Step 1 | loss:23.100542068481445 lr:4.000000000000001e-06 tokens_per_second_per_gpu:332.15099680006404 mfu:4.880864260492929 
Step 2 | loss:23.232769012451172 lr:8.000000000000001e-06 tokens_per_second_per_gpu:827.3494475256628 mfu:12.157664400439335 
Step 3 | loss:15.345669746398926 lr:1.2e-05 tokens_per_second_per_gpu:861.319902898516 mfu:12.656850563176743 
Step 4 | loss:13.020537376403809 lr:1.6000000000000003e-05 tokens_per_second_per_gpu:867.9803298095268 mfu:12.754723638924718 
Step 5 | loss:11.899322509765625 lr:2e-05 tokens_per_second_per_gpu:869.3178914081425 mfu:12.77437872551421 
Step 6 | loss:10.092859268188477 lr:2.4e-05 tokens_per_second_per_gpu:902.439071119817 mfu:13.261085024388832 
Step 7 | loss:8.740328788757324 lr:2.8000000000000003e-05 tokens_per_second_per_gpu:819.8403028468144 mfu:12.047319658912267 
Step 8 | loss:8.281902313232422 lr:3.2000000000000005e-05 tokens_per_second_per_gpu:888.4540382762755 mfu:13.055578951411578 
Step 9 | loss:7.977826118469238 lr:3.6e-05 tokens_per_second_per_gpu:853.8701900136427 mfu:12.547379154928649 
Step 10 | loss:7.483793258666992 lr:4e-05 tokens_per_second_per_gpu:895.9758158866823 mfu:13.166109330268485 
Step 11 | loss:7.130019664764404 lr:4.4000000000000006e-05 tokens_per_second_per_gpu:867.6575928463145 mfu:12.749981111205523 
Step 12 | loss:7.008267879486084 lr:4.8e-05 tokens_per_second_per_gpu:887.539627370896 mfu:13.042141943693794 
Step 13 | loss:6.917208671569824 lr:5.2000000000000004e-05 tokens_per_second_per_gpu:861.0790180351038 mfu:12.653310828742558 
Step 14 | loss:6.67875862121582 lr:5.6000000000000006e-05 tokens_per_second_per_gpu:886.7278471868187 mfu:13.030213065183688 
Step 15 | loss:6.5749616622924805 lr:6e-05 tokens_per_second_per_gpu:872.6600339304338 mfu:12.823490557625748 
Step 16 | loss:6.365464210510254 lr:6.400000000000001e-05 tokens_per_second_per_gpu:844.3830432454779 mfu:12.407968236277515 
Step 17 | loss:6.288224220275879 lr:6.800000000000001e-05 tokens_per_second_per_gpu:876.7753682095018 mfu:12.883964222302948 
Step 18 | loss:6.2326273918151855 lr:7.2e-05 tokens_per_second_per_gpu:831.1815838720722 mfu:12.213976552185741 
Step 19 | loss:6.15156364440918 lr:7.6e-05 tokens_per_second_per_gpu:875.2393224884864 mfu:12.8613924680875 
Step 20 | loss:6.11801815032959 lr:8e-05 tokens_per_second_per_gpu:867.7928066187561 mfu:12.751968039066027 
Step 21 | loss:6.031415939331055 lr:8.4e-05 tokens_per_second_per_gpu:843.9782605427669 mfu:12.402020069793108 
Step 22 | loss:5.994579792022705 lr:8.800000000000001e-05 tokens_per_second_per_gpu:886.0001685309919 mfu:13.019520034668753 
Step 23 | loss:5.97842264175415 lr:9.200000000000001e-05 tokens_per_second_per_gpu:899.1752220401862 mfu:13.21312369210958 
Step 24 | loss:5.9732985496521 lr:9.6e-05 tokens_per_second_per_gpu:883.9183788204717 mfu:12.98892872802259 
Step 25 | loss:5.958714485168457 lr:0.0001 tokens_per_second_per_gpu:894.5781979610273 mfu:13.145571733064585 
Step 26 | loss:5.948930740356445 lr:0.00010400000000000001 tokens_per_second_per_gpu:869.1619411458005 mfu:12.772087080842923 
Step 27 | loss:5.954076766967773 lr:0.00010800000000000001 tokens_per_second_per_gpu:862.5453238222199 mfu:12.674857774499872 
Step 28 | loss:5.931089401245117 lr:0.00011200000000000001 tokens_per_second_per_gpu:892.539327872488 mfu:13.11561111803464 
Step 29 | loss:5.908233642578125 lr:0.000116 tokens_per_second_per_gpu:837.7397233210688 mfu:12.310346542823478 
Step 30 | loss:5.905282020568848 lr:0.00012 tokens_per_second_per_gpu:847.8933230185684 mfu:12.459550797383365 
Step 31 | loss:5.886683464050293 lr:0.000124 tokens_per_second_per_gpu:878.4077067590952 mfu:12.907950972198302 
Step 32 | loss:5.885632514953613 lr:0.00012800000000000002 tokens_per_second_per_gpu:877.7834259506947 mfu:12.898777343590863 
Step 33 | loss:5.899867534637451 lr:0.000132 tokens_per_second_per_gpu:862.7820959350513 mfu:12.678337073236092 
Step 34 | loss:5.877172946929932 lr:0.00013600000000000003 tokens_per_second_per_gpu:879.0837314600358 mfu:12.917884962563585 
Step 35 | loss:5.893932342529297 lr:0.00014 tokens_per_second_per_gpu:889.1779575107109 mfu:13.06621673830031 
Step 36 | loss:5.88293981552124 lr:0.000144 tokens_per_second_per_gpu:894.138275454154 mfu:13.139107197170157 
Step 37 | loss:5.8843607902526855 lr:0.000148 tokens_per_second_per_gpu:887.0121273691543 mfu:13.034390481465126 
Step 38 | loss:5.865139961242676 lr:0.000152 tokens_per_second_per_gpu:854.0898107060915 mfu:12.55060641842918 
Step 39 | loss:5.869900703430176 lr:0.00015600000000000002 tokens_per_second_per_gpu:887.3463199224108 mfu:13.039301345816058 
Step 40 | loss:5.877011775970459 lr:0.00016 tokens_per_second_per_gpu:850.7955511127288 mfu:12.502198212315294 
Step 41 | loss:5.869555473327637 lr:0.000164 tokens_per_second_per_gpu:885.7002870837508 mfu:13.01511336224469 
Step 42 | loss:5.850341796875 lr:0.000168 tokens_per_second_per_gpu:898.2351133515145 mfu:13.19930906278821 
Step 43 | loss:5.842436790466309 lr:0.000172 tokens_per_second_per_gpu:872.498397098176 mfu:12.821115350429785 
Step 44 | loss:5.871784687042236 lr:0.00017600000000000002 tokens_per_second_per_gpu:886.2479798383004 mfu:13.023161551222492 
Step 45 | loss:5.848980903625488 lr:0.00018 tokens_per_second_per_gpu:895.0715955307815 mfu:13.152822069771767 
Step 46 | loss:5.844254493713379 lr:0.00018400000000000003 tokens_per_second_per_gpu:873.438337310627 mfu:12.834927504041096 
Step 47 | loss:5.875574111938477 lr:0.000188 tokens_per_second_per_gpu:902.1575949338912 mfu:13.256948812035713 
Step 48 | loss:5.856260299682617 lr:0.000192 tokens_per_second_per_gpu:901.7271278097389 mfu:13.250623220296312 
Step 49 | loss:5.844776153564453 lr:0.000196 tokens_per_second_per_gpu:860.4698797029142 mfu:12.6443597145086 
Step 50 | loss:5.859039783477783 lr:0.0002 tokens_per_second_per_gpu:878.5538246101502 mfu:12.910098132387207 
Step 51 | loss:5.837793350219727 lr:0.00019999998019747448 tokens_per_second_per_gpu:870.3712551182911 mfu:12.789857605107214 
Step 52 | loss:5.83170747756958 lr:0.00019999992078990572 tokens_per_second_per_gpu:871.301422164388 mfu:12.803526144823552 
Step 53 | loss:5.826205730438232 lr:0.00019999982177731722 tokens_per_second_per_gpu:881.8297694535997 mfu:12.958237208469413 
Step 54 | loss:5.816533088684082 lr:0.00019999968315974827 tokens_per_second_per_gpu:876.0454547485596 mfu:12.873238351963591 
Step 55 | loss:5.819869041442871 lr:0.0001999995049372537 tokens_per_second_per_gpu:884.6851540579559 mfu:13.000196271665459 
Step 56 | loss:5.884873867034912 lr:0.00019999928710990412 tokens_per_second_per_gpu:859.7965622678983 mfu:12.634465506644716 
Step 57 | loss:5.843533515930176 lr:0.00019999902967778583 tokens_per_second_per_gpu:851.6305623847404 mfu:12.514468465043525 
Step 58 | loss:5.847198963165283 lr:0.00019999873264100074 tokens_per_second_per_gpu:852.8547327997261 mfu:12.532457300497336 
Step 59 | loss:5.859317779541016 lr:0.00019999839599966655 tokens_per_second_per_gpu:896.9172065975779 mfu:13.179942798541159 
Step 60 | loss:5.829385757446289 lr:0.00019999801975391653 tokens_per_second_per_gpu:802.9407570509582 mfu:11.798985648512744 
Step 61 | loss:5.817399024963379 lr:0.00019999760390389967 tokens_per_second_per_gpu:869.1808409388851 mfu:12.772364807917315 
Step 62 | loss:5.816955089569092 lr:0.00019999714844978078 tokens_per_second_per_gpu:893.9164176307847 mfu:13.135847059668158 
Step 63 | loss:5.817401885986328 lr:0.00019999665339174013 tokens_per_second_per_gpu:879.5004775041373 mfu:12.924008926941092 
Step 64 | loss:5.795957565307617 lr:0.00019999611872997382 tokens_per_second_per_gpu:867.9449766988466 mfu:12.75420413503619 
Step 65 | loss:5.776983261108398 lr:0.0001999955444646936 tokens_per_second_per_gpu:862.1171725493359 mfu:12.668566213535021 
Step 66 | loss:5.827310562133789 lr:0.00019999493059612698 tokens_per_second_per_gpu:875.1640784750767 mfu:12.8602867787492 
Step 67 | loss:5.829379558563232 lr:0.000199994277124517 tokens_per_second_per_gpu:882.1797436708052 mfu:12.963379979875517 
Step 68 | loss:5.819169044494629 lr:0.0001999935840501225 tokens_per_second_per_gpu:871.7398353289516 mfu:12.809968501362786 
Step 69 | loss:5.818661689758301 lr:0.00019999285137321793 tokens_per_second_per_gpu:882.4625652676805 mfu:12.967535962659198 
Step 70 | loss:5.751194000244141 lr:0.00019999207909409352 tokens_per_second_per_gpu:867.7270876009038 mfu:12.751002316823552 
Step 71 | loss:5.886597156524658 lr:0.00019999126721305513 tokens_per_second_per_gpu:872.9477458662075 mfu:12.827718402546173 
Step 72 | loss:5.955432415008545 lr:0.00019999041573042425 tokens_per_second_per_gpu:892.5912069874882 mfu:13.116373466848012 
Step 73 | loss:6.063299655914307 lr:0.0001999895246465382 tokens_per_second_per_gpu:877.915626364282 mfu:12.900719991001582 
Step 74 | loss:6.044119834899902 lr:0.0001999885939617498 tokens_per_second_per_gpu:893.4924787407606 mfu:13.129617398469225 
Step 75 | loss:6.015655040740967 lr:0.00019998762367642772 tokens_per_second_per_gpu:847.4774607891273 mfu:12.453439820410477 
Step 76 | loss:5.955739974975586 lr:0.0001999866137909562 tokens_per_second_per_gpu:873.2452497247119 mfu:12.832090136981181 
Step 77 | loss:5.925787925720215 lr:0.00019998556430573521 tokens_per_second_per_gpu:870.0296995382912 mfu:12.784838543176182 
Step 78 | loss:5.923828125 lr:0.0001999844752211804 tokens_per_second_per_gpu:827.5471437067383 mfu:12.160569489492035 
Step 79 | loss:5.871138095855713 lr:0.00019998334653772312 tokens_per_second_per_gpu:877.7390136435156 mfu:12.898124717390958 
Step 80 | loss:5.849399089813232 lr:0.0001999821782558104 tokens_per_second_per_gpu:873.5019453351694 mfu:12.835862205838351 
Step 81 | loss:5.81393575668335 lr:0.00019998097037590492 tokens_per_second_per_gpu:858.6927307207293 mfu:12.61824501656615 
Step 82 | loss:5.778236389160156 lr:0.00019997972289848503 tokens_per_second_per_gpu:801.4532243887035 mfu:11.777126779873296 
Step 83 | loss:5.762824535369873 lr:0.0001999784358240448 tokens_per_second_per_gpu:878.2637758737843 mfu:12.905835948847887 
Step 84 | loss:5.734189033508301 lr:0.00019997710915309403 tokens_per_second_per_gpu:885.1163633177823 mfu:13.00653276887714 
Step 85 | loss:5.695340156555176 lr:0.00019997574288615813 tokens_per_second_per_gpu:898.6656787720606 mfu:13.205636098965108 
Step 86 | loss:5.756052017211914 lr:0.00019997433702377817 tokens_per_second_per_gpu:908.6797010179788 mfu:13.352789302642845 
Step 87 | loss:5.554502964019775 lr:0.00019997289156651097 tokens_per_second_per_gpu:879.862970208051 mfu:12.929335653942568 
Step 88 | loss:5.669980049133301 lr:0.000199971406514929 tokens_per_second_per_gpu:892.2308420103919 mfu:13.111078006185878 
Step 89 | loss:5.749878883361816 lr:0.00019996988186962041 tokens_per_second_per_gpu:876.2536963169046 mfu:12.876298402477593 
Step 90 | loss:5.645143508911133 lr:0.00019996831763118909 tokens_per_second_per_gpu:861.0286192596436 mfu:12.652570233096943 
Step 91 | loss:5.5176191329956055 lr:0.00019996671380025446 tokens_per_second_per_gpu:857.9294567055993 mfu:12.607028922388194 
Step 92 | loss:5.420856475830078 lr:0.00019996507037745183 tokens_per_second_per_gpu:879.5835253347133 mfu:12.925229291149162 
Step 93 | loss:5.339001655578613 lr:0.00019996338736343196 tokens_per_second_per_gpu:863.5430882668506 mfu:12.689519638727607 
Step 94 | loss:5.1686906814575195 lr:0.0001999616647588615 tokens_per_second_per_gpu:853.4610126088887 mfu:12.541366409549873 
Step 95 | loss:5.063887596130371 lr:0.00019995990256442263 tokens_per_second_per_gpu:878.6223779057555 mfu:12.91110550353371 
Step 96 | loss:4.940781116485596 lr:0.00019995810078081333 tokens_per_second_per_gpu:885.716639562477 mfu:13.015353657260373 
Step 97 | loss:4.845247268676758 lr:0.00019995625940874714 tokens_per_second_per_gpu:870.022601493497 mfu:12.784734239430326 
Step 98 | loss:4.671420574188232 lr:0.00019995437844895334 tokens_per_second_per_gpu:876.5712077152871 mfu:12.880964142010498 
Step 99 | loss:4.500596523284912 lr:0.00019995245790217694 tokens_per_second_per_gpu:881.5886665180757 mfu:12.954694269527678 
Step 100 | loss:4.381620407104492 lr:0.00019995049776917848 tokens_per_second_per_gpu:873.439406957072 mfu:12.834943222190837 
Step 101 | loss:4.52109956741333 lr:0.0001999484980507344 tokens_per_second_per_gpu:872.9232486216833 mfu:12.82735842251772 
Step 102 | loss:4.687651634216309 lr:0.00019994645874763658 tokens_per_second_per_gpu:868.3832257012674 mfu:12.76064407925951 
Step 103 | loss:4.593243598937988 lr:0.00019994437986069273 tokens_per_second_per_gpu:846.0762207023519 mfu:12.432848996580947 
Step 104 | loss:4.694310665130615 lr:0.0001999422613907262 tokens_per_second_per_gpu:875.9132444524473 mfu:12.871295559331985 
Step 105 | loss:4.515465259552002 lr:0.000199940103338576 tokens_per_second_per_gpu:860.2755929604133 mfu:12.641504726184325 
Step 106 | loss:4.611584663391113 lr:0.0001999379057050968 tokens_per_second_per_gpu:860.6445563274351 mfu:12.646926537736533 
Step 107 | loss:4.365255355834961 lr:0.00019993566849115898 tokens_per_second_per_gpu:870.7383802707823 mfu:12.795252404620644 
Step 108 | loss:4.397634029388428 lr:0.00019993339169764864 tokens_per_second_per_gpu:876.0071931054122 mfu:12.872676108019165 
Step 109 | loss:4.299609184265137 lr:0.0001999310753254675 tokens_per_second_per_gpu:878.7742088062338 mfu:12.913336615356112 
Step 110 | loss:4.253912925720215 lr:0.0001999287193755329 tokens_per_second_per_gpu:881.8846720627156 mfu:12.959043986667352 
Step 111 | loss:4.091870307922363 lr:0.000199926323848778 tokens_per_second_per_gpu:847.7904468387325 mfu:12.458039061232475 
Step 112 | loss:3.9586400985717773 lr:0.00019992388874615148 tokens_per_second_per_gpu:865.3250385517872 mfu:12.71570489044599 
Step 113 | loss:4.148155212402344 lr:0.00019992141406861776 tokens_per_second_per_gpu:876.7407234420128 mfu:12.883455127315791 
Step 114 | loss:4.061575412750244 lr:0.00019991889981715698 tokens_per_second_per_gpu:885.273795308941 mfu:13.008846187131208 
Step 115 | loss:3.960142135620117 lr:0.00019991634599276486 tokens_per_second_per_gpu:805.9633527738551 mfu:11.843401831453443 
Step 116 | loss:3.874739646911621 lr:0.00019991375259645293 tokens_per_second_per_gpu:891.1808308076501 mfu:13.09564839073401 
Step 117 | loss:3.822300672531128 lr:0.00019991111962924826 tokens_per_second_per_gpu:874.6404960840127 mfu:12.852592884693221 
Step 118 | loss:3.9072213172912598 lr:0.00019990844709219356 tokens_per_second_per_gpu:898.7169506054246 mfu:13.206389523947866 
Step 119 | loss:3.71708345413208 lr:0.00019990573498634742 tokens_per_second_per_gpu:861.8565149450119 mfu:12.664735924306846 
Step 120 | loss:3.6412301063537598 lr:0.0001999029833127839 tokens_per_second_per_gpu:885.9839128561491 mfu:13.019281162158556 
Step 121 | loss:3.557239055633545 lr:0.00019990019207259278 tokens_per_second_per_gpu:866.0856314542106 mfu:12.726881586436631 
Step 122 | loss:3.548973560333252 lr:0.00019989736126687963 tokens_per_second_per_gpu:841.1935679821203 mfu:12.361099806037581 
Step 123 | loss:3.473320484161377 lr:0.00019989449089676545 tokens_per_second_per_gpu:888.6268544136669 mfu:13.058118435311238 
Step 124 | loss:3.4649136066436768 lr:0.00019989158096338718 tokens_per_second_per_gpu:906.272944564331 mfu:13.317422702296946 
Step 125 | loss:3.5077953338623047 lr:0.0001998886314678972 tokens_per_second_per_gpu:878.7132578456377 mfu:12.912440958356488 
Step 126 | loss:3.5438055992126465 lr:0.00019988564241146378 tokens_per_second_per_gpu:865.9715425053831 mfu:12.725205081840185 
Step 127 | loss:3.4516847133636475 lr:0.0001998826137952706 tokens_per_second_per_gpu:825.1914373523723 mfu:12.125953055809731 
Step 128 | loss:3.487419843673706 lr:0.00019987954562051725 tokens_per_second_per_gpu:896.5898867696434 mfu:13.175132926930633 
Step 129 | loss:3.4090962409973145 lr:0.00019987643788841884 tokens_per_second_per_gpu:869.39006368415 mfu:12.775439276546592 
Step 130 | loss:3.4108712673187256 lr:0.00019987329060020616 tokens_per_second_per_gpu:886.1254051213504 mfu:13.021360350681277 
Step 131 | loss:3.3988006114959717 lr:0.00019987010375712577 tokens_per_second_per_gpu:885.3119480162059 mfu:13.00940683029388 
Step 132 | loss:3.3397793769836426 lr:0.00019986687736043974 tokens_per_second_per_gpu:874.6417985780416 mfu:12.852612024471865 
Step 133 | loss:3.3401029109954834 lr:0.00019986361141142593 tokens_per_second_per_gpu:890.3410626483785 mfu:13.083308236902841 
Step 134 | loss:3.346322774887085 lr:0.00019986030591137783 tokens_per_second_per_gpu:826.1638943119783 mfu:12.140243033755711 
Step 135 | loss:3.3003907203674316 lr:0.00019985696086160458 tokens_per_second_per_gpu:865.8192420864409 mfu:12.722967070577734 
Step 136 | loss:3.3315224647521973 lr:0.00019985357626343096 tokens_per_second_per_gpu:841.4440224466359 mfu:12.364780163033382 
Step 137 | loss:3.2679100036621094 lr:0.00019985015211819744 tokens_per_second_per_gpu:878.2210888344836 mfu:12.905208674967886 
Step 138 | loss:3.282329559326172 lr:0.0001998466884272602 tokens_per_second_per_gpu:861.5665822883116 mfu:12.660475446525139 
Step 139 | loss:3.227451801300049 lr:0.00019984318519199098 tokens_per_second_per_gpu:821.5530672779656 mfu:12.072488244221919 
Step 140 | loss:3.3009660243988037 lr:0.0001998396424137773 tokens_per_second_per_gpu:870.6816307291181 mfu:12.794418486275143 
Step 141 | loss:3.2272188663482666 lr:0.00019983606009402224 tokens_per_second_per_gpu:890.0756344950642 mfu:13.079407845816494 
Step 142 | loss:3.23952579498291 lr:0.0001998324382341446 tokens_per_second_per_gpu:878.0729775127494 mfu:12.903032221295337 
Step 143 | loss:3.200023889541626 lr:0.00019982877683557879 tokens_per_second_per_gpu:878.5671627177451 mfu:12.91029413207798 
Step 144 | loss:3.2201550006866455 lr:0.00019982507589977496 tokens_per_second_per_gpu:855.4130886811512 mfu:12.57005161124025 
Step 145 | loss:3.2025485038757324 lr:0.00019982133542819882 tokens_per_second_per_gpu:868.827276445336 mfu:12.767169278423292 
Step 146 | loss:3.2547621726989746 lr:0.00019981755542233177 tokens_per_second_per_gpu:880.15644531723 mfu:12.933648187054121 
Step 147 | loss:3.14568829536438 lr:0.0001998137358836709 tokens_per_second_per_gpu:888.4233471614972 mfu:13.055127954224517 
Step 148 | loss:3.135838508605957 lr:0.000199809876813729 tokens_per_second_per_gpu:880.3624759134461 mfu:12.936675747962646 
