030847231196 
Step 7962 | loss:2.0881760120391846 lr:8.053241757672857e-08 tokens_per_second_per_gpu:2182.337782733224 
Step 7963 | loss:2.068936347961426 lr:7.896129791293838e-08 tokens_per_second_per_gpu:2157.1901726111573 
Step 7964 | loss:2.05875301361084 lr:7.740564915071913e-08 tokens_per_second_per_gpu:2161.533453093086 
Step 7965 | loss:2.0655646324157715 lr:7.586547153094481e-08 tokens_per_second_per_gpu:2199.308237491525 
Step 7966 | loss:2.075322151184082 lr:7.434076529208023e-08 tokens_per_second_per_gpu:2196.8088813395007 
Step 7967 | loss:2.070319652557373 lr:7.283153067019211e-08 tokens_per_second_per_gpu:2179.73201509596 
Step 7968 | loss:2.0745067596435547 lr:7.133776789896018e-08 tokens_per_second_per_gpu:2081.316166982285 
Step 7969 | loss:2.0102384090423584 lr:6.985947720966612e-08 tokens_per_second_per_gpu:2142.6872015080467 
Step 7970 | loss:2.061783790588379 lr:6.83966588311935e-08 tokens_per_second_per_gpu:2170.871149175436 
Step 7971 | loss:2.047516345977783 lr:6.694931299002782e-08 tokens_per_second_per_gpu:2189.5866134323082 
Step 7972 | loss:2.050079107284546 lr:6.55174399102787e-08 tokens_per_second_per_gpu:2195.2674859138097 
Step 7973 | loss:2.050252914428711 lr:6.410103981362436e-08 tokens_per_second_per_gpu:2195.297503770165 
Step 7974 | loss:2.008945941925049 lr:6.270011291938938e-08 tokens_per_second_per_gpu:2195.494576098129 
Step 7975 | loss:2.094475746154785 lr:6.13146594444669e-08 tokens_per_second_per_gpu:2197.39035622255 
Step 7976 | loss:2.0349438190460205 lr:5.994467960336314e-08 tokens_per_second_per_gpu:2193.0826193680336 
Step 7977 | loss:2.070862293243408 lr:5.85901736082195e-08 tokens_per_second_per_gpu:2191.189627348714 
Step 7978 | loss:2.0134382247924805 lr:5.7251141668723806e-08 tokens_per_second_per_gpu:2110.803804871784 
Step 7979 | loss:2.107637882232666 lr:5.592758399222131e-08 tokens_per_second_per_gpu:2130.17268937953 
Step 7980 | loss:2.1088809967041016 lr:5.461950078363698e-08 tokens_per_second_per_gpu:2167.0022263735195 
Step 7981 | loss:2.058988094329834 lr:5.3326892245497694e-08 tokens_per_second_per_gpu:2179.439365348023 
Step 7982 | loss:2.093472957611084 lr:5.2049758577943367e-08 tokens_per_second_per_gpu:2192.9738502899336 
Step 7983 | loss:2.1132149696350098 lr:5.078809997870471e-08 tokens_per_second_per_gpu:2161.4270269166927 
Step 7984 | loss:2.0535480976104736 lr:4.954191664313657e-08 tokens_per_second_per_gpu:2153.0011452761323 
Step 7985 | loss:1.9594906568527222 lr:4.83112087641957e-08 tokens_per_second_per_gpu:2155.3664944059465 
Step 7986 | loss:2.0527944564819336 lr:4.709597653241859e-08 tokens_per_second_per_gpu:2122.5478460200316 
Step 7987 | loss:2.125638008117676 lr:4.589622013595474e-08 tokens_per_second_per_gpu:2168.1715951411607 
Step 7988 | loss:2.068843364715576 lr:4.471193976058885e-08 tokens_per_second_per_gpu:2140.8648525090334 
Step 7989 | loss:2.0406341552734375 lr:4.3543135589663166e-08 tokens_per_second_per_gpu:2166.232956350548 
Step 7990 | loss:2.0794014930725098 lr:4.238980780415513e-08 tokens_per_second_per_gpu:2145.6325436716215 
Step 7991 | loss:1.9968256950378418 lr:4.125195658263303e-08 tokens_per_second_per_gpu:2094.681581457806 
Step 7992 | loss:2.0456020832061768 lr:4.012958210126705e-08 tokens_per_second_per_gpu:2152.187206075683 
Step 7993 | loss:2.1317667961120605 lr:3.902268453385149e-08 tokens_per_second_per_gpu:2063.103393533639 
Step 7994 | loss:2.0602145195007324 lr:3.7931264051749295e-08 tokens_per_second_per_gpu:2194.321001989677 
Step 7995 | loss:2.0769970417022705 lr:3.6855320823958596e-08 tokens_per_second_per_gpu:2151.2267695646337 