Step 149 | loss:3.2008354663848877 lr:0.00019980597821403438 tokens_per_second_per_gpu:859.8745205017254 mfu:12.635611080678707 
Step 150 | loss:3.151815176010132 lr:0.00019980204008613112 tokens_per_second_per_gpu:858.4900526423113 mfu:12.615266719951459 
Step 151 | loss:3.133298635482788 lr:0.0001997980624315789 tokens_per_second_per_gpu:900.469369486565 mfu:13.232140820101645 
Step 152 | loss:3.1406197547912598 lr:0.0001997940452519531 tokens_per_second_per_gpu:899.2835376039493 mfu:13.214715358457473 
Step 153 | loss:3.0706706047058105 lr:0.0001997899885488447 tokens_per_second_per_gpu:861.4689074387588 mfu:12.65904014244078 
Step 154 | loss:3.111354351043701 lr:0.00019978589232386035 tokens_per_second_per_gpu:891.4343897946637 mfu:13.09937436780337 
Step 155 | loss:3.1075143814086914 lr:0.0001997817565786224 tokens_per_second_per_gpu:854.2501230261915 mfu:12.552962162296371 
Step 156 | loss:3.093883991241455 lr:0.00019977758131476878 tokens_per_second_per_gpu:872.380834251089 mfu:12.81938779788821 
Step 157 | loss:3.071024179458618 lr:0.00019977336653395313 tokens_per_second_per_gpu:887.9852273014383 mfu:13.04868990771141 
Step 158 | loss:3.1037909984588623 lr:0.0001997691122378447 tokens_per_second_per_gpu:888.0215560157116 mfu:13.049223747816768 
Step 159 | loss:3.0233213901519775 lr:0.0001997648184281284 tokens_per_second_per_gpu:847.5798623549467 mfu:12.454944582243622 
Step 160 | loss:3.101379871368408 lr:0.00019976048510650482 tokens_per_second_per_gpu:845.0532899521065 mfu:12.417817320662667 
Step 161 | loss:3.0275187492370605 lr:0.00019975611227469016 tokens_per_second_per_gpu:862.4977943609165 mfu:12.67415934260826 
Step 162 | loss:3.0025837421417236 lr:0.00019975169993441627 tokens_per_second_per_gpu:900.6757076879142 mfu:13.235172901179954 
Step 163 | loss:3.0217597484588623 lr:0.00019974724808743068 tokens_per_second_per_gpu:861.7562205158563 mfu:12.6632621262466 
Step 164 | loss:3.015925884246826 lr:0.00019974275673549654 tokens_per_second_per_gpu:856.6949505698027 mfu:12.58888820646195 
Step 165 | loss:3.0508809089660645 lr:0.00019973822588039263 tokens_per_second_per_gpu:867.5850052016732 mfu:12.748914456449414 
Step 166 | loss:2.989501953125 lr:0.00019973365552391345 tokens_per_second_per_gpu:855.4397374356503 mfu:12.570443207094767 
Step 167 | loss:3.0300559997558594 lr:0.00019972904566786903 tokens_per_second_per_gpu:866.6137599827919 mfu:12.734642284688128 
Step 168 | loss:2.963494300842285 lr:0.00019972439631408515 tokens_per_second_per_gpu:859.4820290537227 mfu:12.629843530680178 
Step 169 | loss:2.9310860633850098 lr:0.00019971970746440317 tokens_per_second_per_gpu:859.1577379397213 mfu:12.625078165157948 
Step 170 | loss:2.963351249694824 lr:0.00019971497912068013 tokens_per_second_per_gpu:863.1191972587987 mfu:12.683290681140614 
Step 171 | loss:2.9560365676879883 lr:0.00019971021128478865 tokens_per_second_per_gpu:886.7014418277394 mfu:13.029825045955512 
Step 172 | loss:2.9216110706329346 lr:0.0001997054039586171 tokens_per_second_per_gpu:871.4985339137247 mfu:12.806422645818369 
Step 173 | loss:2.966503620147705 lr:0.00019970055714406938 tokens_per_second_per_gpu:890.0819842651854 mfu:13.07950115387923 
Step 174 | loss:2.9313292503356934 lr:0.00019969567084306508 tokens_per_second_per_gpu:865.8037129500575 mfu:12.72273887434319 
Step 175 | loss:2.981842517852783 lr:0.00019969074505753938 tokens_per_second_per_gpu:901.6626125023917 mfu:13.249675186236745 
Step 176 | loss:2.948160171508789 lr:0.00019968577978944323 tokens_per_second_per_gpu:863.8785084843805 mfu:12.694448543255247 
Step 177 | loss:2.9516329765319824 lr:0.00019968077504074305 tokens_per_second_per_gpu:891.0187195602941 mfu:13.09326621214335 
Step 178 | loss:2.8813281059265137 lr:0.00019967573081342103 tokens_per_second_per_gpu:868.9833629368071 mfu:12.769462924942816 
Step 179 | loss:2.919682264328003 lr:0.00019967064710947488 tokens_per_second_per_gpu:855.5977579777737 mfu:12.572765273937572 
Step 180 | loss:2.891373634338379 lr:0.00019966552393091804 tokens_per_second_per_gpu:892.3480436462715 mfu:13.112800250831677 
Step 181 | loss:2.902681827545166 lr:0.00019966036127977955 tokens_per_second_per_gpu:895.8357937961524 mfu:13.164051745543674 
Step 182 | loss:2.883175849914551 lr:0.0001996551591581041 tokens_per_second_per_gpu:827.8921265623688 mfu:12.165638914261951 
Step 183 | loss:2.853330612182617 lr:0.00019964991756795192 tokens_per_second_per_gpu:871.2305574996572 mfu:12.802484808766309 
Step 184 | loss:2.848172903060913 lr:0.000199644636511399 tokens_per_second_per_gpu:883.7457711813613 mfu:12.986392307945762 
Step 185 | loss:2.847189426422119 lr:0.00019963931599053692 tokens_per_second_per_gpu:864.2630791573987 mfu:12.70009969972219 
Step 186 | loss:2.892855167388916 lr:0.00019963395600747284 tokens_per_second_per_gpu:882.9171500988481 mfu:12.974215957231499 
Step 187 | loss:2.844714641571045 lr:0.00019962855656432957 tokens_per_second_per_gpu:856.8549153196548 mfu:12.591238842883376 
Step 188 | loss:2.8281991481781006 lr:0.0001996231176632456 tokens_per_second_per_gpu:887.1566808948559 mfu:13.036514654338673 
Step 189 | loss:2.8296451568603516 lr:0.00019961763930637503 tokens_per_second_per_gpu:822.5952176621963 mfu:12.087802347185496 
Step 190 | loss:2.823481559753418 lr:0.0001996121214958875 tokens_per_second_per_gpu:886.7526390243731 mfu:13.030577374172783 
Step 191 | loss:2.788552761077881 lr:0.00019960656423396834 tokens_per_second_per_gpu:886.5095410599768 mfu:13.027005118850198 
Step 192 | loss:2.848479986190796 lr:0.00019960096752281862 tokens_per_second_per_gpu:861.2819411661901 mfu:12.656292726336387 
Step 193 | loss:2.8353614807128906 lr:0.0001995953313646548 tokens_per_second_per_gpu:898.5307043869522 mfu:13.203652688833259 
Step 194 | loss:2.791628837585449 lr:0.00019958965576170908 tokens_per_second_per_gpu:898.8296939954207 mfu:13.208046255940666 
Step 195 | loss:2.7835068702697754 lr:0.0001995839407162294 tokens_per_second_per_gpu:861.8467064250668 mfu:12.664591790900927 
Step 196 | loss:2.8085906505584717 lr:0.0001995781862304791 tokens_per_second_per_gpu:883.8163404754888 mfu:12.987429303616144 
Step 197 | loss:2.814814567565918 lr:0.0001995723923067373 tokens_per_second_per_gpu:850.0388172654306 mfu:12.491078224040182 
Step 198 | loss:2.792518377304077 lr:0.00019956655894729866 tokens_per_second_per_gpu:901.2148560182379 mfu:13.24309553227826 
Step 199 | loss:2.763641357421875 lr:0.00019956068615447348 tokens_per_second_per_gpu:895.2604135536118 mfu:13.155596696818648 
Step 200 | loss:2.7248239517211914 lr:0.00019955477393058773 tokens_per_second_per_gpu:874.3831690417132 mfu:12.848811537125043 
Step 201 | loss:2.7992467880249023 lr:0.0001995488222779829 tokens_per_second_per_gpu:872.4171093700503 mfu:12.819920850425728 
Step 202 | loss:2.7286455631256104 lr:0.00019954283119901615 tokens_per_second_per_gpu:864.4060530344567 mfu:12.702200660109 
Step 203 | loss:2.745983600616455 lr:0.00019953680069606026 tokens_per_second_per_gpu:869.0780533951009 mfu:12.770854374247948 
Step 204 | loss:2.7217469215393066 lr:0.00019953073077150365 tokens_per_second_per_gpu:876.4070130004927 mfu:12.87855134745946 
Step 205 | loss:2.785653591156006 lr:0.00019952462142775024 tokens_per_second_per_gpu:896.3678880653786 mfu:13.171870719224016 
Step 206 | loss:2.7945711612701416 lr:0.0001995184726672197 tokens_per_second_per_gpu:879.7948057510042 mfu:12.928333996667892 
Step 207 | loss:2.823134183883667 lr:0.0001995122844923472 tokens_per_second_per_gpu:871.2997816765891 mfu:12.803502038322758 
Step 208 | loss:2.8417437076568604 lr:0.00019950605690558364 tokens_per_second_per_gpu:881.3515498369111 mfu:12.951209907457978 
Step 209 | loss:2.8285093307495117 lr:0.00019949978990939542 tokens_per_second_per_gpu:848.8293381467178 mfu:12.47330527299921 
Step 210 | loss:2.7886667251586914 lr:0.00019949348350626456 tokens_per_second_per_gpu:842.3699291854675 mfu:12.378386098748313 
Step 211 | loss:2.808443069458008 lr:0.00019948713769868875 tokens_per_second_per_gpu:862.9365104668236 mfu:12.680606150784222 
Step 212 | loss:2.842609405517578 lr:0.00019948075248918124 tokens_per_second_per_gpu:882.9389632146077 mfu:12.974536494752526 
Step 213 | loss:2.7486634254455566 lr:0.00019947432788027092 tokens_per_second_per_gpu:862.5386847712617 mfu:12.67476021553766 
Step 214 | loss:2.7633602619171143 lr:0.00019946786387450223 tokens_per_second_per_gpu:851.1931350168973 mfu:12.508040594506221 
Step 215 | loss:2.723308563232422 lr:0.00019946136047443522 tokens_per_second_per_gpu:880.9725445400686 mfu:12.945640532608232 
Step 216 | loss:2.712099313735962 lr:0.0001994548176826456 tokens_per_second_per_gpu:862.7341517410131 mfu:12.677632546965105 
Step 217 | loss:2.700279712677002 lr:0.00019944823550172464 tokens_per_second_per_gpu:879.8249977734766 mfu:12.928777659835719 
Step 218 | loss:2.7828102111816406 lr:0.00019944161393427922 tokens_per_second_per_gpu:900.9541386233279 mfu:13.23926436444446 
Step 219 | loss:2.748581886291504 lr:0.00019943495298293181 tokens_per_second_per_gpu:857.4393720683742 mfu:12.599827268280594 
Step 220 | loss:2.711913585662842 lr:0.00019942825265032048 tokens_per_second_per_gpu:850.1166054253786 mfu:12.492221298886978 
Step 221 | loss:2.6641740798950195 lr:0.0001994215129390989 tokens_per_second_per_gpu:839.4147828334511 mfu:12.334961065094824 
Step 222 | loss:2.7180070877075195 lr:0.00019941473385193636 tokens_per_second_per_gpu:896.057860410532 mfu:13.167314951170079 
Step 223 | loss:2.6949546337127686 lr:0.00019940791539151768 tokens_per_second_per_gpu:872.0098427204194 mfu:12.81393618304907 
Step 224 | loss:2.7084522247314453 lr:0.00019940105756054337 tokens_per_second_per_gpu:897.4613564231357 mfu:13.187938925186888 
Step 225 | loss:2.70462703704834 lr:0.0001993941603617294 tokens_per_second_per_gpu:879.3592157186159 mfu:12.921933125251599 
Step 226 | loss:2.678394079208374 lr:0.00019938722379780747 tokens_per_second_per_gpu:864.4827791667742 mfu:12.70332812876236 
Step 227 | loss:2.7020018100738525 lr:0.0001993802478715248 tokens_per_second_per_gpu:870.4847246836796 mfu:12.7915250080405 
Step 228 | loss:2.744690418243408 lr:0.0001993732325856442 tokens_per_second_per_gpu:889.6336594114942 mfu:13.072913147892335 
Step 229 | loss:2.6304311752319336 lr:0.00019936617794294407 tokens_per_second_per_gpu:864.7425789816014 mfu:12.707145813018283 
Step 230 | loss:2.634422540664673 lr:0.00019935908394621844 tokens_per_second_per_gpu:881.0441245895335 mfu:12.946692381040311 
Step 231 | loss:2.6482174396514893 lr:0.00019935195059827683 tokens_per_second_per_gpu:880.7295609108287 mfu:12.942069957408195 
Step 232 | loss:2.682884693145752 lr:0.00019934477790194445 tokens_per_second_per_gpu:878.6309782656058 mfu:12.911231883371268 
Step 233 | loss:2.652756452560425 lr:0.00019933756586006202 tokens_per_second_per_gpu:878.9193141853707 mfu:12.915468897558657 
Step 234 | loss:2.6058883666992188 lr:0.00019933031447548594 tokens_per_second_per_gpu:879.8358819174283 mfu:12.928937599229945 
Step 235 | loss:2.6513447761535645 lr:0.00019932302375108804 tokens_per_second_per_gpu:866.8885807059801 mfu:12.738680696912613 
Step 236 | loss:2.579223155975342 lr:0.00019931569368975588 tokens_per_second_per_gpu:864.8940095492562 mfu:12.709371042063907 
Step 237 | loss:2.6653966903686523 lr:0.0001993083242943925 tokens_per_second_per_gpu:901.8250283505458 mfu:13.252061840849347 
Step 238 | loss:2.655275344848633 lr:0.00019930091556791656 tokens_per_second_per_gpu:882.9476514605611 mfu:12.97466416605133 
Step 239 | loss:2.634225606918335 lr:0.00019929346751326228 tokens_per_second_per_gpu:853.6672588104511 mfu:12.54439713871753 
Step 240 | loss:2.613049268722534 lr:0.00019928598013337946 tokens_per_second_per_gpu:886.715968857767 mfu:13.030038516522684 
Step 241 | loss:2.6563382148742676 lr:0.00019927845343123353 tokens_per_second_per_gpu:875.5143665517331 mfu:12.86543416223051 
Step 242 | loss:2.6390748023986816 lr:0.0001992708874098054 tokens_per_second_per_gpu:890.2737170681618 mfu:13.082318612789868 
Step 243 | loss:2.634441614151001 lr:0.00019926328207209163 tokens_per_second_per_gpu:877.3336515736654 mfu:12.892168037271519 
Step 244 | loss:2.6313130855560303 lr:0.00019925563742110428 tokens_per_second_per_gpu:898.5840774189033 mfu:13.204436990330572 
Step 245 | loss:2.6375410556793213 lr:0.000199247953459871 tokens_per_second_per_gpu:905.0661431471135 mfu:13.299689099316508 
Step 246 | loss:2.6272568702697754 lr:0.00019924023019143508 tokens_per_second_per_gpu:850.752390297071 mfu:12.501563976426715 
Step 247 | loss:2.627944231033325 lr:0.00019923246761885532 tokens_per_second_per_gpu:829.7107705952809 mfu:12.19236337015194 
Step 248 | loss:2.5893988609313965 lr:0.00019922466574520608 tokens_per_second_per_gpu:890.0349877595438 mfu:13.078810553619215 
Step 249 | loss:2.597595453262329 lr:0.00019921682457357728 tokens_per_second_per_gpu:860.3768696337438 mfu:12.642992958042855 
Step 250 | loss:2.585508346557617 lr:0.00019920894410707445 tokens_per_second_per_gpu:878.8661376126539 mfu:12.914687482973818 
Step 251 | loss:2.5778350830078125 lr:0.0001992010243488186 tokens_per_second_per_gpu:853.2835721007003 mfu:12.538758971838941 
Step 252 | loss:2.631514310836792 lr:0.0001991930653019464 tokens_per_second_per_gpu:878.6927004309038 mfu:12.912138873004254 
Step 253 | loss:2.5856356620788574 lr:0.00019918506696961003 tokens_per_second_per_gpu:843.6922993714791 mfu:12.397817951857972 
Step 254 | loss:2.603055238723755 lr:0.00019917702935497725 tokens_per_second_per_gpu:904.0105876953835 mfu:13.284178012705445 
Step 255 | loss:2.6045758724212646 lr:0.00019916895246123128 tokens_per_second_per_gpu:884.6057497220909 mfu:12.99902944757405 
Step 256 | loss:2.551769971847534 lr:0.00019916083629157108 tokens_per_second_per_gpu:883.1460271635979 mfu:12.977579240485639 
Step 257 | loss:2.590336322784424 lr:0.00019915268084921101 tokens_per_second_per_gpu:826.29742095946 mfu:12.14220516979563 
Step 258 | loss:2.6199629306793213 lr:0.00019914448613738106 tokens_per_second_per_gpu:890.829010419283 mfu:13.090478490368703 
Step 259 | loss:2.5671310424804688 lr:0.0001991362521593267 tokens_per_second_per_gpu:866.830721103612 mfu:12.73783046654135 
Step 260 | loss:2.535989999771118 lr:0.00019912797891830908 tokens_per_second_per_gpu:878.6950165756222 mfu:12.912172908090968 
Step 261 | loss:2.5570449829101562 lr:0.00019911966641760476 tokens_per_second_per_gpu:874.6607217919521 mfu:12.85289009570862 
Step 262 | loss:2.665012836456299 lr:0.00019911131466050593 tokens_per_second_per_gpu:869.7158325337905 mfu:12.780226356972996 
Step 263 | loss:2.542912244796753 lr:0.0001991029236503203 tokens_per_second_per_gpu:872.1547688719453 mfu:12.816065831552937 
Step 264 | loss:2.5858187675476074 lr:0.00019909449339037115 tokens_per_second_per_gpu:844.5262849774919 mfu:12.410073132716585 
Step 265 | loss:2.5726318359375 lr:0.00019908602388399728 tokens_per_second_per_gpu:853.5886806262781 mfu:12.543242454689846 
Step 266 | loss:2.564408779144287 lr:0.00019907751513455302 tokens_per_second_per_gpu:884.0159542749371 mfu:12.990362571524459 
Step 267 | loss:2.6135458946228027 lr:0.0001990689671454083 tokens_per_second_per_gpu:854.8651005681718 mfu:12.561999082054475 
Step 268 | loss:2.5442936420440674 lr:0.00019906037991994854 tokens_per_second_per_gpu:850.7230437144262 mfu:12.501132736756269 
Step 269 | loss:2.5882554054260254 lr:0.00019905175346157474 tokens_per_second_per_gpu:859.4191426470984 mfu:12.628919432852621 
Step 270 | loss:2.5741164684295654 lr:0.00019904308777370338 tokens_per_second_per_gpu:856.6504196330777 mfu:12.588233837034668 
Step 271 | loss:2.609436511993408 lr:0.0001990343828597665 tokens_per_second_per_gpu:885.4765044941581 mfu:13.01182494085145 
Step 272 | loss:2.5666704177856445 lr:0.00019902563872321172 tokens_per_second_per_gpu:864.5538117006278 mfu:12.704371931608529 
Step 273 | loss:2.551685333251953 lr:0.0001990168553675021 tokens_per_second_per_gpu:836.2476635454524 mfu:12.288421149543057 
Step 274 | loss:2.6206769943237305 lr:0.0001990080327961164 tokens_per_second_per_gpu:900.8786658497955 mfu:13.238155313541336 
Step 275 | loss:2.58001446723938 lr:0.00019899917101254874 tokens_per_second_per_gpu:858.9925997682194 mfu:12.622651506779404 
Step 276 | loss:2.531311511993408 lr:0.0001989902700203088 tokens_per_second_per_gpu:894.5663674080565 mfu:13.145397886459477 
Step 277 | loss:2.5607545375823975 lr:0.00019898132982292192 tokens_per_second_per_gpu:862.2644095338381 mfu:12.670729819071065 
Step 278 | loss:2.5270237922668457 lr:0.00019897235042392873 tokens_per_second_per_gpu:844.8784749755856 mfu:12.415248464391514 
Step 279 | loss:2.5597434043884277 lr:0.00019896333182688566 tokens_per_second_per_gpu:889.1713714443586 mfu:13.066119957931786 
Step 280 | loss:2.574949264526367 lr:0.00019895427403536443 tokens_per_second_per_gpu:875.7706274161211 mfu:12.869199842618057 
Step 281 | loss:2.5796847343444824 lr:0.00019894517705295245 tokens_per_second_per_gpu:861.2035244555341 mfu:12.655140415116028 
Step 282 | loss:2.493830680847168 lr:0.00019893604088325257 tokens_per_second_per_gpu:888.7777460736366 mfu:13.060335745261979 
Step 283 | loss:2.5784049034118652 lr:0.00019892686552988313 tokens_per_second_per_gpu:868.9716031323803 mfu:12.769290117967406 
Step 284 | loss:2.531250238418579 lr:0.0001989176509964781 tokens_per_second_per_gpu:903.8648672679807 mfu:13.282036692543873 
Step 285 | loss:2.5546789169311523 lr:0.00019890839728668687 tokens_per_second_per_gpu:852.0214659507112 mfu:12.520212681568017 
Step 286 | loss:2.5320539474487305 lr:0.00019889910440417437 tokens_per_second_per_gpu:888.1869052024065 mfu:13.05165350700345 
Step 287 | loss:2.5115110874176025 lr:0.00019888977235262104 tokens_per_second_per_gpu:852.1404709440205 mfu:12.52196142603743 
Step 288 | loss:2.5551185607910156 lr:0.0001988804011357229 tokens_per_second_per_gpu:852.2194346109034 mfu:12.523121774623702 
Step 289 | loss:2.5099287033081055 lr:0.00019887099075719135 tokens_per_second_per_gpu:844.0813159012257 mfu:12.403534438922813 
Step 290 | loss:2.5442240238189697 lr:0.00019886154122075343 tokens_per_second_per_gpu:871.6386476884181 mfu:12.80848157781584 
Step 291 | loss:2.596917152404785 lr:0.0001988520525301516 tokens_per_second_per_gpu:826.0202334944238 mfu:12.13813197897403 
Step 292 | loss:2.5564746856689453 lr:0.00019884252468914388 tokens_per_second_per_gpu:898.5519402022514 mfu:13.203964743088507 
Step 293 | loss:2.5128073692321777 lr:0.0001988329577015038 tokens_per_second_per_gpu:879.8663509374309 mfu:12.929385332797557 
Step 294 | loss:2.4900424480438232 lr:0.00019882335157102033 tokens_per_second_per_gpu:869.1373073632668 mfu:12.771725094427323 
Step 295 | loss:2.5022215843200684 lr:0.00019881370630149797 tokens_per_second_per_gpu:897.9047480934937 mfu:13.19445443945028 
Step 296 | loss:2.545529842376709 lr:0.00019880402189675678 tokens_per_second_per_gpu:897.0122310170638 mfu:13.181339155310853 
Step 297 | loss:2.5089898109436035 lr:0.00019879429836063226 tokens_per_second_per_gpu:902.2081311339881 mfu:13.257691427097207 
Step 298 | loss:2.4708762168884277 lr:0.00019878453569697539 tokens_per_second_per_gpu:845.4293881679021 mfu:12.423343976784723 
Step 299 | loss:2.5059127807617188 lr:0.0001987747339096527 tokens_per_second_per_gpu:867.5682659461434 mfu:12.748668477858804 
Step 300 | loss:2.5231175422668457 lr:0.00019876489300254621 tokens_per_second_per_gpu:890.7724855144215 mfu:13.089647872997013 
Step 301 | loss:2.467526912689209 lr:0.00019875501297955342 tokens_per_second_per_gpu:857.33704248773 mfu:12.598323564249087 
Step 302 | loss:2.502687454223633 lr:0.00019874509384458725 tokens_per_second_per_gpu:867.5991005644757 mfu:12.749121583789702 
Step 303 | loss:2.4711790084838867 lr:0.0001987351356015763 tokens_per_second_per_gpu:883.7345578937784 mfu:12.986227531879656 
Step 304 | loss:2.474004030227661 lr:0.00019872513825446443 tokens_per_second_per_gpu:861.4080412275551 mfu:12.65814573080933 
Step 305 | loss:2.5061254501342773 lr:0.0001987151018072111 tokens_per_second_per_gpu:895.6716349189454 mfu:13.161639477615768 
Step 306 | loss:2.5361504554748535 lr:0.00019870502626379127 tokens_per_second_per_gpu:872.9938594821898 mfu:12.8283960289942 
Step 307 | loss:2.528928756713867 lr:0.00019869491162819545 tokens_per_second_per_gpu:891.1888357770029 mfu:13.095766021477848 
Step 308 | loss:2.4725427627563477 lr:0.0001986847579044294 tokens_per_second_per_gpu:870.0639899828051 mfu:12.785342431488175 
Step 309 | loss:2.4738407135009766 lr:0.00019867456509651461 tokens_per_second_per_gpu:857.1337725699123 mfu:12.595336570723045 
Step 310 | loss:2.486595630645752 lr:0.0001986643332084879 tokens_per_second_per_gpu:902.898489895776 mfu:13.267836052402538 
Step 311 | loss:2.4759771823883057 lr:0.00019865406224440165 tokens_per_second_per_gpu:873.5563481816004 mfu:12.836661640166028 
Step 312 | loss:2.4899659156799316 lr:0.00019864375220832363 tokens_per_second_per_gpu:841.8493565321176 mfu:12.370736431930498 
Step 313 | loss:2.514042854309082 lr:0.0001986334031043372 tokens_per_second_per_gpu:896.9999924686033 mfu:13.181159313328271 
Step 314 | loss:2.4944186210632324 lr:0.00019862301493654108 tokens_per_second_per_gpu:899.1173575201948 mfu:13.212273389475243 
Step 315 | loss:2.5667998790740967 lr:0.00019861258770904948 tokens_per_second_per_gpu:882.2012079169596 mfu:12.963695390857096 
Step 316 | loss:2.4175968170166016 lr:0.0001986021214259922 tokens_per_second_per_gpu:873.9049552438942 mfu:12.841784321620239 
Step 317 | loss:2.4899635314941406 lr:0.00019859161609151436 tokens_per_second_per_gpu:870.3731336503672 mfu:12.789885209600834 
Step 318 | loss:2.463643789291382 lr:0.0001985810717097766 tokens_per_second_per_gpu:849.4304952412378 mfu:12.482139105219654 
Step 319 | loss:2.448676347732544 lr:0.00019857048828495505 tokens_per_second_per_gpu:871.5018879792943 mfu:12.806471932856264 
Step 320 | loss:2.5284862518310547 lr:0.00019855986582124126 tokens_per_second_per_gpu:858.8638220990825 mfu:12.620759155623169 
Step 321 | loss:2.5136566162109375 lr:0.00019854920432284227 tokens_per_second_per_gpu:880.7955117072448 mfu:12.943039085570627 
Step 322 | loss:2.407918691635132 lr:0.0001985385037939806 tokens_per_second_per_gpu:892.5133219393497 mfu:13.115228968256861 
Step 323 | loss:2.4148385524749756 lr:0.0001985277642388941 tokens_per_second_per_gpu:869.9017029267768 mfu:12.782957669439167 
Step 324 | loss:2.482599973678589 lr:0.00019851698566183634 tokens_per_second_per_gpu:896.5666259563891 mfu:13.174791115907404 
Step 325 | loss:2.4439330101013184 lr:0.00019850616806707603 tokens_per_second_per_gpu:868.2367350043519 mfu:12.758491440206917 
Step 326 | loss:2.458939552307129 lr:0.00019849531145889758 tokens_per_second_per_gpu:882.5717596443424 mfu:12.969140542912248 
Step 327 | loss:2.4041171073913574 lr:0.0001984844158416007 tokens_per_second_per_gpu:876.5833890891291 mfu:12.881143143828353 
Step 328 | loss:2.4712727069854736 lr:0.00019847348121950062 tokens_per_second_per_gpu:874.4304647641753 mfu:12.849506534290981 
Step 329 | loss:2.4752049446105957 lr:0.000198462507596928 tokens_per_second_per_gpu:852.2017557025389 mfu:12.522861988102415 
Step 330 | loss:2.470505714416504 lr:0.00019845149497822896 tokens_per_second_per_gpu:885.6000224267469 mfu:13.013640001677734 
Step 331 | loss:2.5035712718963623 lr:0.00019844044336776509 tokens_per_second_per_gpu:837.6636118795076 mfu:12.309228106875642 
Step 332 | loss:2.5219788551330566 lr:0.0001984293527699133 tokens_per_second_per_gpu:875.8759126532714 mfu:12.870746979179787 
Step 333 | loss:2.4784467220306396 lr:0.00019841822318906606 tokens_per_second_per_gpu:886.6462036097136 mfu:13.029013336080267 
Step 334 | loss:2.4790918827056885 lr:0.00019840705462963133 tokens_per_second_per_gpu:887.1728994203124 mfu:13.036752980949226 
Step 335 | loss:2.469571590423584 lr:0.00019839584709603226 tokens_per_second_per_gpu:899.5964068717769 mfu:13.219312883204527 
Step 336 | loss:2.4717838764190674 lr:0.00019838460059270775 tokens_per_second_per_gpu:890.4718660694648 mfu:13.085230355906791 
Step 337 | loss:2.4630138874053955 lr:0.00019837331512411192 tokens_per_second_per_gpu:885.6358617643602 mfu:13.014166650532506 
Step 338 | loss:2.4534614086151123 lr:0.00019836199069471437 tokens_per_second_per_gpu:882.7362555131048 mfu:12.971557762835042 
Step 339 | loss:2.4205760955810547 lr:0.00019835062730900015 tokens_per_second_per_gpu:868.6199462218066 mfu:12.764122619861693 
Step 340 | loss:2.430479049682617 lr:0.0001983392249714698 tokens_per_second_per_gpu:822.9758535186554 mfu:12.093395682644223 
Step 341 | loss:2.413313865661621 lr:0.00019832778368663917 tokens_per_second_per_gpu:884.4373630660943 mfu:12.996555053641426 
Step 342 | loss:2.448932647705078 lr:0.00019831630345903953 tokens_per_second_per_gpu:868.7848524977678 mfu:12.76654587060134 
Step 343 | loss:2.3813014030456543 lr:0.00019830478429321775 tokens_per_second_per_gpu:849.3358564166707 mfu:12.480748414657425 
Step 344 | loss:2.436352252960205 lr:0.00019829322619373588 tokens_per_second_per_gpu:855.1795089395029 mfu:12.566619223488985 
Step 345 | loss:2.4214649200439453 lr:0.00019828162916517164 tokens_per_second_per_gpu:898.236042496685 mfu:13.199322716311753 
Step 346 | loss:2.4567928314208984 lr:0.00019826999321211793 tokens_per_second_per_gpu:885.0072103567888 mfu:13.004928797215538 
Step 347 | loss:2.4680771827697754 lr:0.00019825831833918323 tokens_per_second_per_gpu:886.7993796809643 mfu:13.0312642148039 
Step 348 | loss:2.463165283203125 lr:0.00019824660455099137 tokens_per_second_per_gpu:877.6509577794765 mfu:12.896830761558052 
Step 349 | loss:2.4400925636291504 lr:0.00019823485185218158 tokens_per_second_per_gpu:859.6682255853767 mfu:12.632579635661145 
Step 350 | loss:2.4079315662384033 lr:0.00019822306024740852 tokens_per_second_per_gpu:850.5663090794774 mfu:12.49882956595301 
Step 351 | loss:2.4598617553710938 lr:0.00019821122974134233 tokens_per_second_per_gpu:888.7793842799847 mfu:13.0603598182375 
Step 352 | loss:2.4795515537261963 lr:0.0001981993603386684 tokens_per_second_per_gpu:885.0318841150723 mfu:13.005291371063391 
Step 353 | loss:2.5268452167510986 lr:0.0001981874520440877 tokens_per_second_per_gpu:844.6147508552057 mfu:12.411373113583618 
Step 354 | loss:2.487504005432129 lr:0.00019817550486231643 tokens_per_second_per_gpu:879.3153345897824 mfu:12.921288304566136 
Step 355 | loss:2.4738574028015137 lr:0.0001981635187980863 tokens_per_second_per_gpu:874.8035777116469 mfu:12.854989322745586 
Step 356 | loss:2.499979019165039 lr:0.00019815149385614444 tokens_per_second_per_gpu:871.442280365257 mfu:12.805596015951568 
Step 357 | loss:2.4794468879699707 lr:0.0001981394300412533 tokens_per_second_per_gpu:843.3324833450304 mfu:12.392530557869197 
Step 358 | loss:2.5082290172576904 lr:0.00019812732735819078 tokens_per_second_per_gpu:872.5188062676796 mfu:12.821415257360597 
Step 359 | loss:2.485642671585083 lr:0.00019811518581175014 tokens_per_second_per_gpu:866.6457097150625 mfu:12.735111776900629 
Step 360 | loss:2.4108834266662598 lr:0.00019810300540674 tokens_per_second_per_gpu:893.9521518306094 mfu:13.136372163553084 
Step 361 | loss:2.462923049926758 lr:0.00019809078614798452 tokens_per_second_per_gpu:861.7661022409627 mfu:12.663407335381509 
Step 362 | loss:2.4719080924987793 lr:0.00019807852804032305 tokens_per_second_per_gpu:887.973428262804 mfu:13.0485165242005 
Step 363 | loss:2.431520462036133 lr:0.00019806623108861046 tokens_per_second_per_gpu:883.4246279641897 mfu:12.981673199870539 
Step 364 | loss:2.4482665061950684 lr:0.000198053895297717 tokens_per_second_per_gpu:886.156580418955 mfu:13.021818462797015 
Step 365 | loss:2.420222520828247 lr:0.00019804152067252816 tokens_per_second_per_gpu:866.4439910648836 mfu:12.732147578810547 
Step 366 | loss:2.4257278442382812 lr:0.00019802910721794504 tokens_per_second_per_gpu:864.3267979090951 mfu:12.701036028623426 
Step 367 | loss:2.418271064758301 lr:0.00019801665493888388 tokens_per_second_per_gpu:898.926938272351 mfu:13.209475232883015 
Step 368 | loss:2.4394190311431885 lr:0.0001980041638402765 tokens_per_second_per_gpu:836.8539852172931 mfu:12.297330873755719 
Step 369 | loss:2.438833713531494 lr:0.00019799163392707 tokens_per_second_per_gpu:878.8574679267527 mfu:12.914560084409691 
Step 370 | loss:2.4166040420532227 lr:0.00019797906520422677 tokens_per_second_per_gpu:889.2678562901292 mfu:13.067537775249624 
Step 371 | loss:2.480531930923462 lr:0.00019796645767672477 tokens_per_second_per_gpu:875.5822255499706 mfu:12.866431330875017 
Step 372 | loss:2.451152801513672 lr:0.00019795381134955715 tokens_per_second_per_gpu:902.9300727022061 mfu:13.268300152744358 
Step 373 | loss:2.447972297668457 lr:0.0001979411262277325 tokens_per_second_per_gpu:867.655722095463 mfu:12.74995362105478 
Step 374 | loss:2.4462711811065674 lr:0.00019792840231627482 tokens_per_second_per_gpu:871.9108670744616 mfu:12.812481764132164 
Step 375 | loss:2.460538625717163 lr:0.00019791563962022338 tokens_per_second_per_gpu:846.8199751808293 mfu:12.443778256729358 
Step 376 | loss:2.407651901245117 lr:0.00019790283814463284 tokens_per_second_per_gpu:864.4687136184976 mfu:12.703121439538036 
Step 377 | loss:2.4385857582092285 lr:0.00019788999789457326 tokens_per_second_per_gpu:899.2774871215047 mfu:13.214626448341873 
Step 378 | loss:2.425808906555176 lr:0.00019787711887513 tokens_per_second_per_gpu:843.0890983591395 mfu:12.38895408484753 
Step 379 | loss:2.3697071075439453 lr:0.00019786420109140385 tokens_per_second_per_gpu:867.6900682902084 mfu:12.75045832860054 
Step 380 | loss:2.392979860305786 lr:0.00019785124454851084 tokens_per_second_per_gpu:900.2798478935501 mfu:13.229355854291365 
Step 381 | loss:2.4017128944396973 lr:0.00019783824925158244 tokens_per_second_per_gpu:845.9693562303651 mfu:12.431278653613255 
Step 382 | loss:2.3731722831726074 lr:0.00019782521520576548 tokens_per_second_per_gpu:876.9924253838278 mfu:12.88715381563507 
Step 383 | loss:2.430168390274048 lr:0.00019781214241622208 tokens_per_second_per_gpu:885.9945168150944 mfu:13.019436984313943 
Step 384 | loss:2.400266170501709 lr:0.0001977990308881297 tokens_per_second_per_gpu:885.2933564770337 mfu:13.009133632922904 
Step 385 | loss:2.4000439643859863 lr:0.0001977858806266812 tokens_per_second_per_gpu:879.4931097276473 mfu:12.92390065956482 
Step 386 | loss:2.390014410018921 lr:0.00019777269163708468 tokens_per_second_per_gpu:894.8192222488275 mfu:13.149113516300426 
Step 387 | loss:2.4490678310394287 lr:0.00019775946392456377 tokens_per_second_per_gpu:839.485675193469 mfu:12.336002808126418 
Step 388 | loss:2.37144136428833 lr:0.0001977461974943572 tokens_per_second_per_gpu:884.4034718101751 mfu:12.996057031292095 
Step 389 | loss:2.386988401412964 lr:0.00019773289235171918 tokens_per_second_per_gpu:859.9888381214945 mfu:12.637290945529484 
Step 390 | loss:2.41227126121521 lr:0.00019771954850191924 tokens_per_second_per_gpu:857.6580320329346 mfu:12.603040414158539 
Step 391 | loss:2.3511626720428467 lr:0.00019770616595024223 tokens_per_second_per_gpu:886.3246323979971 mfu:13.024287938747152 
Step 392 | loss:2.4103870391845703 lr:0.00019769274470198827 tokens_per_second_per_gpu:863.3075059014515 mfu:12.686057822990916 
Step 393 | loss:2.3631138801574707 lr:0.00019767928476247285 tokens_per_second_per_gpu:855.6099871851321 mfu:12.572944978655322 
Step 394 | loss:2.408336877822876 lr:0.00019766578613702684 tokens_per_second_per_gpu:880.8254090473104 mfu:12.94347841846445 
Step 395 | loss:2.373701333999634 lr:0.00019765224883099635 tokens_per_second_per_gpu:881.0584730103373 mfu:12.946903226995827 
Step 396 | loss:2.37391996383667 lr:0.0001976386728497428 tokens_per_second_per_gpu:886.9714134017045 mfu:13.033792201313798 
Step 397 | loss:2.393702745437622 lr:0.00019762505819864303 tokens_per_second_per_gpu:883.5250702572245 mfu:12.983149170748357 
Step 398 | loss:2.3611702919006348 lr:0.0001976114048830891 tokens_per_second_per_gpu:882.9470872775584 mfu:12.974655875542853 
Step 399 | loss:2.358593225479126 lr:0.00019759771290848839 tokens_per_second_per_gpu:878.3677691345858 mfu:12.907364100185287 
Step 400 | loss:2.3314199447631836 lr:0.00019758398228026365 tokens_per_second_per_gpu:866.8668595850827 mfu:12.738361511229876 
Step 401 | loss:2.4333767890930176 lr:0.00019757021300385286 tokens_per_second_per_gpu:864.9443488873893 mfu:12.710110764294935 
Step 402 | loss:2.3895492553710938 lr:0.00019755640508470942 tokens_per_second_per_gpu:897.2954841501362 mfu:13.185501479395999 
Step 403 | loss:2.3873395919799805 lr:0.00019754255852830186 tokens_per_second_per_gpu:877.6661365657612 mfu:12.89705380949772 
Step 404 | loss:2.3747901916503906 lr:0.00019752867334011423 tokens_per_second_per_gpu:842.4146877141324 mfu:12.379043812574306 
Step 405 | loss:2.405444860458374 lr:0.00019751474952564566 tokens_per_second_per_gpu:841.7739873778677 mfu:12.369628903683209 
Step 406 | loss:2.398433208465576 lr:0.00019750078709041078 tokens_per_second_per_gpu:891.2307412453447 mfu:13.096381810395297 
Step 407 | loss:2.338675022125244 lr:0.00019748678603993933 tokens_per_second_per_gpu:879.2152936109875 mfu:12.919818230886728 
Step 408 | loss:2.363835096359253 lr:0.0001974727463797765 tokens_per_second_per_gpu:865.9782068470809 mfu:12.72530301244261 
Step 409 | loss:2.350391387939453 lr:0.0001974586681154827 tokens_per_second_per_gpu:862.6780072426552 mfu:12.6768075195586 
Step 410 | loss:2.404025077819824 lr:0.0001974445512526336 tokens_per_second_per_gpu:862.7456315920851 mfu:12.677801240105735 
Step 411 | loss:2.3462612628936768 lr:0.00019743039579682016 tokens_per_second_per_gpu:888.6400237443912 mfu:13.058311954873988 
Step 412 | loss:2.406792163848877 lr:0.00019741620175364876 tokens_per_second_per_gpu:861.9894211366312 mfu:12.666688942924651 
Step 413 | loss:2.3446223735809326 lr:0.00019740196912874087 tokens_per_second_per_gpu:865.0506681606868 mfu:12.711673095723226 
Step 414 | loss:2.337446689605713 lr:0.00019738769792773336 tokens_per_second_per_gpu:877.0916448044233 mfu:12.888611816750819 
Step 415 | loss:2.3622031211853027 lr:0.00019737338815627837 tokens_per_second_per_gpu:892.4816281792409 mfu:13.114763237482348 
Step 416 | loss:2.357642650604248 lr:0.00019735903982004324 tokens_per_second_per_gpu:798.001368572061 mfu:11.726402742161113 
Step 417 | loss:2.3678126335144043 lr:0.00019734465292471068 tokens_per_second_per_gpu:902.0453086880631 mfu:13.255298797646212 
Step 418 | loss:2.3936755657196045 lr:0.0001973302274759786 tokens_per_second_per_gpu:898.9720418747245 mfu:13.210138017468838 
Step 419 | loss:2.411846160888672 lr:0.0001973157634795602 tokens_per_second_per_gpu:877.6225672552775 mfu:12.896413570894063 
Step 420 | loss:2.369032859802246 lr:0.00019730126094118398 tokens_per_second_per_gpu:861.7259518161767 mfu:12.662817336329061 
Step 421 | loss:2.398662805557251 lr:0.00019728671986659368 tokens_per_second_per_gpu:878.80969107086 mfu:12.91385801712508 
Step 422 | loss:2.371133804321289 lr:0.00019727214026154827 tokens_per_second_per_gpu:891.9143996167642 mfu:13.106427975373258 
Step 423 | loss:2.3472061157226562 lr:0.00019725752213182204 tokens_per_second_per_gpu:864.8195675772345 mfu:12.708277138495284 
Step 424 | loss:2.3213016986846924 lr:0.0001972428654832045 tokens_per_second_per_gpu:907.1672927462395 mfu:13.330564894009655 
Step 425 | loss:2.3827927112579346 lr:0.0001972281703215004 tokens_per_second_per_gpu:891.2323873522487 mfu:13.096405999467237 
Step 426 | loss:2.3636980056762695 lr:0.0001972134366525298 tokens_per_second_per_gpu:874.7715290576867 mfu:12.854518376907043 
Step 427 | loss:2.3680579662323 lr:0.00019719866448212795 tokens_per_second_per_gpu:878.6133754696535 mfu:12.910973215300194 
Step 428 | loss:2.36203670501709 lr:0.0001971838538161454 tokens_per_second_per_gpu:854.5201971482227 mfu:12.556930824569267 
Step 429 | loss:2.3758673667907715 lr:0.00019716900466044789 tokens_per_second_per_gpu:881.0809746783298 mfu:12.947233882595732 
Step 430 | loss:2.3737289905548096 lr:0.00019715411702091645 tokens_per_second_per_gpu:845.2581948229722 mfu:12.420828339357913 
Step 431 | loss:2.381789207458496 lr:0.00019713919090344736 tokens_per_second_per_gpu:857.7696137597824 mfu:12.604680075842358 
Step 432 | loss:2.344176769256592 lr:0.0001971242263139521 tokens_per_second_per_gpu:862.5485373135867 mfu:12.67490499583991 
Step 433 | loss:2.3588085174560547 lr:0.00019710922325835738 tokens_per_second_per_gpu:867.6648729419888 mfu:12.750088090137188 
Step 434 | loss:2.373425245285034 lr:0.0001970941817426052 tokens_per_second_per_gpu:906.5932998014343 mfu:13.32213023122958 