Step 7996 | loss:2.063485622406006 lr:3.579485501706836e-08 tokens_per_second_per_gpu:2177.687874290642 
Step 7997 | loss:1.9999810457229614 lr:3.474986679526948e-08 tokens_per_second_per_gpu:2162.937611701796 
Step 7998 | loss:2.069387435913086 lr:3.372035632035475e-08 tokens_per_second_per_gpu:2200.7118051303446 
Step 7999 | loss:2.047567367553711 lr:3.270632375173e-08 tokens_per_second_per_gpu:2191.0874430664753 
Step 8000 | loss:2.0791544914245605 lr:3.170776924639185e-08 tokens_per_second_per_gpu:2189.857175066357 
Step 8001 | loss:2.1039576530456543 lr:3.072469295896108e-08 tokens_per_second_per_gpu:2122.9120054625523 
Step 8002 | loss:2.014026165008545 lr:2.975709504163815e-08 tokens_per_second_per_gpu:2207.141752970812 
Step 8003 | loss:2.059049606323242 lr:2.8804975644247665e-08 tokens_per_second_per_gpu:2155.050992884449 
Step 8004 | loss:2.1022090911865234 lr:2.7868334914193937e-08 tokens_per_second_per_gpu:2193.3315193171834 
Step 8005 | loss:2.0402581691741943 lr:2.69471729965054e-08 tokens_per_second_per_gpu:2195.3873271481225 
Step 8006 | loss:2.0254359245300293 lr:2.60414900338124e-08 tokens_per_second_per_gpu:2169.288768717042 
Step 8007 | loss:2.05985164642334 lr:2.5151286166325004e-08 tokens_per_second_per_gpu:2189.1215784275737 
Step 8008 | loss:2.0092244148254395 lr:2.4276561531888508e-08 tokens_per_second_per_gpu:2162.381745766766 
Step 8009 | loss:2.060403823852539 lr:2.3417316265939016e-08 tokens_per_second_per_gpu:2170.6053284491686 
Step 8010 | loss:2.127223014831543 lr:2.257355050151455e-08 tokens_per_second_per_gpu:2191.6636875880968 
Step 8011 | loss:2.0544440746307373 lr:2.1745264369243958e-08 tokens_per_second_per_gpu:2186.2483829093944 
Step 8012 | loss:2.0266549587249756 lr:2.0932457997391296e-08 tokens_per_second_per_gpu:2172.4513623280777 
Step 8013 | loss:2.055058717727661 lr:2.013513151178925e-08 tokens_per_second_per_gpu:2176.992852988607 
Step 8014 | loss:2.017575263977051 lr:1.9353285035883518e-08 tokens_per_second_per_gpu:2150.9435434011143 
Step 8015 | loss:2.0031840801239014 lr:1.8586918690755018e-08 tokens_per_second_per_gpu:2197.008522294554 
Step 8016 | loss:2.099419116973877 lr:1.7836032595031082e-08 tokens_per_second_per_gpu:2102.0490421340846 
Step 8017 | loss:2.079279661178589 lr:1.7100626864996473e-08 tokens_per_second_per_gpu:2199.3758919852544 
Step 8018 | loss:2.0771656036376953 lr:1.6380701614493455e-08 tokens_per_second_per_gpu:2138.1454645781937 
Step 8019 | loss:2.016995668411255 lr:1.5676256955010626e-08 tokens_per_second_per_gpu:2150.567118140067 
Step 8020 | loss:2.0791993141174316 lr:1.4987292995594093e-08 tokens_per_second_per_gpu:2180.920489612212 
Step 8021 | loss:2.0486607551574707 lr:1.431380984294739e-08 tokens_per_second_per_gpu:2191.9677285422845 
Step 8022 | loss:2.066812515258789 lr:1.3655807601320458e-08 tokens_per_second_per_gpu:2190.6268267319283 
Step 8023 | loss:2.062837600708008 lr:1.3013286372598465e-08 tokens_per_second_per_gpu:2169.762889429888 
Step 8024 | loss:2.048008441925049 lr:1.2386246256268496e-08 tokens_per_second_per_gpu:2176.833568830603 
Step 8025 | loss:2.1112256050109863 lr:1.1774687349408453e-08 tokens_per_second_per_gpu:2191.5902091628636 
Step 8026 | loss:1.9898662567138672 lr:1.1178609746720359e-08 tokens_per_second_per_gpu:2193.7768846080294 
Step 8027 | loss:2.0780739784240723 lr:1.0598013540497053e-08 tokens_per_second_per_gpu:2178.727840652712 
Step 8028 | loss:2.1028425693511963 lr:1.0032898820611091e-08 tokens_per_second_per_gpu:2184.9482232222927 
Step 8029 | loss:2.0602097511291504 lr:9.483265674581353e-09 tokens_per_second_per_gpu:2155.9962559189175 