Step 435 | loss:2.3414807319641113 lr:0.00019707910177265277 tokens_per_second_per_gpu:883.2592514927203 mfu:12.979243039741869 
Step 436 | loss:2.3429982662200928 lr:0.00019706398335447248 tokens_per_second_per_gpu:901.5123065139833 mfu:13.247466482562727 
Step 437 | loss:2.4184272289276123 lr:0.00019704882649405198 tokens_per_second_per_gpu:880.7743270924055 mfu:12.94272778369155 
Step 438 | loss:2.2997243404388428 lr:0.0001970336311973942 tokens_per_second_per_gpu:880.6586352401861 mfu:12.941027724886464 
Step 439 | loss:2.3754162788391113 lr:0.00019701839747051728 tokens_per_second_per_gpu:866.0041832217331 mfu:12.725684727866856 
Step 440 | loss:2.375096321105957 lr:0.00019700312531945442 tokens_per_second_per_gpu:873.4223882134555 mfu:12.834693136602427 
Step 441 | loss:2.3780627250671387 lr:0.00019698781475025422 tokens_per_second_per_gpu:871.093447392831 mfu:12.800470014812332 
Step 442 | loss:2.3572731018066406 lr:0.0001969724657689805 tokens_per_second_per_gpu:870.105148988301 mfu:12.785947251346787 
Step 443 | loss:2.3425350189208984 lr:0.00019695707838171216 tokens_per_second_per_gpu:865.6345817990283 mfu:12.720253540268184 
Step 444 | loss:2.324669599533081 lr:0.0001969416525945434 tokens_per_second_per_gpu:855.0574136344841 mfu:12.564825067769505 
Step 445 | loss:2.3005104064941406 lr:0.00019692618841358364 tokens_per_second_per_gpu:854.7389336448337 mfu:12.560145095063891 
Step 446 | loss:2.371504783630371 lr:0.00019691068584495742 tokens_per_second_per_gpu:890.101666832645 mfu:13.07979038360003 
Step 447 | loss:2.3731400966644287 lr:0.00019689514489480461 tokens_per_second_per_gpu:879.4035323985031 mfu:12.922584346235695 
Step 448 | loss:2.3842172622680664 lr:0.00019687956556928017 tokens_per_second_per_gpu:875.8252989171455 mfu:12.870003224748437 
Step 449 | loss:2.3162841796875 lr:0.00019686394787455424 tokens_per_second_per_gpu:864.4745073223806 mfu:12.703206576365835 
Step 450 | loss:2.387892723083496 lr:0.00019684829181681234 tokens_per_second_per_gpu:861.8342020982276 mfu:12.664408043380796 
Step 451 | loss:2.3479409217834473 lr:0.000196832597402255 tokens_per_second_per_gpu:893.3919996749117 mfu:13.128140887225383 
Step 452 | loss:2.297175168991089 lr:0.000196816864637098 tokens_per_second_per_gpu:837.7775897726434 mfu:12.310902979540339 
Step 453 | loss:2.3667073249816895 lr:0.00019680109352757227 tokens_per_second_per_gpu:899.3184343389771 mfu:13.215228156035824 
Step 454 | loss:2.3115758895874023 lr:0.00019678528407992405 tokens_per_second_per_gpu:870.2270727144563 mfu:12.787738885763757 
Step 455 | loss:2.319852352142334 lr:0.00019676943630041462 tokens_per_second_per_gpu:897.6211627867945 mfu:13.190287234168332 
Step 456 | loss:2.334388256072998 lr:0.00019675355019532051 tokens_per_second_per_gpu:885.945011380133 mfu:13.018709516052429 
Step 457 | loss:2.3061301708221436 lr:0.00019673762577093344 tokens_per_second_per_gpu:877.9632538872453 mfu:12.901419863881346 
Step 458 | loss:2.3732376098632812 lr:0.00019672166303356028 tokens_per_second_per_gpu:885.3278870008178 mfu:13.009641049131368 
Step 459 | loss:2.3556227684020996 lr:0.00019670566198952308 tokens_per_second_per_gpu:882.7254018318306 mfu:12.971398271081183 
Step 460 | loss:2.3218436241149902 lr:0.000196689622645159 tokens_per_second_per_gpu:889.8966099811997 mfu:13.076777131593472 
Step 461 | loss:2.286595344543457 lr:0.00019667354500682054 tokens_per_second_per_gpu:878.8232378401933 mfu:12.914057083040644 
Step 462 | loss:2.356306791305542 lr:0.0001966574290808752 tokens_per_second_per_gpu:864.532080604271 mfu:12.704052599339258 
Step 463 | loss:2.303318977355957 lr:0.0001966412748737057 tokens_per_second_per_gpu:887.7656541216495 mfu:13.04546334239588 
Step 464 | loss:2.341552972793579 lr:0.0001966250823917099 tokens_per_second_per_gpu:863.7669259371318 mfu:12.692808869515869 
Step 465 | loss:2.304478883743286 lr:0.00019660885164130088 tokens_per_second_per_gpu:847.1724805590065 mfu:12.448958222824757 
Step 466 | loss:2.340658664703369 lr:0.00019659258262890683 tokens_per_second_per_gpu:887.1530136537509 mfu:13.036460765275518 
Step 467 | loss:2.337923765182495 lr:0.0001965762753609711 tokens_per_second_per_gpu:849.1983901874281 mfu:12.478728387586006 
Step 468 | loss:2.344913959503174 lr:0.00019655992984395217 tokens_per_second_per_gpu:866.1703177935037 mfu:12.728126028063452 
Step 469 | loss:2.3480021953582764 lr:0.00019654354608432373 tokens_per_second_per_gpu:861.6521277103683 mfu:12.661732512128397 
Step 470 | loss:2.3654441833496094 lr:0.0001965271240885745 tokens_per_second_per_gpu:873.6617751463951 mfu:12.838210859375112 
Step 471 | loss:2.3800108432769775 lr:0.00019651066386320855 tokens_per_second_per_gpu:856.7069642632794 mfu:12.589064744264611 
Step 472 | loss:2.3411688804626465 lr:0.00019649416541474483 tokens_per_second_per_gpu:873.808067987974 mfu:12.840360590999907 
Step 473 | loss:2.3092103004455566 lr:0.00019647762874971765 tokens_per_second_per_gpu:869.8699908876506 mfu:12.782491670059699 
Step 474 | loss:2.3095741271972656 lr:0.00019646105387467627 tokens_per_second_per_gpu:877.5683754138179 mfu:12.89561723722432 
Step 475 | loss:2.3063504695892334 lr:0.0001964444407961853 tokens_per_second_per_gpu:862.2584786307378 mfu:12.670642666139857 
Step 476 | loss:2.3219997882843018 lr:0.00019642778952082426 tokens_per_second_per_gpu:849.0436212959023 mfu:12.476454102822263 
Step 477 | loss:2.271550416946411 lr:0.00019641110005518792 tokens_per_second_per_gpu:893.5284266432388 mfu:13.130145642653758 
Step 478 | loss:2.325260877609253 lr:0.00019639437240588618 tokens_per_second_per_gpu:847.7764333679312 mfu:12.45783313727181 
Step 479 | loss:2.361453056335449 lr:0.000196377606579544 tokens_per_second_per_gpu:864.8389695239548 mfu:12.708562244574276 
Step 480 | loss:2.335312843322754 lr:0.0001963608025828015 tokens_per_second_per_gpu:899.6128911204164 mfu:13.219555114541542 
Step 481 | loss:2.3330793380737305 lr:0.00019634396042231394 tokens_per_second_per_gpu:893.2930693292532 mfu:13.126687133983468 
Step 482 | loss:2.3746416568756104 lr:0.00019632708010475165 tokens_per_second_per_gpu:889.7863851751146 mfu:13.07515740947364 
Step 483 | loss:2.3241779804229736 lr:0.00019631016163680008 tokens_per_second_per_gpu:869.7703309874724 mfu:12.781027196221986 
Step 484 | loss:2.2994987964630127 lr:0.00019629320502515977 tokens_per_second_per_gpu:885.8309751768696 mfu:13.017033786537018 
Step 485 | loss:2.3644580841064453 lr:0.00019627621027654648 tokens_per_second_per_gpu:845.1220842597335 mfu:12.41882823341216 
Step 486 | loss:2.314119338989258 lr:0.00019625917739769092 tokens_per_second_per_gpu:890.3399011282676 mfu:13.083291168695755 
Step 487 | loss:2.3302133083343506 lr:0.00019624210639533895 tokens_per_second_per_gpu:896.300404001587 mfu:13.170879060134366 
Step 488 | loss:2.345066547393799 lr:0.00019622499727625162 tokens_per_second_per_gpu:886.3469883275351 mfu:13.024616452761991 
Step 489 | loss:2.3551764488220215 lr:0.00019620785004720496 tokens_per_second_per_gpu:892.9344203251734 mfu:13.121416889055892 
Step 490 | loss:2.4368157386779785 lr:0.00019619066471499014 tokens_per_second_per_gpu:877.1975749244328 mfu:12.890168429682424 
Step 491 | loss:2.4436559677124023 lr:0.00019617344128641345 tokens_per_second_per_gpu:895.7303266120996 mfu:13.162501935324052 
Step 492 | loss:2.3881478309631348 lr:0.0001961561797682962 tokens_per_second_per_gpu:901.0138979038223 mfu:13.240142510044528 
Step 493 | loss:2.4935553073883057 lr:0.00019613888016747484 tokens_per_second_per_gpu:836.7766516397611 mfu:12.296194478868006 
Step 494 | loss:2.4124536514282227 lr:0.0001961215424908009 tokens_per_second_per_gpu:861.0498820161278 mfu:12.65288268324523 
Step 495 | loss:2.4508605003356934 lr:0.00019610416674514095 tokens_per_second_per_gpu:868.7105516149494 mfu:12.765454040298359 
Step 496 | loss:2.369961977005005 lr:0.00019608675293737672 tokens_per_second_per_gpu:887.7629320983953 mfu:13.045423343039726 
Step 497 | loss:2.3674988746643066 lr:0.00019606930107440485 tokens_per_second_per_gpu:878.5667990697676 mfu:12.910288788374562 
Step 498 | loss:2.4048047065734863 lr:0.00019605181116313724 tokens_per_second_per_gpu:872.250722158805 mfu:12.817475837764034 
Step 499 | loss:2.3876147270202637 lr:0.00019603428321050075 tokens_per_second_per_gpu:874.8343797725761 mfu:12.855441950254722 
Step 500 | loss:2.372481346130371 lr:0.00019601671722343738 tokens_per_second_per_gpu:876.6165198467156 mfu:12.881629990871371 
Step 501 | loss:2.3239617347717285 lr:0.00019599911320890406 tokens_per_second_per_gpu:870.3379872882124 mfu:12.78936874382298 
Step 502 | loss:2.4084877967834473 lr:0.00019598147117387297 tokens_per_second_per_gpu:888.5342021375016 mfu:13.05675693651176 
Step 503 | loss:2.3706722259521484 lr:0.0001959637911253312 tokens_per_second_per_gpu:875.9082488496202 mfu:12.871222150371805 
Step 504 | loss:2.357841730117798 lr:0.0001959460730702809 tokens_per_second_per_gpu:887.0967952815704 mfu:13.035634652314236 
Step 505 | loss:2.3662452697753906 lr:0.00019592831701573937 tokens_per_second_per_gpu:883.1807627576595 mfu:12.978089670143403 
Step 506 | loss:2.3374459743499756 lr:0.00019591052296873888 tokens_per_second_per_gpu:872.7671100875092 mfu:12.825064011245505 
Step 507 | loss:2.3844714164733887 lr:0.00019589269093632682 tokens_per_second_per_gpu:876.1356903593202 mfu:12.874564338553512 
Step 508 | loss:2.3063173294067383 lr:0.0001958748209255655 tokens_per_second_per_gpu:862.8717672667292 mfu:12.679654767905665 
Step 509 | loss:2.3767616748809814 lr:0.0001958569129435324 tokens_per_second_per_gpu:885.4774885302006 mfu:13.011839400980719 
Step 510 | loss:2.266878128051758 lr:0.00019583896699731996 tokens_per_second_per_gpu:882.3907287466619 mfu:12.966480345450714 
Step 511 | loss:2.327268123626709 lr:0.00019582098309403568 tokens_per_second_per_gpu:837.6292495867584 mfu:12.308723162774301 
Step 512 | loss:2.3526105880737305 lr:0.00019580296124080212 tokens_per_second_per_gpu:891.4187562951704 mfu:13.09914463798266 
Step 513 | loss:2.3022079467773438 lr:0.00019578490144475685 tokens_per_second_per_gpu:853.8388037383714 mfu:12.546917942556211 
Step 514 | loss:2.3196353912353516 lr:0.0001957668037130524 tokens_per_second_per_gpu:847.2669608590811 mfu:12.450346583914733 
Step 515 | loss:2.3678622245788574 lr:0.00019574866805285645 tokens_per_second_per_gpu:881.9493670384719 mfu:12.959994660902998 
Step 516 | loss:2.3194034099578857 lr:0.0001957304944713516 tokens_per_second_per_gpu:876.8701819826747 mfu:12.885357483685091 
Step 517 | loss:2.3026695251464844 lr:0.00019571228297573555 tokens_per_second_per_gpu:873.1548179100732 mfu:12.830761267231177 
Step 518 | loss:2.3086495399475098 lr:0.0001956940335732209 tokens_per_second_per_gpu:864.7631931121717 mfu:12.707448731793573 
Step 519 | loss:2.2877297401428223 lr:0.00019567574627103536 tokens_per_second_per_gpu:876.2522607147758 mfu:12.876277306713348 
Step 520 | loss:2.2974512577056885 lr:0.0001956574210764217 tokens_per_second_per_gpu:867.8439894877905 mfu:12.752720156743308 
Step 521 | loss:2.2983665466308594 lr:0.00019563905799663752 tokens_per_second_per_gpu:870.6071918492372 mfu:12.793324628144648 
Step 522 | loss:2.3266007900238037 lr:0.0001956206570389556 tokens_per_second_per_gpu:872.9871018467464 mfu:12.828296727466766 
Step 523 | loss:2.344357967376709 lr:0.0001956022182106636 tokens_per_second_per_gpu:884.6155006614225 mfu:12.999172734849262 
Step 524 | loss:2.2808218002319336 lr:0.0001955837415190643 tokens_per_second_per_gpu:851.0001867855162 mfu:12.505205275221481 
Step 525 | loss:2.3217790126800537 lr:0.0001955652269714753 tokens_per_second_per_gpu:856.7096855105591 mfu:12.58910473221804 
Step 526 | loss:2.2654268741607666 lr:0.00019554667457522936 tokens_per_second_per_gpu:872.5514189852646 mfu:12.821894491953392 
Step 527 | loss:2.3046932220458984 lr:0.00019552808433767415 tokens_per_second_per_gpu:865.1326069291496 mfu:12.71287716257954 
Step 528 | loss:2.321894645690918 lr:0.00019550945626617235 tokens_per_second_per_gpu:858.8018858202973 mfu:12.619849019653493 
Step 529 | loss:2.2977027893066406 lr:0.0001954907903681016 tokens_per_second_per_gpu:893.0327574937139 mfu:13.122861925729067 
Step 530 | loss:2.261763572692871 lr:0.00019547208665085457 tokens_per_second_per_gpu:832.5836252213466 mfu:12.234579150339394 
Step 531 | loss:2.2907614707946777 lr:0.00019545334512183885 tokens_per_second_per_gpu:876.0974516490919 mfu:12.874002431601797 
Step 532 | loss:2.313994884490967 lr:0.00019543456578847702 tokens_per_second_per_gpu:869.1132675996789 mfu:12.771371836950882 
Step 533 | loss:2.306640386581421 lr:0.00019541574865820672 tokens_per_second_per_gpu:865.6477879490327 mfu:12.720447600879762 
Step 534 | loss:2.290083408355713 lr:0.00019539689373848038 tokens_per_second_per_gpu:862.514726931185 mfu:12.674408161903875 
Step 535 | loss:2.2714738845825195 lr:0.00019537800103676557 tokens_per_second_per_gpu:877.9130475197842 mfu:12.900682095616459 
Step 536 | loss:2.2569100856781006 lr:0.00019535907056054475 tokens_per_second_per_gpu:872.2547700590127 mfu:12.817535320504245 
Step 537 | loss:2.313945770263672 lr:0.0001953401023173153 tokens_per_second_per_gpu:880.0751175085386 mfu:12.93245309807757 
Step 538 | loss:2.3029470443725586 lr:0.00019532109631458964 tokens_per_second_per_gpu:871.2501812602102 mfu:12.802773174336375 
Step 539 | loss:2.3256800174713135 lr:0.0001953020525598951 tokens_per_second_per_gpu:875.1976559297857 mfu:12.860780189879158 
Step 540 | loss:2.346677780151367 lr:0.000195282971060774 tokens_per_second_per_gpu:859.5245335034451 mfu:12.63046812145835 
Step 541 | loss:2.319843053817749 lr:0.00019526385182478347 tokens_per_second_per_gpu:898.2514603479951 mfu:13.199549277243856 
Step 542 | loss:2.321310043334961 lr:0.00019524469485949583 tokens_per_second_per_gpu:888.5641622710117 mfu:13.057197192137359 
Step 543 | loss:2.290947198867798 lr:0.00019522550017249813 tokens_per_second_per_gpu:883.7609338885159 mfu:12.986615119607192 
Step 544 | loss:2.2745468616485596 lr:0.00019520626777139245 tokens_per_second_per_gpu:865.8815098760064 mfu:12.723882078003868 
Step 545 | loss:2.312251091003418 lr:0.00019518699766379576 tokens_per_second_per_gpu:872.1773989056344 mfu:12.816398373450179 
Step 546 | loss:2.248955488204956 lr:0.00019516768985734006 tokens_per_second_per_gpu:857.879122537673 mfu:12.606289276131884 
Step 547 | loss:2.276315927505493 lr:0.00019514834435967218 tokens_per_second_per_gpu:884.1414702341483 mfu:12.992206992782675 
Step 548 | loss:2.2784829139709473 lr:0.00019512896117845392 tokens_per_second_per_gpu:860.387876154966 mfu:12.643154695736204 
Step 549 | loss:2.2680909633636475 lr:0.00019510954032136198 tokens_per_second_per_gpu:859.4632090070568 mfu:12.629566975456688 
Step 550 | loss:2.3487720489501953 lr:0.00019509008179608803 tokens_per_second_per_gpu:885.6236970190857 mfu:13.013987893066714 
Step 551 | loss:2.280533790588379 lr:0.0001950705856103386 tokens_per_second_per_gpu:873.598250098818 mfu:12.837277376900717 
Step 552 | loss:2.295240879058838 lr:0.00019505105177183523 tokens_per_second_per_gpu:802.8409706569686 mfu:11.797519315884514 
Step 553 | loss:2.2501931190490723 lr:0.00019503148028831424 tokens_per_second_per_gpu:849.6486010165028 mfu:12.485344107443803 
Step 554 | loss:2.2395546436309814 lr:0.00019501187116752693 tokens_per_second_per_gpu:869.7655282771426 mfu:12.780956621762092 
Step 555 | loss:2.2442216873168945 lr:0.0001949922244172395 tokens_per_second_per_gpu:886.3093540879577 mfu:13.024063428334266 
Step 556 | loss:2.284714698791504 lr:0.00019497254004523308 tokens_per_second_per_gpu:868.091105971679 mfu:12.75635146306486 
Step 557 | loss:2.335782051086426 lr:0.00019495281805930367 tokens_per_second_per_gpu:868.9331174957506 mfu:12.768724582502577 
Step 558 | loss:2.2864818572998047 lr:0.00019493305846726217 tokens_per_second_per_gpu:880.2760160785344 mfu:12.935405245323022 
Step 559 | loss:2.284724712371826 lr:0.0001949132612769344 tokens_per_second_per_gpu:881.4570538131394 mfu:12.952760258328135 
Step 560 | loss:2.286109447479248 lr:0.000194893426496161 tokens_per_second_per_gpu:896.2712672603711 mfu:13.170450904023928 
Step 561 | loss:2.293503999710083 lr:0.00019487355413279757 tokens_per_second_per_gpu:859.0086759726814 mfu:12.622887742023492 
Step 562 | loss:2.344238519668579 lr:0.00019485364419471454 tokens_per_second_per_gpu:877.8883995330848 mfu:12.90031990047469 
Step 563 | loss:2.2539830207824707 lr:0.00019483369668979732 tokens_per_second_per_gpu:869.9530359272743 mfu:12.78371199325552 
Step 564 | loss:2.2649357318878174 lr:0.00019481371162594608 tokens_per_second_per_gpu:847.4949928882475 mfu:12.453697449611745 
Step 565 | loss:2.2728617191314697 lr:0.00019479368901107594 tokens_per_second_per_gpu:879.1789267587128 mfu:12.919283830354306 
Step 566 | loss:2.2559123039245605 lr:0.00019477362885311682 tokens_per_second_per_gpu:905.1529187040526 mfu:13.30096424140137 
Step 567 | loss:2.3113675117492676 lr:0.0001947535311600136 tokens_per_second_per_gpu:891.304555781492 mfu:13.097466493972515 
Step 568 | loss:2.2826039791107178 lr:0.00019473339593972596 tokens_per_second_per_gpu:898.7873943338394 mfu:13.207424674465877 
Step 569 | loss:2.307546854019165 lr:0.00019471322320022849 tokens_per_second_per_gpu:846.1398608154691 mfu:12.433784169910668 
Step 570 | loss:2.2670974731445312 lr:0.0001946930129495106 tokens_per_second_per_gpu:875.8983690379449 mfu:12.871076969354222 
Step 571 | loss:2.2554099559783936 lr:0.0001946727651955765 tokens_per_second_per_gpu:862.3271430249464 mfu:12.671651669848682 
Step 572 | loss:2.2702839374542236 lr:0.00019465247994644545 tokens_per_second_per_gpu:861.4385905955884 mfu:12.658594645068359 
Step 573 | loss:2.266993761062622 lr:0.00019463215721015137 tokens_per_second_per_gpu:868.2805465312815 mfu:12.759135238112233 
Step 574 | loss:2.260669231414795 lr:0.0001946117969947431 tokens_per_second_per_gpu:897.9434817430601 mfu:13.195023619394549 
Step 575 | loss:2.2474918365478516 lr:0.00019459139930828428 tokens_per_second_per_gpu:870.6726631390717 mfu:12.794286710094484 
Step 576 | loss:2.3275701999664307 lr:0.00019457096415885348 tokens_per_second_per_gpu:885.7193818429081 mfu:13.01539395428997 
Step 577 | loss:2.262718915939331 lr:0.000194550491554544 tokens_per_second_per_gpu:883.335499835889 mfu:12.98036348741982 
Step 578 | loss:2.2902491092681885 lr:0.00019452998150346401 tokens_per_second_per_gpu:880.7993433342637 mfu:12.94309539023795 
Step 579 | loss:2.3197121620178223 lr:0.00019450943401373662 tokens_per_second_per_gpu:895.1368085934273 mfu:13.153780357146642 
Step 580 | loss:2.2977287769317627 lr:0.0001944888490934996 tokens_per_second_per_gpu:882.497534818871 mfu:12.968049830250312 
Step 581 | loss:2.2880260944366455 lr:0.00019446822675090565 tokens_per_second_per_gpu:888.811020355104 mfu:13.06082470134753 
Step 582 | loss:2.2532098293304443 lr:0.00019444756699412224 tokens_per_second_per_gpu:864.134794999044 mfu:12.698214600566283 
Step 583 | loss:2.2575523853302 lr:0.00019442686983133168 tokens_per_second_per_gpu:866.5415860942984 mfu:12.733581709960722 
Step 584 | loss:2.3065507411956787 lr:0.00019440613527073105 tokens_per_second_per_gpu:863.936398979247 mfu:12.695299227582971 
Step 585 | loss:2.2720770835876465 lr:0.0001943853633205324 tokens_per_second_per_gpu:862.1386303194564 mfu:12.668881529353127 
Step 586 | loss:2.231937885284424 lr:0.00019436455398896233 tokens_per_second_per_gpu:866.7612333557171 mfu:12.736809363884698 
Step 587 | loss:2.2914578914642334 lr:0.00019434370728426252 tokens_per_second_per_gpu:877.2099214358568 mfu:12.890349858149994 
Step 588 | loss:2.2804553508758545 lr:0.0001943228232146892 tokens_per_second_per_gpu:875.8817089283363 mfu:12.870832153790374 
Step 589 | loss:2.283270835876465 lr:0.0001943019017885136 tokens_per_second_per_gpu:876.825686491865 mfu:12.884703635125437 
Step 590 | loss:2.249405860900879 lr:0.00019428094301402162 tokens_per_second_per_gpu:898.9825012233077 mfu:13.210291714616158 
Step 591 | loss:2.23799991607666 lr:0.00019425994689951402 tokens_per_second_per_gpu:891.3377341188802 mfu:13.097954040187162 
Step 592 | loss:2.3388590812683105 lr:0.0001942389134533063 tokens_per_second_per_gpu:889.1844177543143 mfu:13.06631166973939 
Step 593 | loss:2.227994441986084 lr:0.00019421784268372876 tokens_per_second_per_gpu:872.2032859913398 mfu:12.816778776798792 
Step 594 | loss:2.324234962463379 lr:0.0001941967345991265 tokens_per_second_per_gpu:861.160461164181 mfu:12.654507612319321 
Step 595 | loss:2.2581896781921387 lr:0.00019417558920785939 tokens_per_second_per_gpu:824.4047460353937 mfu:12.11439285105324 
Step 596 | loss:2.2779693603515625 lr:0.00019415440651830208 tokens_per_second_per_gpu:877.8222103645204 mfu:12.899347269501458 
Step 597 | loss:2.238668918609619 lr:0.000194133186538844 tokens_per_second_per_gpu:876.0578868770439 mfu:12.873421038549468 
Step 598 | loss:2.256185293197632 lr:0.00019411192927788927 tokens_per_second_per_gpu:891.0608467589387 mfu:13.09388525932442 
Step 599 | loss:2.258289337158203 lr:0.0001940906347438569 tokens_per_second_per_gpu:885.3298121171127 mfu:13.00966933816681 
Step 600 | loss:2.2215123176574707 lr:0.0001940693029451806 tokens_per_second_per_gpu:889.4841731527036 mfu:13.07071648991149 
Step 601 | loss:2.26560115814209 lr:0.00019404793389030882 tokens_per_second_per_gpu:896.1378239904086 mfu:13.168489993192896 
Step 602 | loss:2.282196044921875 lr:0.00019402652758770475 tokens_per_second_per_gpu:891.6509150268861 mfu:13.10255614439784 
Step 603 | loss:2.3035950660705566 lr:0.00019400508404584645 tokens_per_second_per_gpu:878.8460543239792 mfu:12.914392364768934 
Step 604 | loss:2.3148422241210938 lr:0.00019398360327322654 tokens_per_second_per_gpu:838.8400702159248 mfu:12.326515826929164 
Step 605 | loss:2.1799871921539307 lr:0.00019396208527835263 tokens_per_second_per_gpu:860.1607918153526 mfu:12.639817756067155 
Step 606 | loss:2.237663745880127 lr:0.0001939405300697468 tokens_per_second_per_gpu:826.8002013276548 mfu:12.149593384052524 
Step 607 | loss:2.2552762031555176 lr:0.00019391893765594606 tokens_per_second_per_gpu:877.3780391613573 mfu:12.892820300225603 
Step 608 | loss:2.2853798866271973 lr:0.00019389730804550211 tokens_per_second_per_gpu:838.5491452333623 mfu:12.322240767201647 
Step 609 | loss:2.2523295879364014 lr:0.00019387564124698133 tokens_per_second_per_gpu:871.3839000056051 mfu:12.804738133200397 
Step 610 | loss:2.2882227897644043 lr:0.0001938539372689649 tokens_per_second_per_gpu:835.4371527372796 mfu:12.27651092415019 
Step 611 | loss:2.265392541885376 lr:0.00019383219612004865 tokens_per_second_per_gpu:850.4042192053377 mfu:12.496447701435674 
Step 612 | loss:2.271329164505005 lr:0.00019381041780884323 tokens_per_second_per_gpu:884.8294826676638 mfu:13.002317139462566 
Step 613 | loss:2.280533790588379 lr:0.00019378860234397393 tokens_per_second_per_gpu:876.9954560834411 mfu:12.887198350902372 
Step 614 | loss:2.2736878395080566 lr:0.00019376674973408075 tokens_per_second_per_gpu:878.6528903162598 mfu:12.911553874712382 
Step 615 | loss:2.191652774810791 lr:0.00019374485998781843 tokens_per_second_per_gpu:891.099402388324 mfu:13.09445182331285 
Step 616 | loss:2.2672512531280518 lr:0.00019372293311385646 tokens_per_second_per_gpu:863.2700573293305 mfu:12.685507526893561 
Step 617 | loss:2.334188938140869 lr:0.00019370096912087897 tokens_per_second_per_gpu:828.620296643926 mfu:12.176339166137973 
Step 618 | loss:2.2988743782043457 lr:0.0001936789680175848 tokens_per_second_per_gpu:889.0305433248114 mfu:13.064050528840221 
Step 619 | loss:2.2278499603271484 lr:0.00019365692981268743 tokens_per_second_per_gpu:854.4216414397316 mfu:12.555482576513787 
Step 620 | loss:2.2481870651245117 lr:0.00019363485451491524 tokens_per_second_per_gpu:859.2924972041257 mfu:12.627058414152346 
Step 621 | loss:2.3429465293884277 lr:0.0001936127421330111 tokens_per_second_per_gpu:870.7007565384612 mfu:12.794699534594054 
Step 622 | loss:2.2818918228149414 lr:0.0001935905926757326 tokens_per_second_per_gpu:868.1702446890885 mfu:12.757514383968745 
Step 623 | loss:2.2971298694610596 lr:0.00019356840615185203 tokens_per_second_per_gpu:836.3199171803152 mfu:12.289482896120637 
Step 624 | loss:2.2743773460388184 lr:0.00019354618257015646 tokens_per_second_per_gpu:882.1165032463897 mfu:12.962450679857389 
Step 625 | loss:2.2979848384857178 lr:0.0001935239219394475 tokens_per_second_per_gpu:852.9026343931218 mfu:12.533161200764017 
Step 626 | loss:2.303593873977661 lr:0.0001935016242685415 tokens_per_second_per_gpu:897.9198014693021 mfu:13.194675644518728 
Step 627 | loss:2.2126026153564453 lr:0.0001934792895662694 tokens_per_second_per_gpu:850.515190817486 mfu:12.49807839765782 
Step 628 | loss:2.27461838722229 lr:0.000193456917841477 tokens_per_second_per_gpu:883.4740597258435 mfu:12.982399585523792 
Step 629 | loss:2.285086154937744 lr:0.0001934345091030245 tokens_per_second_per_gpu:875.8061856313379 mfu:12.869722360459312 
Step 630 | loss:2.2706944942474365 lr:0.00019341206335978694 tokens_per_second_per_gpu:889.0204615955804 mfu:13.06390238070169 
Step 631 | loss:2.2271456718444824 lr:0.000193389580620654 tokens_per_second_per_gpu:869.5704891830765 mfu:12.77809057784593 
Step 632 | loss:2.2669107913970947 lr:0.00019336706089452996 tokens_per_second_per_gpu:894.6080644118521 mfu:13.146010612049814 
Step 633 | loss:2.2395288944244385 lr:0.00019334450419033377 tokens_per_second_per_gpu:880.005237765103 mfu:12.931426235158135 
Step 634 | loss:2.216320514678955 lr:0.000193321910516999 tokens_per_second_per_gpu:869.9370681415394 mfu:12.783477351193737 
Step 635 | loss:2.260971784591675 lr:0.0001932992798834739 tokens_per_second_per_gpu:839.9448577491227 mfu:12.342750364950042 
Step 636 | loss:2.247520923614502 lr:0.00019327661229872137 tokens_per_second_per_gpu:867.1151645135188 mfu:12.74201028140544 
Step 637 | loss:2.2250890731811523 lr:0.00019325390777171885 tokens_per_second_per_gpu:870.1722024150691 mfu:12.786932582348076 
Step 638 | loss:2.237753391265869 lr:0.0001932311663114586 tokens_per_second_per_gpu:870.0871524152551 mfu:12.785682796833516 
Step 639 | loss:2.2944180965423584 lr:0.00019320838792694724 tokens_per_second_per_gpu:895.9099029997484 mfu:13.165140759175095 
Step 640 | loss:2.2239694595336914 lr:0.0001931855726272063 tokens_per_second_per_gpu:865.1790371815315 mfu:12.713559441909242 
Step 641 | loss:2.2778737545013428 lr:0.0001931627204212717 tokens_per_second_per_gpu:882.5428035302992 mfu:12.968715041066648 
Step 642 | loss:2.220721483230591 lr:0.00019313983131819407 tokens_per_second_per_gpu:897.1584933561576 mfu:13.18348843871032 
Step 643 | loss:2.273466110229492 lr:0.0001931169053270387 tokens_per_second_per_gpu:892.6652453004288 mfu:13.117461438761447 
Step 644 | loss:2.2774956226348877 lr:0.0001930939424568854 tokens_per_second_per_gpu:897.3991260999675 mfu:13.187024468318786 
Step 645 | loss:2.2430171966552734 lr:0.00019307094271682864 tokens_per_second_per_gpu:868.340808466605 mfu:12.760020770081795 
Step 646 | loss:2.2565596103668213 lr:0.0001930479061159775 tokens_per_second_per_gpu:876.1808578367189 mfu:12.875228061764629 
Step 647 | loss:2.2588419914245605 lr:0.0001930248326634556 tokens_per_second_per_gpu:888.6168428968364 mfu:13.057971318923926 
Step 648 | loss:2.24153470993042 lr:0.00019300172236840122 tokens_per_second_per_gpu:864.4437645175558 mfu:12.70275481960827 
Step 649 | loss:2.2121453285217285 lr:0.00019297857523996719 tokens_per_second_per_gpu:875.6190257286637 mfu:12.86697209901569 
Step 650 | loss:2.270551919937134 lr:0.00019295539128732093 tokens_per_second_per_gpu:879.6807298486771 mfu:12.92665768378605 
Step 651 | loss:2.269848346710205 lr:0.0001929321705196445 tokens_per_second_per_gpu:858.7168931958192 mfu:12.618600077253149 
Step 652 | loss:2.2390787601470947 lr:0.00019290891294613448 tokens_per_second_per_gpu:867.9515371365346 mfu:12.754300538798795 
Step 653 | loss:2.2759740352630615 lr:0.000192885618576002 tokens_per_second_per_gpu:859.0568370779743 mfu:12.62359545574356 
Step 654 | loss:2.2544045448303223 lr:0.00019286228741847286 tokens_per_second_per_gpu:889.5841773654354 mfu:13.072186023324075 
Step 655 | loss:2.2275209426879883 lr:0.00019283891948278735 tokens_per_second_per_gpu:889.5996716934058 mfu:13.072413708058908 
Step 656 | loss:2.2795729637145996 lr:0.00019281551477820036 tokens_per_second_per_gpu:845.0168516012188 mfu:12.4172818694785 
Step 657 | loss:2.2424755096435547 lr:0.00019279207331398136 tokens_per_second_per_gpu:879.8396501552843 mfu:12.928992972411582 
Step 658 | loss:2.248110294342041 lr:0.0001927685950994143 tokens_per_second_per_gpu:857.3114813471648 mfu:12.59794795057144 
Step 659 | loss:2.2685468196868896 lr:0.00019274508014379777 tokens_per_second_per_gpu:866.0200859019642 mfu:12.72591841322181 
Step 660 | loss:2.241215229034424 lr:0.0001927215284564449 tokens_per_second_per_gpu:870.8177584270346 mfu:12.796418844010104 
Step 661 | loss:2.2477426528930664 lr:0.0001926979400466833 tokens_per_second_per_gpu:859.050103367298 mfu:12.623496505783761 
Step 662 | loss:2.263469934463501 lr:0.00019267431492385521 tokens_per_second_per_gpu:900.4302995453979 mfu:13.231566698448121 
Step 663 | loss:2.268491744995117 lr:0.00019265065309731738 tokens_per_second_per_gpu:860.8549263378176 mfu:12.650017865099834 
Step 664 | loss:2.215160608291626 lr:0.00019262695457644103 tokens_per_second_per_gpu:837.0372666977885 mfu:12.300024142890475 
Step 665 | loss:2.2312138080596924 lr:0.00019260321937061202 tokens_per_second_per_gpu:882.173600559414 mfu:12.963289708603938 
Step 666 | loss:2.2635438442230225 lr:0.00019257944748923072 tokens_per_second_per_gpu:866.3391152302688 mfu:12.730606458302429 
Step 667 | loss:2.256765365600586 lr:0.00019255563894171192 tokens_per_second_per_gpu:858.7514980939018 mfu:12.619108586370738 
Step 668 | loss:2.2460036277770996 lr:0.00019253179373748504 tokens_per_second_per_gpu:856.273323386839 mfu:12.582692515139613 
Step 669 | loss:2.2177608013153076 lr:0.000192507911885994 tokens_per_second_per_gpu:859.1978166305446 mfu:12.625667110100252 
Step 670 | loss:2.2686967849731445 lr:0.0001924839933966972 tokens_per_second_per_gpu:866.6111624998225 mfu:12.734604115415976 
Step 671 | loss:2.2685670852661133 lr:0.0001924600382790676 tokens_per_second_per_gpu:889.834921281562 mfu:13.075870633728828 
Step 672 | loss:2.265474557876587 lr:0.0001924360465425926 tokens_per_second_per_gpu:809.554810970643 mfu:11.896177286365917 
Step 673 | loss:2.211202383041382 lr:0.00019241201819677413 tokens_per_second_per_gpu:889.6489841278113 mfu:13.073138340232248 
Step 674 | loss:2.2941949367523193 lr:0.0001923879532511287 tokens_per_second_per_gpu:873.2273069202078 mfu:12.831826472581312 
Step 675 | loss:2.2620487213134766 lr:0.00019236385171518715 tokens_per_second_per_gpu:858.3609124965858 mfu:12.61336904230503 
Step 676 | loss:2.282688856124878 lr:0.000192339713598495 tokens_per_second_per_gpu:868.7344593626284 mfu:12.765805357838634 
Step 677 | loss:2.274847984313965 lr:0.00019231553891061208 tokens_per_second_per_gpu:906.8216751324405 mfu:13.325486141649314 
Step 678 | loss:2.285968780517578 lr:0.00019229132766111282 tokens_per_second_per_gpu:864.6029402719937 mfu:12.705093861966887 
Step 679 | loss:2.228471517562866 lr:0.00019226707985958613 tokens_per_second_per_gpu:861.8171186361483 mfu:12.664157006773014 
Step 680 | loss:2.268690586090088 lr:0.00019224279551563532 tokens_per_second_per_gpu:873.8860702697507 mfu:12.841506812305965 
Step 681 | loss:2.2051291465759277 lr:0.00019221847463887824 tokens_per_second_per_gpu:889.6425780959953 mfu:13.073044205419938 
Step 682 | loss:2.267836332321167 lr:0.00019219411723894717 tokens_per_second_per_gpu:864.2634465120711 mfu:12.700105097894433 
Step 683 | loss:2.1963839530944824 lr:0.00019216972332548887 tokens_per_second_per_gpu:850.2686838568 mfu:12.49445604810606 
Step 684 | loss:2.1739141941070557 lr:0.00019214529290816459 tokens_per_second_per_gpu:834.3295058520628 mfu:12.260234368766087 
Step 685 | loss:2.2877004146575928 lr:0.00019212082599664998 tokens_per_second_per_gpu:882.350631619606 mfu:12.965891129593224 
Step 686 | loss:2.2279064655303955 lr:0.0001920963226006352 tokens_per_second_per_gpu:893.3817442920015 mfu:13.127990187295511 
Step 687 | loss:2.283386707305908 lr:0.0001920717827298248 tokens_per_second_per_gpu:888.1390401347442 mfu:13.050950143472015 
Step 688 | loss:2.2047195434570312 lr:0.00019204720639393782 tokens_per_second_per_gpu:842.7434941236278 mfu:12.383875529077308 
Step 689 | loss:2.2218806743621826 lr:0.0001920225936027077 tokens_per_second_per_gpu:885.5738069254 mfu:13.013254772354841 
Step 690 | loss:2.2568578720092773 lr:0.00019199794436588243 tokens_per_second_per_gpu:880.0614604812378 mfu:12.932252411952586 
Step 691 | loss:2.2597243785858154 lr:0.0001919732586932243 tokens_per_second_per_gpu:836.3014930329799 mfu:12.28921215852501 
Step 692 | loss:2.1902060508728027 lr:0.0001919485365945101 tokens_per_second_per_gpu:873.2499274309932 mfu:12.832158874542198 
Step 693 | loss:2.218075752258301 lr:0.00019192377807953097 tokens_per_second_per_gpu:860.3209433450148 mfu:12.642171137164674 
Step 694 | loss:2.265346050262451 lr:0.00019189898315809261 tokens_per_second_per_gpu:897.1276695448533 mfu:13.18303549158562 
Step 695 | loss:2.2147514820098877 lr:0.00019187415184001503 tokens_per_second_per_gpu:876.5043426024431 mfu:12.87998157822867 
Step 696 | loss:2.2249743938446045 lr:0.0001918492841351327 tokens_per_second_per_gpu:897.5529924865098 mfu:13.18928549102894 
Step 697 | loss:2.2810630798339844 lr:0.00019182438005329447 tokens_per_second_per_gpu:876.465078001826 mfu:12.879404596109994 
Step 698 | loss:2.2404487133026123 lr:0.00019179943960436358 tokens_per_second_per_gpu:912.9423511666843 mfu:13.415427732050677 
Step 699 | loss:2.2307159900665283 lr:0.0001917744627982178 tokens_per_second_per_gpu:891.2514430183784 mfu:13.096686017051614 
Step 700 | loss:2.2563908100128174 lr:0.00019174944964474912 tokens_per_second_per_gpu:859.1688936564063 mfu:12.625242095236114 
Step 701 | loss:2.2346432209014893 lr:0.0001917244001538641 tokens_per_second_per_gpu:858.343190118005 mfu:12.6131086170013 
Step 702 | loss:2.275686502456665 lr:0.0001916993143354835 tokens_per_second_per_gpu:828.0888232430522 mfu:12.168529315941168 
Step 703 | loss:2.2203850746154785 lr:0.00019167419219954263 tokens_per_second_per_gpu:874.4934901402877 mfu:12.850432674235567 
Step 704 | loss:2.2040462493896484 lr:0.00019164903375599112 tokens_per_second_per_gpu:852.7060966713883 mfu:12.530273134941277 
Step 705 | loss:2.239696741104126 lr:0.000191623839014793 tokens_per_second_per_gpu:891.2224974303593 mfu:13.09626066988294 
Step 706 | loss:2.1996755599975586 lr:0.00019159860798592662 tokens_per_second_per_gpu:886.8106340549404 mfu:13.031429594622846 
Step 707 | loss:2.173297882080078 lr:0.00019157334067938474 tokens_per_second_per_gpu:872.3006514606636 mfu:12.818209534628837 
Step 708 | loss:2.276651382446289 lr:0.00019154803710517455 tokens_per_second_per_gpu:827.9039476079373 mfu:12.165812621158489 
Step 709 | loss:2.1915929317474365 lr:0.00019152269727331747 tokens_per_second_per_gpu:862.8586121942653 mfu:12.679461457863994 
Step 710 | loss:2.21895694732666 lr:0.00019149732119384943 tokens_per_second_per_gpu:880.3447339765984 mfu:12.936415035255754 
Step 711 | loss:2.276521921157837 lr:0.00019147190887682056 tokens_per_second_per_gpu:898.038102053675 mfu:13.196414037899522 
Step 712 | loss:2.2537500858306885 lr:0.00019144646033229549 tokens_per_second_per_gpu:851.3820128846772 mfu:12.510816100957584 
Step 713 | loss:2.2146663665771484 lr:0.00019142097557035308 tokens_per_second_per_gpu:850.7607320089505 mfu:12.501686555506039 
Step 714 | loss:2.2811849117279053 lr:0.00019139545460108659 tokens_per_second_per_gpu:885.8677699915171 mfu:13.01757447585457 
Step 715 | loss:2.184236526489258 lr:0.00019136989743460364 tokens_per_second_per_gpu:882.5568589981154 mfu:12.968921582161482 
Step 716 | loss:2.2091643810272217 lr:0.00019134430408102615 tokens_per_second_per_gpu:900.7672901334288 mfu:13.23651867912284 
Step 717 | loss:2.2018234729766846 lr:0.00019131867455049036 tokens_per_second_per_gpu:868.7815980625472 mfu:12.766498047603037 
Step 718 | loss:2.212231159210205 lr:0.00019129300885314688 tokens_per_second_per_gpu:880.5392856374082 mfu:12.939273916479097 
Step 719 | loss:2.161224842071533 lr:0.00019126730699916061 tokens_per_second_per_gpu:863.1206957366492 mfu:12.683312700845674 
Step 720 | loss:2.254030227661133 lr:0.0001912415689987108 tokens_per_second_per_gpu:861.5275854204612 mfu:12.659902398663185 