Step 8030 | loss:2.1177501678466797 lr:8.949114187495333e-09 tokens_per_second_per_gpu:2134.050857588484 
Step 8031 | loss:2.0651564598083496 lr:8.430444442053542e-09 tokens_per_second_per_gpu:2154.677516611577 
Step 8032 | loss:2.056551456451416 lr:7.927256518580617e-09 tokens_per_second_per_gpu:2194.9905590604913 
Step 8033 | loss:2.05711030960083 lr:7.4395504949698044e-09 tokens_per_second_per_gpu:2194.543479930459 
Step 8034 | loss:2.04400634765625 lr:6.967326446738476e-09 tokens_per_second_per_gpu:2162.5344255828513 
Step 8035 | loss:2.0319573879241943 lr:6.510584447005918e-09 tokens_per_second_per_gpu:2141.6617622205217 
Step 8036 | loss:2.0827980041503906 lr:6.069324566471135e-09 tokens_per_second_per_gpu:2200.9799323948523 
Step 8037 | loss:2.1004562377929688 lr:5.643546873490557e-09 tokens_per_second_per_gpu:2175.663872533589 
Step 8038 | loss:2.0509262084960938 lr:5.233251433944819e-09 tokens_per_second_per_gpu:2193.615559190121 
Step 8039 | loss:2.065110683441162 lr:4.838438311394189e-09 tokens_per_second_per_gpu:2176.651361146048 
Step 8040 | loss:2.072147846221924 lr:4.459107566956444e-09 tokens_per_second_per_gpu:2174.466396723606 
Step 8041 | loss:2.130557060241699 lr:4.095259259362383e-09 tokens_per_second_per_gpu:2142.365196788571 
Step 8042 | loss:2.0399508476257324 lr:3.746893444955823e-09 tokens_per_second_per_gpu:2172.0610936458083 
Step 8043 | loss:2.150731086730957 lr:3.4140101776602984e-09 tokens_per_second_per_gpu:2186.2773757305945 
Step 8044 | loss:2.085972785949707 lr:3.0966095090234626e-09 tokens_per_second_per_gpu:2186.1972704992586 
Step 8045 | loss:2.079998731613159 lr:2.794691488183787e-09 tokens_per_second_per_gpu:2172.189890779657 
Step 8046 | loss:2.065028429031372 lr:2.5082561618927634e-09 tokens_per_second_per_gpu:2199.6439200468026 
Step 8047 | loss:2.0687308311462402 lr:2.2373035745038017e-09 tokens_per_second_per_gpu:2192.6759712838657 
Step 8048 | loss:2.1168365478515625 lr:1.98183376797223e-09 tokens_per_second_per_gpu:2199.415398774891 
Step 8049 | loss:2.0693745613098145 lr:1.7418467818330898e-09 tokens_per_second_per_gpu:2193.2837382182897 
Step 8050 | loss:2.0360636711120605 lr:1.5173426532677504e-09 tokens_per_second_per_gpu:2162.8928326000537 
Step 8051 | loss:2.052788734436035 lr:1.3083214170150904e-09 tokens_per_second_per_gpu:2190.8277779873065 
Step 8052 | loss:2.042693614959717 lr:1.114783105449213e-09 tokens_per_second_per_gpu:2162.115269656331 
Step 8053 | loss:2.156027317047119 lr:9.36727748535038e-10 tokens_per_second_per_gpu:2120.5889304986276 
Step 8054 | loss:2.1206789016723633 lr:7.741553738394025e-10 tokens_per_second_per_gpu:2159.9999379030664 
Step 8055 | loss:2.0961055755615234 lr:6.27066006531063e-10 tokens_per_second_per_gpu:2158.940045895312 
Step 8056 | loss:2.062976360321045 lr:4.954596693917956e-10 tokens_per_second_per_gpu:2154.5493452956744 
Step 8057 | loss:2.0445330142974854 lr:3.7933638279419316e-10 tokens_per_second_per_gpu:2192.371009392583 
Step 8058 | loss:2.014847755432129 lr:2.786961647238684e-10 tokens_per_second_per_gpu:2180.9293078113296 
Step 8059 | loss:2.051575183868408 lr:1.935390307461482e-10 tokens_per_second_per_gpu:2148.895475531725 
Step 8060 | loss:2.1057357788085938 lr:1.2386499406158437e-10 tokens_per_second_per_gpu:2188.2303899500203 
Step 8061 | loss:2.0598440170288086 lr:6.967406545044242e-11 tokens_per_second_per_gpu:2113.1653195769113 
Step 8062 | loss:2.0824642181396484 lr:3.096625330600844e-11 tokens_per_second_per_gpu:2154.303988052214 
Step 8063 | loss:2.0345826148986816 lr:7.74156362348677e-12 tokens_per_second_per_gpu:2194.4449767549086 
Step 8064 | loss:2.1164469718933105 lr:0.0 tokens_per_second_per_gpu:2093.390477675745