Step 721 | loss:2.2435359954833984 lr:0.00019121579486199098 tokens_per_second_per_gpu:862.9790312140909 mfu:12.681230981050174 
Step 722 | loss:2.300543785095215 lr:0.00019118998459920902 tokens_per_second_per_gpu:872.6850046466343 mfu:12.823857495185582 
Step 723 | loss:2.248905658721924 lr:0.00019116413822058706 tokens_per_second_per_gpu:849.4367023879029 mfu:12.482230317471336 
Step 724 | loss:2.226889133453369 lr:0.00019113825573636162 tokens_per_second_per_gpu:871.2356476329219 mfu:12.802559606824339 
Step 725 | loss:2.202754259109497 lr:0.00019111233715678343 tokens_per_second_per_gpu:882.4162850322103 mfu:12.966855887785272 
Step 726 | loss:2.1886210441589355 lr:0.00019108638249211758 tokens_per_second_per_gpu:902.4718770973635 mfu:13.261567098881697 
Step 727 | loss:2.2118825912475586 lr:0.00019106039175264343 tokens_per_second_per_gpu:833.6570246177483 mfu:12.25035244863326 
Step 728 | loss:2.215108871459961 lr:0.0001910343649486546 tokens_per_second_per_gpu:875.1575872076334 mfu:12.860191391423633 
Step 729 | loss:2.268012523651123 lr:0.00019100830209045906 tokens_per_second_per_gpu:873.508381084831 mfu:12.835956777345935 
Step 730 | loss:2.1912143230438232 lr:0.00019098220318837896 tokens_per_second_per_gpu:887.4829153219714 mfu:13.041308576293419 
Step 731 | loss:2.237241506576538 lr:0.00019095606825275083 tokens_per_second_per_gpu:876.5530931030731 mfu:12.880697952945287 
Step 732 | loss:2.2176029682159424 lr:0.00019092989729392544 tokens_per_second_per_gpu:895.4488899861464 mfu:13.158366304293459 
Step 733 | loss:2.2536120414733887 lr:0.00019090369032226777 tokens_per_second_per_gpu:867.7069041251375 mfu:12.750705726397905 
Step 734 | loss:2.254232883453369 lr:0.00019087744734815708 tokens_per_second_per_gpu:893.0242157973969 mfu:13.122736407935415 
Step 735 | loss:2.1943705081939697 lr:0.00019085116838198698 tokens_per_second_per_gpu:885.4103496625079 mfu:13.010852814449388 
Step 736 | loss:2.18638277053833 lr:0.00019082485343416522 tokens_per_second_per_gpu:875.3866335737246 mfu:12.863557162512747 
Step 737 | loss:2.186988115310669 lr:0.0001907985025151139 tokens_per_second_per_gpu:849.5915954042838 mfu:12.48450642621446 
Step 738 | loss:2.1998941898345947 lr:0.00019077211563526926 tokens_per_second_per_gpu:893.5234577351175 mfu:13.130072625964672 
Step 739 | loss:2.233297824859619 lr:0.0001907456928050819 tokens_per_second_per_gpu:861.1066387746922 mfu:12.653716707641024 
Step 740 | loss:2.2692158222198486 lr:0.0001907192340350165 tokens_per_second_per_gpu:865.7211494866565 mfu:12.721525627772749 
Step 741 | loss:2.2171149253845215 lr:0.00019069273933555215 tokens_per_second_per_gpu:888.582448849908 mfu:13.057465908203973 
Step 742 | loss:2.2786550521850586 lr:0.00019066620871718205 tokens_per_second_per_gpu:883.0043294672496 mfu:12.975497033210745 
Step 743 | loss:2.199463129043579 lr:0.0001906396421904137 tokens_per_second_per_gpu:883.2498052722522 mfu:12.979104230223536 
Step 744 | loss:2.219891309738159 lr:0.00019061303976576873 tokens_per_second_per_gpu:842.3304022565293 mfu:12.3778052617897 
Step 745 | loss:2.2162842750549316 lr:0.00019058640145378313 tokens_per_second_per_gpu:872.8046943415492 mfu:12.82561630115 
Step 746 | loss:2.256592035293579 lr:0.00019055972726500695 tokens_per_second_per_gpu:868.038575838047 mfu:12.755579547718185 
Step 747 | loss:2.2264821529388428 lr:0.00019053301721000453 tokens_per_second_per_gpu:874.0205341089587 mfu:12.843482720111275 
Step 748 | loss:2.248840093612671 lr:0.00019050627129935438 tokens_per_second_per_gpu:894.1443131140212 mfu:13.139195918861637 
Step 749 | loss:2.203780174255371 lr:0.0001904794895436493 tokens_per_second_per_gpu:884.7941399425339 mfu:13.001797788186739 
Step 750 | loss:2.2035470008850098 lr:0.00019045267195349613 tokens_per_second_per_gpu:854.0548116604693 mfu:12.550092117425798 
Step 751 | loss:2.1944499015808105 lr:0.00019042581853951604 tokens_per_second_per_gpu:862.7356816594386 mfu:12.67765502868046 
Step 752 | loss:2.233395576477051 lr:0.00019039892931234435 tokens_per_second_per_gpu:893.8427524242269 mfu:13.134764570446709 
Step 753 | loss:2.2669076919555664 lr:0.00019037200428263052 tokens_per_second_per_gpu:826.8861757611314 mfu:12.150856753856363 
Step 754 | loss:2.2101356983184814 lr:0.00019034504346103823 tokens_per_second_per_gpu:875.3671700476859 mfu:12.863271151543218 
Step 755 | loss:2.178417444229126 lr:0.00019031804685824534 tokens_per_second_per_gpu:831.8300826318005 mfu:12.223506056687688 
Step 756 | loss:2.2553563117980957 lr:0.00019029101448494385 tokens_per_second_per_gpu:882.6511477882227 mfu:12.970307129067056 
Step 757 | loss:2.2093536853790283 lr:0.00019026394635184 tokens_per_second_per_gpu:873.1672831473987 mfu:12.830944440342043 
Step 758 | loss:2.2247185707092285 lr:0.00019023684246965406 tokens_per_second_per_gpu:885.7673710494802 mfu:13.016099142007315 
Step 759 | loss:2.2450978755950928 lr:0.0001902097028491206 tokens_per_second_per_gpu:881.4937183707483 mfu:12.95329903355562 
Step 760 | loss:2.2528510093688965 lr:0.0001901825275009882 tokens_per_second_per_gpu:865.4329793690433 mfu:12.717291050000739 
Step 761 | loss:2.2608487606048584 lr:0.00019015531643601973 tokens_per_second_per_gpu:871.1614293269782 mfu:12.801468989965004 
Step 762 | loss:2.212533473968506 lr:0.00019012806966499217 tokens_per_second_per_gpu:876.1190931058427 mfu:12.8743204466426 
Step 763 | loss:2.2094850540161133 lr:0.00019010078719869657 tokens_per_second_per_gpu:872.1890420610553 mfu:12.816569466301685 
Step 764 | loss:2.249227285385132 lr:0.00019007346904793818 tokens_per_second_per_gpu:856.4499460040081 mfu:12.585287934175053 
Step 765 | loss:2.1902546882629395 lr:0.00019004611522353636 tokens_per_second_per_gpu:852.9499164384324 mfu:12.53385599694811 
Step 766 | loss:2.208460807800293 lr:0.00019001872573632463 tokens_per_second_per_gpu:860.8606296404652 mfu:12.650101673507237 
Step 767 | loss:2.2099623680114746 lr:0.00018999130059715058 tokens_per_second_per_gpu:873.2253724385342 mfu:12.831798045924298 
Step 768 | loss:2.2390646934509277 lr:0.00018996383981687598 tokens_per_second_per_gpu:875.031784025083 mfu:12.858342749500284 
Step 769 | loss:2.182539939880371 lr:0.00018993634340637666 tokens_per_second_per_gpu:872.4962861643875 mfu:12.821084330859216 
Step 770 | loss:2.2143213748931885 lr:0.00018990881137654258 tokens_per_second_per_gpu:866.6874196228123 mfu:12.735724692110898 
Step 771 | loss:2.257352352142334 lr:0.00018988124373827789 tokens_per_second_per_gpu:886.469555925925 mfu:13.026417548697994 
Step 772 | loss:2.242870807647705 lr:0.00018985364050250065 tokens_per_second_per_gpu:883.9675333477556 mfu:12.989651039795767 
Step 773 | loss:2.2392079830169678 lr:0.00018982600168014323 tokens_per_second_per_gpu:899.122565612807 mfu:13.212349920912272 
Step 774 | loss:2.198538064956665 lr:0.00018979832728215196 tokens_per_second_per_gpu:884.4557022252577 mfu:12.996824542360082 
Step 775 | loss:2.19303560256958 lr:0.0001897706173194873 tokens_per_second_per_gpu:872.9210817155309 mfu:12.827326580449213 
Step 776 | loss:2.223444938659668 lr:0.00018974287180312377 tokens_per_second_per_gpu:872.0090003500559 mfu:12.813923804656586 
Step 777 | loss:2.195993423461914 lr:0.00018971509074405007 tokens_per_second_per_gpu:888.0069728965146 mfu:13.049009453035236 
Step 778 | loss:2.2548298835754395 lr:0.00018968727415326884 tokens_per_second_per_gpu:872.8071916726666 mfu:12.825652998719224 
Step 779 | loss:2.243952989578247 lr:0.00018965942204179686 tokens_per_second_per_gpu:876.8726129345096 mfu:12.885393205829672 
Step 780 | loss:2.166943073272705 lr:0.000189631534420665 tokens_per_second_per_gpu:881.9028027652422 mfu:12.959310412175123 
Step 781 | loss:2.213888168334961 lr:0.00018960361130091816 tokens_per_second_per_gpu:888.0827988989932 mfu:13.050123694537081 
Step 782 | loss:2.2031898498535156 lr:0.00018957565269361531 tokens_per_second_per_gpu:867.2726479458876 mfu:12.744324455573434 
Step 783 | loss:2.184781074523926 lr:0.00018954765860982944 tokens_per_second_per_gpu:865.9024536534109 mfu:12.724189840845463 
Step 784 | loss:2.2080092430114746 lr:0.00018951962906064762 tokens_per_second_per_gpu:898.1228864279121 mfu:13.197659920121913 
Step 785 | loss:2.1630897521972656 lr:0.000189491564057171 tokens_per_second_per_gpu:853.0180005473212 mfu:12.534856473529498 
Step 786 | loss:2.264007091522217 lr:0.00018946346361051474 tokens_per_second_per_gpu:884.1235613304593 mfu:12.991943826545626 
Step 787 | loss:2.263176918029785 lr:0.00018943532773180803 tokens_per_second_per_gpu:862.8781268390491 mfu:12.679748220008916 
Step 788 | loss:2.2408838272094727 lr:0.00018940715643219407 tokens_per_second_per_gpu:842.8273852018709 mfu:12.385108284569586 
Step 789 | loss:2.227428913116455 lr:0.00018937894972283017 tokens_per_second_per_gpu:882.1002863957921 mfu:12.96221237785841 
Step 790 | loss:2.2134509086608887 lr:0.00018935070761488752 tokens_per_second_per_gpu:895.6603550554237 mfu:13.16147372323521 
Step 791 | loss:2.221574068069458 lr:0.00018932243011955154 tokens_per_second_per_gpu:866.8837477120915 mfu:12.738609677444451 
Step 792 | loss:2.249216318130493 lr:0.00018929411724802147 tokens_per_second_per_gpu:829.0442633808492 mfu:12.18256923653915 
Step 793 | loss:2.2263410091400146 lr:0.00018926576901151068 tokens_per_second_per_gpu:854.5716487464363 mfu:12.55768689114527 
Step 794 | loss:2.1934146881103516 lr:0.00018923738542124644 tokens_per_second_per_gpu:866.7059196558314 mfu:12.735996544825028 
Step 795 | loss:2.2492423057556152 lr:0.00018920896648847016 tokens_per_second_per_gpu:877.6516523505287 mfu:12.896840968081765 
Step 796 | loss:2.2219393253326416 lr:0.0001891805122244371 tokens_per_second_per_gpu:887.356794464919 mfu:13.039455266233775 
Step 797 | loss:2.232104539871216 lr:0.00018915202264041664 tokens_per_second_per_gpu:876.5346545736451 mfu:12.880427004008904 
Step 798 | loss:2.2530949115753174 lr:0.00018912349774769207 tokens_per_second_per_gpu:859.8878231771555 mfu:12.635806559703912 
Step 799 | loss:2.180528402328491 lr:0.00018909493755756072 tokens_per_second_per_gpu:864.8504103731568 mfu:12.708730364593539 
Step 800 | loss:2.228545665740967 lr:0.00018906634208133385 tokens_per_second_per_gpu:887.2347774630475 mfu:13.037662261156736 
Step 801 | loss:2.2010793685913086 lr:0.00018903771133033667 tokens_per_second_per_gpu:870.7120028336581 mfu:12.794864795697643 
Step 802 | loss:2.2676236629486084 lr:0.00018900904531590846 tokens_per_second_per_gpu:837.2399449602948 mfu:12.30300244221029 
Step 803 | loss:2.1787753105163574 lr:0.00018898034404940238 tokens_per_second_per_gpu:890.8105782256969 mfu:13.090207634535712 
Step 804 | loss:2.163668394088745 lr:0.00018895160754218561 tokens_per_second_per_gpu:873.8281700994536 mfu:12.840655985800543 
Step 805 | loss:2.155952215194702 lr:0.00018892283580563922 tokens_per_second_per_gpu:836.2214513794103 mfu:12.288035969231517 
Step 806 | loss:2.1803107261657715 lr:0.00018889402885115833 tokens_per_second_per_gpu:828.4999301347485 mfu:12.174570414580804 
Step 807 | loss:2.15944504737854 lr:0.00018886518669015186 tokens_per_second_per_gpu:915.4826571584002 mfu:13.452756804807144 
Step 808 | loss:2.222046375274658 lr:0.00018883630933404284 tokens_per_second_per_gpu:894.3157859226908 mfu:13.141715662928476 
Step 809 | loss:2.2047510147094727 lr:0.00018880739679426816 tokens_per_second_per_gpu:863.1107024264564 mfu:12.683165851999716 
Step 810 | loss:2.1603734493255615 lr:0.00018877844908227857 tokens_per_second_per_gpu:888.6967707588216 mfu:13.059145836082507 
Step 811 | loss:2.202949047088623 lr:0.0001887494662095389 tokens_per_second_per_gpu:884.1346274450466 mfu:12.992106439946493 
Step 812 | loss:2.1902201175689697 lr:0.0001887204481875278 tokens_per_second_per_gpu:891.9055462595818 mfu:13.106297877811988 
Step 813 | loss:2.2324955463409424 lr:0.0001886913950277379 tokens_per_second_per_gpu:883.2801118594318 mfu:12.979549576887095 
Step 814 | loss:2.210371494293213 lr:0.00018866230674167568 tokens_per_second_per_gpu:848.2898823542372 mfu:12.465378123832112 
Step 815 | loss:2.221824884414673 lr:0.00018863318334086157 tokens_per_second_per_gpu:868.493835865413 mfu:12.76226946410624 
Step 816 | loss:2.2355294227600098 lr:0.00018860402483682998 tokens_per_second_per_gpu:896.116049625886 mfu:13.168170025110257 
Step 817 | loss:2.1528124809265137 lr:0.00018857483124112907 tokens_per_second_per_gpu:896.917102765307 mfu:13.179941272755523 
Step 818 | loss:2.2148280143737793 lr:0.000188545602565321 tokens_per_second_per_gpu:876.8806454190725 mfu:12.885511240901682 
Step 819 | loss:2.2173845767974854 lr:0.0001885163388209818 tokens_per_second_per_gpu:867.9141554072243 mfu:12.753751224937497 
Step 820 | loss:2.198547124862671 lr:0.00018848704001970143 tokens_per_second_per_gpu:852.7371667330932 mfu:12.530729700645452 
Step 821 | loss:2.2175233364105225 lr:0.00018845770617308366 tokens_per_second_per_gpu:853.1472319014609 mfu:12.536755491457587 
Step 822 | loss:2.214859962463379 lr:0.00018842833729274615 tokens_per_second_per_gpu:920.6879181217622 mfu:13.52924663156478 
Step 823 | loss:2.19633150100708 lr:0.00018839893339032054 tokens_per_second_per_gpu:840.1260204931682 mfu:12.345412499856344 
Step 824 | loss:2.1572821140289307 lr:0.00018836949447745215 tokens_per_second_per_gpu:898.0919541437123 mfu:13.197205379018918 
Step 825 | loss:2.2476203441619873 lr:0.00018834002056580037 tokens_per_second_per_gpu:868.6269023625428 mfu:12.764224838367847 
Step 826 | loss:2.2410905361175537 lr:0.00018831051166703832 tokens_per_second_per_gpu:874.7216239691832 mfu:12.853785035850594 
Step 827 | loss:2.195971727371216 lr:0.00018828096779285303 tokens_per_second_per_gpu:875.097810212001 mfu:12.85931298550466 
Step 828 | loss:2.212890625 lr:0.00018825138895494533 tokens_per_second_per_gpu:898.8465927217547 mfu:13.208294577909307 
Step 829 | loss:2.2699689865112305 lr:0.00018822177516502998 tokens_per_second_per_gpu:887.8008303547706 mfu:13.045980247119074 
Step 830 | loss:2.230287551879883 lr:0.0001881921264348355 tokens_per_second_per_gpu:896.6808020573806 mfu:13.176468901180067 
Step 831 | loss:2.226921558380127 lr:0.00018816244277610432 tokens_per_second_per_gpu:833.1279255797665 mfu:12.242577489022642 
Step 832 | loss:2.203295946121216 lr:0.00018813272420059265 tokens_per_second_per_gpu:833.2278314868707 mfu:12.24404557786204 
Step 833 | loss:2.1826298236846924 lr:0.00018810297072007054 tokens_per_second_per_gpu:853.9251421853243 mfu:12.548186661434366 
Step 834 | loss:2.15838885307312 lr:0.00018807318234632185 tokens_per_second_per_gpu:891.4724014443584 mfu:13.099932938165235 
Step 835 | loss:2.1929304599761963 lr:0.00018804335909114434 tokens_per_second_per_gpu:901.3574000246617 mfu:13.245190175838582 
Step 836 | loss:2.1704788208007812 lr:0.00018801350096634946 tokens_per_second_per_gpu:882.3649243760935 mfu:12.966101157577473 
Step 837 | loss:2.1745145320892334 lr:0.0001879836079837626 tokens_per_second_per_gpu:877.5417189486418 mfu:12.8952255280636 
Step 838 | loss:2.160379648208618 lr:0.00018795368015522287 tokens_per_second_per_gpu:865.4447846547325 mfu:12.717464525310342 
Step 839 | loss:2.1891331672668457 lr:0.00018792371749258314 tokens_per_second_per_gpu:848.9396718082695 mfu:12.474926594719108 
Step 840 | loss:2.128190755844116 lr:0.00018789372000771026 tokens_per_second_per_gpu:866.8211821998842 mfu:12.737690295068925 
Step 841 | loss:2.24538254737854 lr:0.00018786368771248464 tokens_per_second_per_gpu:893.5171424211387 mfu:13.129979824225131 
Step 842 | loss:2.217623710632324 lr:0.00018783362061880062 tokens_per_second_per_gpu:873.4987391151838 mfu:12.835815091349188 
Step 843 | loss:2.1852002143859863 lr:0.00018780351873856627 tokens_per_second_per_gpu:893.8571963309935 mfu:13.13497681954124 
Step 844 | loss:2.188889265060425 lr:0.0001877733820837035 tokens_per_second_per_gpu:906.7027450474279 mfu:13.32373849793598 
Step 845 | loss:2.2290685176849365 lr:0.00018774321066614795 tokens_per_second_per_gpu:869.6747050285468 mfu:12.779622000001615 
Step 846 | loss:2.2174839973449707 lr:0.00018771300449784898 tokens_per_second_per_gpu:890.5790531439621 mfu:13.086805439426458 
Step 847 | loss:2.1412014961242676 lr:0.00018768276359076977 tokens_per_second_per_gpu:863.6274301463019 mfu:12.690759018615195 
Step 848 | loss:2.1864333152770996 lr:0.00018765248795688726 tokens_per_second_per_gpu:869.973494207385 mfu:12.784012621852712 
Step 849 | loss:2.1988465785980225 lr:0.00018762217760819212 tokens_per_second_per_gpu:886.905866554691 mfu:13.032829009072744 
Step 850 | loss:2.2219772338867188 lr:0.0001875918325566888 tokens_per_second_per_gpu:892.1245646372822 mfu:13.109516290468907 
Step 851 | loss:2.11826753616333 lr:0.00018756145281439545 tokens_per_second_per_gpu:897.4346334127628 mfu:13.18754623816346 
Step 852 | loss:2.20184063911438 lr:0.00018753103839334398 tokens_per_second_per_gpu:886.9331783187605 mfu:13.033230347663993 
Step 853 | loss:2.1750316619873047 lr:0.00018750058930558006 tokens_per_second_per_gpu:882.0880237148464 mfu:12.962032181255834 
Step 854 | loss:2.2269575595855713 lr:0.00018747010556316305 tokens_per_second_per_gpu:900.4182837571927 mfu:13.231390129864021 
Step 855 | loss:2.1650071144104004 lr:0.00018743958717816605 tokens_per_second_per_gpu:842.6899621392255 mfu:12.383088891819012 
Step 856 | loss:2.243131160736084 lr:0.0001874090341626759 tokens_per_second_per_gpu:856.9188614031108 mfu:12.592178512360048 
Step 857 | loss:2.2198173999786377 lr:0.00018737844652879312 tokens_per_second_per_gpu:886.5694298719087 mfu:13.027885167877834 
Step 858 | loss:2.1449832916259766 lr:0.00018734782428863196 tokens_per_second_per_gpu:878.7719817561502 mfu:12.913303889489672 
Step 859 | loss:2.1739814281463623 lr:0.00018731716745432037 tokens_per_second_per_gpu:864.8201270452537 mfu:12.70828535971842 
Step 860 | loss:2.1962921619415283 lr:0.00018728647603800003 tokens_per_second_per_gpu:893.8728809565922 mfu:13.1352073006455 
Step 861 | loss:2.2011685371398926 lr:0.00018725575005182625 tokens_per_second_per_gpu:868.8552633700823 mfu:12.76758053830832 
Step 862 | loss:2.207547187805176 lr:0.00018722498950796813 tokens_per_second_per_gpu:821.6082938249682 mfu:12.073299782594805 
Step 863 | loss:2.2117326259613037 lr:0.00018719419441860834 tokens_per_second_per_gpu:877.6807926990202 mfu:12.897269177200089 
Step 864 | loss:2.169611692428589 lr:0.0001871633647959433 tokens_per_second_per_gpu:878.9405679691813 mfu:12.915781215856061 
Step 865 | loss:2.181431770324707 lr:0.00018713250065218313 tokens_per_second_per_gpu:870.9229956434962 mfu:12.797965274921493 
Step 866 | loss:2.211200714111328 lr:0.00018710160199955156 tokens_per_second_per_gpu:890.1482911419504 mfu:13.08047551454093 
Step 867 | loss:2.2154064178466797 lr:0.00018707066885028604 tokens_per_second_per_gpu:879.981731819604 mfu:12.931080821986413 
Step 868 | loss:2.182394027709961 lr:0.00018703970121663766 tokens_per_second_per_gpu:878.4575828505591 mfu:12.908683887151515 
Step 869 | loss:2.2100565433502197 lr:0.00018700869911087115 tokens_per_second_per_gpu:884.4315847139975 mfu:12.996470142403748 
Step 870 | loss:2.2215518951416016 lr:0.00018697766254526492 tokens_per_second_per_gpu:878.5970310014342 mfu:12.910733037996627 
Step 871 | loss:2.218463182449341 lr:0.000186946591532111 tokens_per_second_per_gpu:831.1623592480272 mfu:12.21369405181294 
Step 872 | loss:2.188504695892334 lr:0.0001869154860837151 tokens_per_second_per_gpu:849.4199902336173 mfu:12.48198473712579 
Step 873 | loss:2.212244987487793 lr:0.00018688434621239657 tokens_per_second_per_gpu:871.0683356153171 mfu:12.80010100439669 
Step 874 | loss:2.1458897590637207 lr:0.00018685317193048833 tokens_per_second_per_gpu:902.3725702638683 mfu:13.260107813258294 
Step 875 | loss:2.2125158309936523 lr:0.00018682196325033696 tokens_per_second_per_gpu:883.0698644721797 mfu:12.976460051435756 
Step 876 | loss:2.2104859352111816 lr:0.00018679072018430273 tokens_per_second_per_gpu:887.6677493626948 mfu:13.044024659858367 
Step 877 | loss:2.1675047874450684 lr:0.00018675944274475944 tokens_per_second_per_gpu:869.0158974083622 mfu:12.769941009732499 
Step 878 | loss:2.1716222763061523 lr:0.0001867281309440945 tokens_per_second_per_gpu:872.7515898313117 mfu:12.82483594550276 
Step 879 | loss:2.1819798946380615 lr:0.00018669678479470907 tokens_per_second_per_gpu:879.4538436815735 mfu:12.92332365620557 
Step 880 | loss:2.1891398429870605 lr:0.0001866654043090177 tokens_per_second_per_gpu:863.4867993351668 mfu:12.688692488914528 
Step 881 | loss:2.201566219329834 lr:0.00018663398949944865 tokens_per_second_per_gpu:836.2055127830204 mfu:12.287801756098842 
Step 882 | loss:2.2009689807891846 lr:0.00018660254037844388 tokens_per_second_per_gpu:839.1313347752347 mfu:12.330795876640227 
Step 883 | loss:2.202293872833252 lr:0.00018657105695845874 tokens_per_second_per_gpu:860.1372267720623 mfu:12.639471474470227 
Step 884 | loss:2.188159227371216 lr:0.00018653953925196225 tokens_per_second_per_gpu:879.0210771134253 mfu:12.916964274791814 
Step 885 | loss:2.2134180068969727 lr:0.00018650798727143706 tokens_per_second_per_gpu:874.1492921726667 mfu:12.845374783171323 
Step 886 | loss:2.1784961223602295 lr:0.0001864764010293793 tokens_per_second_per_gpu:894.216033115626 mfu:13.140249823850535 
Step 887 | loss:2.1584582328796387 lr:0.00018644478053829878 tokens_per_second_per_gpu:848.7500762870799 mfu:12.472140542555364 
Step 888 | loss:2.2024126052856445 lr:0.00018641312581071877 tokens_per_second_per_gpu:886.7864687404847 mfu:13.031074492212175 
Step 889 | loss:2.204922676086426 lr:0.00018638143685917612 tokens_per_second_per_gpu:889.5766244975881 mfu:13.072075036083046 
Step 890 | loss:2.188857078552246 lr:0.0001863497136962213 tokens_per_second_per_gpu:885.6667237934383 mfu:13.014620159256506 
Step 891 | loss:2.2039506435394287 lr:0.00018631795633441826 tokens_per_second_per_gpu:864.2737267924994 mfu:12.700256163686237 
Step 892 | loss:2.133845090866089 lr:0.00018628616478634453 tokens_per_second_per_gpu:844.8490451692916 mfu:12.414816001773255 
Step 893 | loss:2.1396377086639404 lr:0.00018625433906459116 tokens_per_second_per_gpu:857.744923110437 mfu:12.604317253785164 
Step 894 | loss:2.220963478088379 lr:0.00018622247918176276 tokens_per_second_per_gpu:872.5016545690725 mfu:12.82116321803648 
Step 895 | loss:2.1753122806549072 lr:0.00018619058515047745 tokens_per_second_per_gpu:871.4981304736731 mfu:12.806416717381758 
Step 896 | loss:2.132375717163086 lr:0.00018615865698336684 tokens_per_second_per_gpu:873.2492872602138 mfu:12.832149467414995 
Step 897 | loss:2.192464828491211 lr:0.00018612669469307615 tokens_per_second_per_gpu:831.0570142547734 mfu:12.212146037152294 
Step 898 | loss:2.138176679611206 lr:0.000186094698292264 tokens_per_second_per_gpu:879.6435812621509 mfu:12.926111795891538 
Step 899 | loss:2.1780266761779785 lr:0.00018606266779360266 tokens_per_second_per_gpu:881.1803356997502 mfu:12.948693964495257 
Step 900 | loss:2.186756134033203 lr:0.00018603060320977776 tokens_per_second_per_gpu:865.4326585094394 mfu:12.71728633506028 
Step 901 | loss:2.170529842376709 lr:0.00018599850455348853 tokens_per_second_per_gpu:889.7410374799936 mfu:13.074491038014441 
Step 902 | loss:2.1662356853485107 lr:0.00018596637183744763 tokens_per_second_per_gpu:899.1684349977864 mfu:13.213023958455299 
Step 903 | loss:2.206350803375244 lr:0.00018593420507438126 tokens_per_second_per_gpu:890.337353634288 mfu:13.083253733997564 
Step 904 | loss:2.192270040512085 lr:0.0001859020042770291 tokens_per_second_per_gpu:883.1422281209168 mfu:12.977523414635876 
Step 905 | loss:2.1018662452697754 lr:0.00018586976945814425 tokens_per_second_per_gpu:859.983628022577 mfu:12.63721438461037 
Step 906 | loss:2.160953998565674 lr:0.00018583750063049336 tokens_per_second_per_gpu:875.8251167876537 mfu:12.870000548407448 
Step 907 | loss:2.192464590072632 lr:0.0001858051978068565 tokens_per_second_per_gpu:849.9978380313108 mfu:12.490476045870723 
Step 908 | loss:2.1777265071868896 lr:0.00018577286100002723 tokens_per_second_per_gpu:883.7405194404557 mfu:12.986315135109496 
Step 909 | loss:2.177412509918213 lr:0.00018574049022281253 tokens_per_second_per_gpu:897.2699814091495 mfu:13.185126723883519 
Step 910 | loss:2.1430182456970215 lr:0.0001857080854880329 tokens_per_second_per_gpu:868.920136858743 mfu:12.768533835740234 
Step 911 | loss:2.169964075088501 lr:0.00018567564680852224 tokens_per_second_per_gpu:877.6185996848981 mfu:12.896355268577791 
Step 912 | loss:2.1762399673461914 lr:0.0001856431741971279 tokens_per_second_per_gpu:870.0967345090796 mfu:12.785823602972107 
Step 913 | loss:2.1571168899536133 lr:0.00018561066766671064 tokens_per_second_per_gpu:897.1299779027952 mfu:13.183069412247871 
Step 914 | loss:2.1464548110961914 lr:0.00018557812723014476 tokens_per_second_per_gpu:882.1456493650445 mfu:12.962878973766617 
Step 915 | loss:2.1970572471618652 lr:0.00018554555290031788 tokens_per_second_per_gpu:903.0011670508001 mfu:13.269344863940526 
Step 916 | loss:2.1915969848632812 lr:0.00018551294469013106 tokens_per_second_per_gpu:887.7448048503409 mfu:13.045156968294439 
Step 917 | loss:2.18380069732666 lr:0.00018548030261249885 tokens_per_second_per_gpu:879.1177321111254 mfu:12.918384592443777 
Step 918 | loss:2.1906754970550537 lr:0.00018544762668034912 tokens_per_second_per_gpu:877.9873307663937 mfu:12.901773666760374 
Step 919 | loss:2.1831095218658447 lr:0.00018541491690662317 tokens_per_second_per_gpu:866.4392335099875 mfu:12.732077667896888 
Step 920 | loss:2.2019283771514893 lr:0.00018538217330427582 tokens_per_second_per_gpu:887.3107226165303 mfu:13.038778253548637 
Step 921 | loss:2.1802403926849365 lr:0.00018534939588627503 tokens_per_second_per_gpu:901.1529158968215 mfu:13.242185339842216 
Step 922 | loss:2.249444007873535 lr:0.00018531658466560246 tokens_per_second_per_gpu:882.6974425133742 mfu:12.970987416862721 
Step 923 | loss:2.1493115425109863 lr:0.00018528373965525296 tokens_per_second_per_gpu:837.9230895614485 mfu:12.313041057480584 
Step 924 | loss:2.179760217666626 lr:0.00018525086086823483 tokens_per_second_per_gpu:860.9250854956344 mfu:12.651048833933988 
Step 925 | loss:2.1650872230529785 lr:0.00018521794831756968 tokens_per_second_per_gpu:888.9009867376486 mfu:13.062146731705525 
Step 926 | loss:2.151995897293091 lr:0.00018518500201629258 tokens_per_second_per_gpu:873.2603357721352 mfu:12.832311822149705 
Step 927 | loss:2.165329694747925 lr:0.00018515202197745193 tokens_per_second_per_gpu:895.5538845873158 mfu:13.159909170042258 
Step 928 | loss:2.189267158508301 lr:0.00018511900821410946 tokens_per_second_per_gpu:840.7131415213884 mfu:12.35404007608171 
Step 929 | loss:2.1029014587402344 lr:0.0001850859607393403 tokens_per_second_per_gpu:853.179832495632 mfu:12.537234547900269 
Step 930 | loss:2.131218433380127 lr:0.00018505287956623297 tokens_per_second_per_gpu:888.4328309036491 mfu:13.055267315113303 
Step 931 | loss:2.164335250854492 lr:0.00018501976470788924 tokens_per_second_per_gpu:904.4379684540979 mfu:13.290458251184111 
Step 932 | loss:2.232882022857666 lr:0.00018498661617742426 tokens_per_second_per_gpu:905.54714169586 mfu:13.30675723594275 
Step 933 | loss:2.1444387435913086 lr:0.00018495343398796654 tokens_per_second_per_gpu:877.8695721738765 mfu:12.900043237795474 
Step 934 | loss:2.148636817932129 lr:0.0001849202181526579 tokens_per_second_per_gpu:888.4335858576718 mfu:13.055278408947563 
Step 935 | loss:2.169005870819092 lr:0.0001848869686846535 tokens_per_second_per_gpu:842.3947684457398 mfu:12.378751104600736 
Step 936 | loss:2.2306363582611084 lr:0.00018485368559712179 tokens_per_second_per_gpu:845.144747228561 mfu:12.419161259281879 
Step 937 | loss:2.1948447227478027 lr:0.00018482036890324452 tokens_per_second_per_gpu:892.4780611739988 mfu:13.114710821356637 
Step 938 | loss:2.1569442749023438 lr:0.00018478701861621686 tokens_per_second_per_gpu:863.8850203906852 mfu:12.694544233863002 
Step 939 | loss:2.1779141426086426 lr:0.00018475363474924715 tokens_per_second_per_gpu:890.9306401975543 mfu:13.09197191100373 
Step 940 | loss:2.205378532409668 lr:0.00018472021731555716 tokens_per_second_per_gpu:848.5687918302187 mfu:12.469476619113916 
Step 941 | loss:2.160007953643799 lr:0.0001846867663283818 tokens_per_second_per_gpu:888.7785540686361 mfu:13.060347618518279 
Step 942 | loss:2.187723159790039 lr:0.00018465328180096934 tokens_per_second_per_gpu:859.4091015000629 mfu:12.62877188105789 
Step 943 | loss:2.1694164276123047 lr:0.00018461976374658143 tokens_per_second_per_gpu:869.1322239315289 mfu:12.77165039484632 
Step 944 | loss:2.136322498321533 lr:0.00018458621217849286 tokens_per_second_per_gpu:863.4614816408973 mfu:12.688320452610832 
Step 945 | loss:2.182891607284546 lr:0.00018455262710999175 tokens_per_second_per_gpu:887.1109948320361 mfu:13.035843310662552 
Step 946 | loss:2.178098440170288 lr:0.0001845190085543795 tokens_per_second_per_gpu:872.9022009813174 mfu:12.827049133439502 
Step 947 | loss:2.1824474334716797 lr:0.00018448535652497073 tokens_per_second_per_gpu:903.8536330009794 mfu:13.281871608191189 
Step 948 | loss:2.2067670822143555 lr:0.00018445167103509332 tokens_per_second_per_gpu:871.9478519989373 mfu:12.813025247059475 
Step 949 | loss:2.1872920989990234 lr:0.00018441795209808853 tokens_per_second_per_gpu:880.7678967632025 mfu:12.94263329183606 
Step 950 | loss:2.1737661361694336 lr:0.00018438419972731067 tokens_per_second_per_gpu:884.374485583838 mfu:12.995631086954916 
Step 951 | loss:2.187316656112671 lr:0.0001843504139361274 tokens_per_second_per_gpu:854.0320207691171 mfu:12.549757211771027 
Step 952 | loss:2.2340054512023926 lr:0.0001843165947379196 tokens_per_second_per_gpu:889.8349916163058 mfu:13.07587166727785 
Step 953 | loss:2.1977736949920654 lr:0.0001842827421460814 tokens_per_second_per_gpu:877.7380364207457 mfu:12.89811035738079 
Step 954 | loss:2.152860641479492 lr:0.00018424885617402014 tokens_per_second_per_gpu:863.7538214500167 mfu:12.692616302811484 
Step 955 | loss:2.2017757892608643 lr:0.00018421493683515633 tokens_per_second_per_gpu:877.6346803576527 mfu:12.896591569482164 
Step 956 | loss:2.202787160873413 lr:0.0001841809841429238 tokens_per_second_per_gpu:896.2536004717743 mfu:13.170191295599174 
Step 957 | loss:2.2204232215881348 lr:0.00018414699811076949 tokens_per_second_per_gpu:880.0847101945612 mfu:12.932594059865496 
Step 958 | loss:2.122915267944336 lr:0.0001841129787521536 tokens_per_second_per_gpu:908.7568395249323 mfu:13.353922831023986 
Step 959 | loss:2.1405701637268066 lr:0.0001840789260805495 tokens_per_second_per_gpu:863.5748531207058 mfu:12.689986414204467 
Step 960 | loss:2.2021517753601074 lr:0.0001840448401094438 tokens_per_second_per_gpu:903.2993738932552 mfu:13.273726928524393 
Step 961 | loss:2.196195125579834 lr:0.00018401072085233626 tokens_per_second_per_gpu:898.7148402787362 mfu:13.20635851329846 
Step 962 | loss:2.200442314147949 lr:0.0001839765683227398 tokens_per_second_per_gpu:860.6031397167945 mfu:12.646317932443718 
Step 963 | loss:2.1554272174835205 lr:0.00018394238253418056 tokens_per_second_per_gpu:887.2562424072413 mfu:13.037977682395805 
Step 964 | loss:2.169292449951172 lr:0.00018390816350019785 tokens_per_second_per_gpu:875.4871836583199 mfu:12.865034717356835 
Step 965 | loss:2.14835524559021 lr:0.00018387391123434412 tokens_per_second_per_gpu:894.0434160116572 mfu:13.137713264690309 
Step 966 | loss:2.16998028755188 lr:0.00018383962575018503 tokens_per_second_per_gpu:884.4989533664444 mfu:12.997460105556572 
Step 967 | loss:2.211986780166626 lr:0.0001838053070612993 tokens_per_second_per_gpu:869.2289024572015 mfu:12.773071058235136 
Step 968 | loss:2.169811725616455 lr:0.00018377095518127897 tokens_per_second_per_gpu:822.2465580782336 mfu:12.082678893940328 
Step 969 | loss:2.205091714859009 lr:0.00018373657012372898 tokens_per_second_per_gpu:884.3211502998065 mfu:12.994847340152525 
Step 970 | loss:2.1470894813537598 lr:0.00018370215190226767 tokens_per_second_per_gpu:856.0818563630143 mfu:12.579878961777881 
Step 971 | loss:2.1643800735473633 lr:0.00018366770053052634 tokens_per_second_per_gpu:833.3035334460076 mfu:12.24515799658232 
Step 972 | loss:2.201085090637207 lr:0.00018363321602214946 tokens_per_second_per_gpu:881.8341656439569 mfu:12.958301809234136 
Step 973 | loss:2.2115769386291504 lr:0.0001835986983907947 tokens_per_second_per_gpu:890.9087763779341 mfu:13.091650628403919 
Step 974 | loss:2.188400983810425 lr:0.00018356414765013267 tokens_per_second_per_gpu:870.0780742087302 mfu:12.785549395175222 
Step 975 | loss:2.1811470985412598 lr:0.00018352956381384737 tokens_per_second_per_gpu:878.337064077669 mfu:12.906912898122473 
Step 976 | loss:2.1959848403930664 lr:0.0001834949468956356 tokens_per_second_per_gpu:885.5943354053336 mfu:13.013556432518428 
Step 977 | loss:2.171266555786133 lr:0.00018346029690920746 tokens_per_second_per_gpu:851.0432361943457 mfu:12.505837874018459 
Step 978 | loss:2.151564598083496 lr:0.00018342561386828615 tokens_per_second_per_gpu:862.4102755598241 mfu:12.672873278762331 
Step 979 | loss:2.148872137069702 lr:0.0001833908977866078 tokens_per_second_per_gpu:866.7835098997347 mfu:12.737136711351935 
Step 980 | loss:2.168149471282959 lr:0.00018335614867792183 tokens_per_second_per_gpu:887.0458826773789 mfu:13.034886506101818 
Step 981 | loss:2.2133429050445557 lr:0.0001833213665559906 tokens_per_second_per_gpu:867.915082730782 mfu:12.753764851692964 
Step 982 | loss:2.135127067565918 lr:0.00018328655143458957 tokens_per_second_per_gpu:851.2694145367767 mfu:12.509161500317052 
Step 983 | loss:2.1302661895751953 lr:0.00018325170332750732 tokens_per_second_per_gpu:875.5331736472989 mfu:12.865710527141275 
Step 984 | loss:2.1430656909942627 lr:0.00018321682224854544 tokens_per_second_per_gpu:837.3468470705399 mfu:12.304573338261465 
Step 985 | loss:2.1817824840545654 lr:0.0001831819082115186 tokens_per_second_per_gpu:859.2345960114095 mfu:12.626207572622768 
Step 986 | loss:2.1244349479675293 lr:0.00018314696123025454 tokens_per_second_per_gpu:860.9000017244142 mfu:12.650680235062852 
Step 987 | loss:2.1496288776397705 lr:0.00018311198131859403 tokens_per_second_per_gpu:862.9484814836046 mfu:12.680782061465 
Step 988 | loss:2.173630475997925 lr:0.0001830769684903908 tokens_per_second_per_gpu:881.1043964914417 mfu:12.947578059465997 
Step 989 | loss:2.184420585632324 lr:0.00018304192275951184 tokens_per_second_per_gpu:903.9564277622924 mfu:13.283382147920083 
Step 990 | loss:2.1362104415893555 lr:0.00018300684413983693 tokens_per_second_per_gpu:870.9921671041965 mfu:12.798981729827942 
Step 991 | loss:2.1732661724090576 lr:0.000182971732645259 tokens_per_second_per_gpu:896.7518612249219 mfu:13.177513095400691 
Step 992 | loss:2.180218458175659 lr:0.00018293658828968397 tokens_per_second_per_gpu:868.6926951850714 mfu:12.765191645149013 
Step 993 | loss:2.1657752990722656 lr:0.0001829014110870308 tokens_per_second_per_gpu:875.2084077185464 mfu:12.860938184351562 
Step 994 | loss:2.1232776641845703 lr:0.00018286620105123142 tokens_per_second_per_gpu:864.7249298743242 mfu:12.706886464415483 
Step 995 | loss:2.147423028945923 lr:0.00018283095819623078 tokens_per_second_per_gpu:883.9089527673121 mfu:12.98879021485711 
Step 996 | loss:2.1597702503204346 lr:0.00018279568253598685 tokens_per_second_per_gpu:887.9676137608794 mfu:13.048431081751403 
Step 997 | loss:2.16556978225708 lr:0.00018276037408447059 tokens_per_second_per_gpu:867.0697735681921 mfu:12.74134327439679 
Step 998 | loss:2.177845001220703 lr:0.00018272503285566587 tokens_per_second_per_gpu:839.5262161685356 mfu:12.33659854620396 
Step 999 | loss:2.1587612628936768 lr:0.00018268965886356964 tokens_per_second_per_gpu:848.0154386568678 mfu:12.461345251894612 
Step 1000 | loss:2.187852382659912 lr:0.00018265425212219175 tokens_per_second_per_gpu:825.6099352616955 mfu:12.132102763347522 
Step 1001 | loss:2.1527318954467773 lr:0.00018261881264555516 tokens_per_second_per_gpu:872.7564110163239 mfu:12.82490679144285 
Step 1002 | loss:2.1917426586151123 lr:0.00018258334044769558 tokens_per_second_per_gpu:904.7565608895851 mfu:13.295139876249259 
Step 1003 | loss:2.115631580352783 lr:0.00018254783554266183 tokens_per_second_per_gpu:873.0785090555528 mfu:12.829639930356151 
Step 1004 | loss:2.1506989002227783 lr:0.00018251229794451567 tokens_per_second_per_gpu:882.6388122499259 mfu:12.970125861846464 
Step 1005 | loss:2.1499459743499756 lr:0.00018247672766733176 tokens_per_second_per_gpu:870.4897740258737 mfu:12.791599206685369 
Step 1006 | loss:2.1720101833343506 lr:0.0001824411247251977 tokens_per_second_per_gpu:877.4156008160957 mfu:12.8933722580398 
Step 1007 | loss:2.1966631412506104 lr:0.00018240548913221416 tokens_per_second_per_gpu:903.9725421698962 mfu:13.283618944548454 
Step 1008 | loss:2.174565553665161 lr:0.00018236982090249451 tokens_per_second_per_gpu:887.9986119619563 mfu:13.048886591484123 
Step 1009 | loss:2.1599538326263428 lr:0.00018233412005016524 tokens_per_second_per_gpu:872.4762513752606 mfu:12.820789925341371 
Step 1010 | loss:2.1138734817504883 lr:0.00018229838658936564 tokens_per_second_per_gpu:853.3620743880776 mfu:12.539912540584837 
Step 1011 | loss:2.168031692504883 lr:0.00018226262053424802 tokens_per_second_per_gpu:886.06039783236 mfu:13.020405087091639 
Step 1012 | loss:2.178645133972168 lr:0.00018222682189897752 tokens_per_second_per_gpu:899.3980861634086 mfu:13.2163986169012 
Step 1013 | loss:2.1666057109832764 lr:0.0001821909906977322 tokens_per_second_per_gpu:838.0708883156311 mfu:12.31521291806202 
Step 1014 | loss:2.171940565109253 lr:0.00018215512694470305 tokens_per_second_per_gpu:902.5238178785596 mfu:13.262330353862247 
Step 1015 | loss:2.1533284187316895 lr:0.0001821192306540939 tokens_per_second_per_gpu:862.1131328793201 mfu:12.668506851735133 
Step 1016 | loss:2.162555694580078 lr:0.0001820833018401215 tokens_per_second_per_gpu:878.5641579425956 mfu:12.910249977763288 
Step 1017 | loss:2.2242066860198975 lr:0.00018204734051701548 tokens_per_second_per_gpu:868.1433118872338 mfu:12.757118614119268 
Step 1018 | loss:2.159262180328369 lr:0.00018201134669901836 tokens_per_second_per_gpu:862.5627280707762 mfu:12.675113524973534 
Step 1019 | loss:2.1227240562438965 lr:0.00018197532040038547 tokens_per_second_per_gpu:852.7701593267462 mfu:12.531214517408833 
Step 1020 | loss:2.1557226181030273 lr:0.0001819392616353851 tokens_per_second_per_gpu:883.0291507171497 mfu:12.97586177440588 
Step 1021 | loss:2.2095296382904053 lr:0.00018190317041829828 tokens_per_second_per_gpu:891.2445423064448 mfu:13.09658461305592 
Step 1022 | loss:2.1239006519317627 lr:0.00018186704676341898 tokens_per_second_per_gpu:872.7623453138685 mfu:12.824993994254449 
Step 1023 | loss:2.1885690689086914 lr:0.00018183089068505402 tokens_per_second_per_gpu:857.5990627527148 mfu:12.602173877387418 
Step 1024 | loss:2.2067980766296387 lr:0.000181794702197523 tokens_per_second_per_gpu:868.6147369372741 mfu:12.764046070909734 
Step 1025 | loss:2.1802072525024414 lr:0.00018175848131515837 tokens_per_second_per_gpu:856.7858947273006 mfu:12.590224604944293 
Step 1026 | loss:2.2267284393310547 lr:0.00018172222805230547 tokens_per_second_per_gpu:833.662433902225 mfu:12.250431936527413 
Step 1027 | loss:2.132678270339966 lr:0.0001816859424233224 tokens_per_second_per_gpu:880.4150354179751 mfu:12.937448094906284 
Step 1028 | loss:2.1524226665496826 lr:0.00018164962444258014 tokens_per_second_per_gpu:865.137326738984 mfu:12.712946518840274 
Step 1029 | loss:2.151948928833008 lr:0.0001816132741244624 tokens_per_second_per_gpu:852.6879087290326 mfu:12.530005868310525 
Step 1030 | loss:2.105640172958374 lr:0.00018157689148336578 tokens_per_second_per_gpu:875.0110809937403 mfu:12.858038524353475 
Step 1031 | loss:2.1288771629333496 lr:0.0001815404765336996 tokens_per_second_per_gpu:899.6139786369869 mfu:13.219571095287685 
Step 1032 | loss:2.235403060913086 lr:0.00018150402928988606 tokens_per_second_per_gpu:875.7280168859578 mfu:12.86857369301803 
Step 1033 | loss:2.1748225688934326 lr:0.00018146754976636006 tokens_per_second_per_gpu:849.7421801366278 mfu:12.48671922595119 
Step 1034 | loss:2.13645076751709 lr:0.0001814310379775694 tokens_per_second_per_gpu:898.453880169912 mfu:13.202523778852846 
Step 1035 | loss:2.180678367614746 lr:0.00018139449393797454 tokens_per_second_per_gpu:869.6808532111174 mfu:12.779712345792733 
Step 1036 | loss:2.133986473083496 lr:0.00018135791766204877 tokens_per_second_per_gpu:870.8505867841994 mfu:12.796901247365083 
Step 1037 | loss:2.1325154304504395 lr:0.00018132130916427816 tokens_per_second_per_gpu:875.8130914578427 mfu:12.86982383961217 
Step 1038 | loss:2.1339128017425537 lr:0.00018128466845916154 tokens_per_second_per_gpu:869.660853934817 mfu:12.779418462125752 
Step 1039 | loss:2.173882484436035 lr:0.00018124799556121045 tokens_per_second_per_gpu:885.3111124513973 mfu:13.00939455190709 
Step 1040 | loss:2.1767663955688477 lr:0.00018121129048494922 tokens_per_second_per_gpu:895.5269503359827 mfu:13.15951337889311 
Step 1041 | loss:2.0598747730255127 lr:0.0001811745532449149 tokens_per_second_per_gpu:870.667021774183 mfu:12.794203811844799 
Step 1042 | loss:2.152597188949585 lr:0.00018113778385565733 tokens_per_second_per_gpu:860.6738921645886 mfu:12.647357619505046 
Step 1043 | loss:2.1871743202209473 lr:0.000181100982331739 tokens_per_second_per_gpu:872.0938182388197 mfu:12.815170179365397 
Step 1044 | loss:2.1844048500061035 lr:0.00018106414868773518 tokens_per_second_per_gpu:883.1680253604776 mfu:12.977902497720992 
Step 1045 | loss:2.1516096591949463 lr:0.0001810272829382339 tokens_per_second_per_gpu:867.991612885764 mfu:12.754889440515214 
Step 1046 | loss:2.193446636199951 lr:0.00018099038509783582 tokens_per_second_per_gpu:878.055607822856 mfu:12.902776978651378 
Step 1047 | loss:2.146817684173584 lr:0.00018095345518115435 tokens_per_second_per_gpu:884.1300599219707 mfu:12.992039321496286 
Step 1048 | loss:2.158112049102783 lr:0.0001809164932028156 tokens_per_second_per_gpu:895.955413138562 mfu:13.16580951769807 
Step 1049 | loss:2.1182780265808105 lr:0.0001808794991774584 tokens_per_second_per_gpu:888.1170592207326 mfu:13.050627140203485 
Step 1050 | loss:2.173227548599243 lr:0.00018084247311973427 tokens_per_second_per_gpu:895.7972981145576 mfu:13.163486062470945 
Step 1051 | loss:2.1959989070892334 lr:0.00018080541504430733 tokens_per_second_per_gpu:882.1477663533723 mfu:12.962910082306916 
Step 1052 | loss:2.1771602630615234 lr:0.0001807683249658545 tokens_per_second_per_gpu:853.374375959429 mfu:12.540093308670842 
Step 1053 | loss:2.1549696922302246 lr:0.0001807312028990653 tokens_per_second_per_gpu:853.8632993546613 mfu:12.547277898658225 
Step 1054 | loss:2.126497507095337 lr:0.00018069404885864197 tokens_per_second_per_gpu:891.441379601176 mfu:13.099477081018508 
Step 1055 | loss:2.126894235610962 lr:0.0001806568628592994 tokens_per_second_per_gpu:876.3797827060221 mfu:12.878151206040753 
Step 1056 | loss:2.163292646408081 lr:0.00018061964491576505 tokens_per_second_per_gpu:892.8354537212016 mfu:13.119962603008398 
Step 1057 | loss:2.1342661380767822 lr:0.00018058239504277918 tokens_per_second_per_gpu:879.9584645379964 mfu:12.930738915912578 
Step 1058 | loss:2.107971668243408 lr:0.0001805451132550946 tokens_per_second_per_gpu:885.5677346239338 mfu:13.013165541614935 
Step 1059 | loss:2.120266914367676 lr:0.0001805077995674768 tokens_per_second_per_gpu:872.7202539294835 mfu:12.824375473353719 
Step 1060 | loss:2.149627685546875 lr:0.0001804704539947038 tokens_per_second_per_gpu:896.012204359803 mfu:13.166644048513078 
Step 1061 | loss:2.1292529106140137 lr:0.00018043307655156644 tokens_per_second_per_gpu:838.4181131406169 mfu:12.320315287932821 
Step 1062 | loss:2.1508352756500244 lr:0.000180395667252868 tokens_per_second_per_gpu:887.5734381238767 mfu:13.042638783075382 
Step 1063 | loss:2.1367383003234863 lr:0.0001803582261134245 tokens_per_second_per_gpu:848.0293464546072 mfu:12.46154962301974 
Step 1064 | loss:2.141310930252075 lr:0.00018032075314806448 tokens_per_second_per_gpu:806.5219695995921 mfu:11.851610546544823 
Step 1065 | loss:2.1861071586608887 lr:0.0001802832483716292 tokens_per_second_per_gpu:858.3142780638834 mfu:12.612683762603695 
Step 1066 | loss:2.1328506469726562 lr:0.00018024571179897235 tokens_per_second_per_gpu:883.1081190191339 mfu:12.977022191103647 
Step 1067 | loss:2.184809684753418 lr:0.00018020814344496037 tokens_per_second_per_gpu:875.0678396918813 mfu:12.858872577250795 
Step 1068 | loss:2.089726448059082 lr:0.00018017054332447222 tokens_per_second_per_gpu:866.471811912653 mfu:12.73255639824172 
Step 1069 | loss:2.166046142578125 lr:0.00018013291145239942 tokens_per_second_per_gpu:887.4267413278766 mfu:13.040483115455464 
Step 1070 | loss:2.192290782928467 lr:0.00018009524784364615 tokens_per_second_per_gpu:897.7548803647514 mfu:13.192252175877186 
Step 1071 | loss:2.1709144115448 lr:0.00018005755251312904 tokens_per_second_per_gpu:887.0143596893424 mfu:13.03442328477425 
Step 1072 | loss:2.1409897804260254 lr:0.00018001982547577737 tokens_per_second_per_gpu:844.812144606418 mfu:12.414273758515648 
Step 1073 | loss:2.169597625732422 lr:0.00017998206674653294 tokens_per_second_per_gpu:889.4392456331166 mfu:13.070056292812046 
Step 1074 | loss:2.214968204498291 lr:0.00017994427634035015 tokens_per_second_per_gpu:894.866395337423 mfu:13.149806711396636 
Step 1075 | loss:2.165700674057007 lr:0.00017990645427219584 tokens_per_second_per_gpu:893.4782431746854 mfu:13.129408210881794 
Step 1076 | loss:2.186716318130493 lr:0.00017986860055704953 tokens_per_second_per_gpu:861.3479330269661 mfu:12.657262457927887 
Step 1077 | loss:2.168945550918579 lr:0.00017983071520990315 tokens_per_second_per_gpu:859.842767937888 mfu:12.635144485800152 
Step 1078 | loss:2.186817169189453 lr:0.00017979279824576128 tokens_per_second_per_gpu:869.6911330183929 mfu:12.77986340463169 
Step 1079 | loss:2.131391763687134 lr:0.00017975484967964087 tokens_per_second_per_gpu:881.76352607671 mfu:12.957263780920286 
Step 1080 | loss:2.157134771347046 lr:0.00017971686952657153 tokens_per_second_per_gpu:869.2447054526016 mfu:12.773303278749903 
Step 1081 | loss:2.0842409133911133 lr:0.00017967885780159528 tokens_per_second_per_gpu:876.7511048270088 mfu:12.883607678810412 
Step 1082 | loss:2.1393065452575684 lr:0.00017964081451976672 tokens_per_second_per_gpu:897.6560864518988 mfu:13.190800427476482 
Step 1083 | loss:2.134894371032715 lr:0.0001796027396961529 tokens_per_second_per_gpu:852.4605613539861 mfu:12.526665063410729 
Step 1084 | loss:2.1922457218170166 lr:0.00017956463334583333 tokens_per_second_per_gpu:905.2425352931525 mfu:13.302281131644358 
Step 1085 | loss:2.1308975219726562 lr:0.0001795264954839001 tokens_per_second_per_gpu:864.5251869976439 mfu:12.70395129975402 
Step 1086 | loss:2.1900105476379395 lr:0.00017948832612545772 tokens_per_second_per_gpu:837.5234079394704 mfu:12.307167849924133 
Step 1087 | loss:2.1266653537750244 lr:0.00017945012528562318 tokens_per_second_per_gpu:856.2935651200161 mfu:12.582989961641312 
Step 1088 | loss:2.122424602508545 lr:0.00017941189297952597 tokens_per_second_per_gpu:887.3122685317298 mfu:13.038800970332028 
Step 1089 | loss:2.1517298221588135 lr:0.00017937362922230792 tokens_per_second_per_gpu:862.7087716108847 mfu:12.677259593184255 
Step 1090 | loss:2.1357169151306152 lr:0.00017933533402912354 tokens_per_second_per_gpu:889.1219608617449 mfu:13.065393883498494 
Step 1091 | loss:2.1493499279022217 lr:0.00017929700741513955 tokens_per_second_per_gpu:874.5521635080692 mfu:12.851294862657719 
Step 1092 | loss:2.171057939529419 lr:0.0001792586493955353 tokens_per_second_per_gpu:874.2382277743526 mfu:12.84668166649829 
Step 1093 | loss:2.140338182449341 lr:0.00017922025998550245 tokens_per_second_per_gpu:897.8903560950422 mfu:13.194242953133648 
Step 1094 | loss:2.1185529232025146 lr:0.0001791818392002452 tokens_per_second_per_gpu:849.5444542213132 mfu:12.483813699962319 
Step 1095 | loss:2.165389060974121 lr:0.0001791433870549801 tokens_per_second_per_gpu:867.14117529978 mfu:12.742392502498474 
Step 1096 | loss:2.1617398262023926 lr:0.0001791049035649361 tokens_per_second_per_gpu:877.5489611298926 mfu:12.895331949853617 
Step 1097 | loss:2.133312702178955 lr:0.00017906638874535462 tokens_per_second_per_gpu:896.4453839654745 mfu:13.173009499395556 
Step 1098 | loss:2.134138822555542 lr:0.00017902784261148954 tokens_per_second_per_gpu:863.8788814179122 mfu:12.694454023407237 
Step 1099 | loss:2.1839141845703125 lr:0.00017898926517860702 tokens_per_second_per_gpu:869.813301311559 mfu:12.781658632891203 
Step 1100 | loss:2.162198543548584 lr:0.00017895065646198567 tokens_per_second_per_gpu:848.5307707473919 mfu:12.46891791013486 
Step 1101 | loss:2.168844699859619 lr:0.0001789120164769165 tokens_per_second_per_gpu:861.3809702600591 mfu:12.65774793065512 
Step 1102 | loss:2.205371618270874 lr:0.0001788733452387029 tokens_per_second_per_gpu:855.4622694241226 mfu:12.570774308245486 
Step 1103 | loss:2.1346046924591064 lr:0.00017883464276266064 tokens_per_second_per_gpu:826.5971945399864 mfu:12.146610257149057 
Step 1104 | loss:2.108712673187256 lr:0.00017879590906411786 tokens_per_second_per_gpu:882.6083692519536 mfu:12.969678510665172 
Step 1105 | loss:2.1596882343292236 lr:0.00017875714415841503 tokens_per_second_per_gpu:867.9750815340666 mfu:12.754646517012185 
Step 1106 | loss:2.1087448596954346 lr:0.00017871834806090501 tokens_per_second_per_gpu:839.7240937548144 mfu:12.339506300954438 
Step 1107 | loss:2.1393775939941406 lr:0.00017867952078695306 tokens_per_second_per_gpu:878.2881489966624 mfu:12.906194104944115 
Step 1108 | loss:2.0856456756591797 lr:0.00017864066235193674 tokens_per_second_per_gpu:854.1572505272077 mfu:12.551597427385321 
Step 1109 | loss:2.129396438598633 lr:0.0001786017727712459 tokens_per_second_per_gpu:863.3468449050664 mfu:12.686635898440448 
Step 1110 | loss:2.1409754753112793 lr:0.0001785628520602828 tokens_per_second_per_gpu:879.2841827928121 mfu:12.920830537785523 
Step 1111 | loss:2.077305793762207 lr:0.00017852390023446205 tokens_per_second_per_gpu:832.1761679870783 mfu:12.228591682375791 
Step 1112 | loss:2.2102713584899902 lr:0.00017848491730921046 tokens_per_second_per_gpu:891.1482150035555 mfu:13.095169110785834 
Step 1113 | loss:2.1254451274871826 lr:0.00017844590329996733 tokens_per_second_per_gpu:846.153932782102 mfu:12.433990953450909 
Step 1114 | loss:2.114248752593994 lr:0.00017840685822218411 tokens_per_second_per_gpu:877.1620133756336 mfu:12.889645862855126 
Step 1115 | loss:2.1681766510009766 lr:0.00017836778209132464 tokens_per_second_per_gpu:834.3062721218512 mfu:12.259892955720453 
Step 1116 | loss:2.1204185485839844 lr:0.00017832867492286505 tokens_per_second_per_gpu:875.6773833233736 mfu:12.867829647242527 
Step 1117 | loss:2.156733274459839 lr:0.00017828953673229374 tokens_per_second_per_gpu:868.413438157937 mfu:12.761088042702044 
Step 1118 | loss:2.129359722137451 lr:0.00017825036753511144 tokens_per_second_per_gpu:889.3313805249135 mfu:13.068471245780259 
Step 1119 | loss:2.1063714027404785 lr:0.00017821116734683109 tokens_per_second_per_gpu:851.4943535370647 mfu:12.512466914835974 
Step 1120 | loss:2.1957879066467285 lr:0.00017817193618297798 tokens_per_second_per_gpu:874.6098891775503 mfu:12.85214312492337 
Step 1121 | loss:2.1206212043762207 lr:0.0001781326740590896 tokens_per_second_per_gpu:893.2702040137577 mfu:13.126351134687118 
Step 1122 | loss:2.1474802494049072 lr:0.00017809338099071577 tokens_per_second_per_gpu:891.8312507316745 mfu:13.105206126197903 
Step 1123 | loss:2.119347095489502 lr:0.0001780540569934185 tokens_per_second_per_gpu:884.7251308570095 mfu:13.00078371933724 
Step 1124 | loss:2.1984448432922363 lr:0.0001780147020827721 tokens_per_second_per_gpu:882.4977793275459 mfu:12.968053423235624 
Step 1125 | loss:2.129105567932129 lr:0.0001779753162743631 tokens_per_second_per_gpu:884.3291728575177 mfu:12.99496522935228 
Step 1126 | loss:2.1264469623565674 lr:0.00017793589958379021 tokens_per_second_per_gpu:897.7948939499363 mfu:13.192840164110684 
Step 1127 | loss:2.153491258621216 lr:0.00017789645202666456 tokens_per_second_per_gpu:889.228329774287 mfu:13.06695694436134 
Step 1128 | loss:2.1750237941741943 lr:0.00017785697361860926 tokens_per_second_per_gpu:901.5639304446895 mfu:13.248225081515608 
Step 1129 | loss:2.0912559032440186 lr:0.0001778174643752598 tokens_per_second_per_gpu:859.1619609751331 mfu:12.625140221460084 
Step 1130 | loss:2.1228034496307373 lr:0.00017777792431226383 tokens_per_second_per_gpu:876.0053544446582 mfu:12.872649089423263 
Step 1131 | loss:2.1944034099578857 lr:0.0001777383534452812 tokens_per_second_per_gpu:860.9612207072097 mfu:12.651579830572333 
Step 1132 | loss:2.168907880783081 lr:0.00017769875178998398 tokens_per_second_per_gpu:901.337653924388 mfu:13.244900012521178 
Step 1133 | loss:2.1578619480133057 lr:0.00017765911936205644 tokens_per_second_per_gpu:865.4552883757573 mfu:12.717618874498049 
Step 1134 | loss:2.152885913848877 lr:0.00017761945617719499 tokens_per_second_per_gpu:866.8013711130285 mfu:12.737399176792215 
Step 1135 | loss:2.154902935028076 lr:0.00017757976225110832 tokens_per_second_per_gpu:849.3625090978159 mfu:12.48114006821289 
Step 1136 | loss:2.139177083969116 lr:0.00017754003759951715 tokens_per_second_per_gpu:875.5397489567895 mfu:12.86580714944078 
Step 1137 | loss:2.1366353034973145 lr:0.00017750028223815448 tokens_per_second_per_gpu:910.0836760234594 mfu:13.373420315323505 
Step 1138 | loss:2.129331588745117 lr:0.00017746049618276545 tokens_per_second_per_gpu:879.6725895993677 mfu:12.926538065141795 
Step 1139 | loss:2.1544718742370605 lr:0.00017742067944910737 tokens_per_second_per_gpu:830.9450323434389 mfu:12.210500494871466 
Step 1140 | loss:2.1537606716156006 lr:0.00017738083205294964 tokens_per_second_per_gpu:895.9741373696144 mfu:13.16608466493842 
Step 1141 | loss:2.1876182556152344 lr:0.00017734095401007385 tokens_per_second_per_gpu:846.1885886816443 mfu:12.434500212020419 
Step 1142 | loss:2.0966734886169434 lr:0.0001773010453362737 tokens_per_second_per_gpu:890.0996144583664 mfu:13.079760224544776 
Step 1143 | loss:2.1669390201568604 lr:0.0001772611060473551 tokens_per_second_per_gpu:882.7707979162875 mfu:12.972065353607885 
Step 1144 | loss:2.091553211212158 lr:0.00017722113615913597 tokens_per_second_per_gpu:865.1679211823107 mfu:12.713396095467898 
Step 1145 | loss:2.1666505336761475 lr:0.00017718113568744638 tokens_per_second_per_gpu:894.995867089112 mfu:13.151709261898217 
Step 1146 | loss:2.134310245513916 lr:0.00017714110464812864 tokens_per_second_per_gpu:895.351998772587 mfu:13.156942515516745 
Step 1147 | loss:2.125822067260742 lr:0.00017710104305703698 tokens_per_second_per_gpu:856.4557405312004 mfu:12.58537308310115 
Step 1148 | loss:2.1901862621307373 lr:0.00017706095093003785 tokens_per_second_per_gpu:829.667017037588 mfu:12.19172042408804 
Step 1149 | loss:2.109851121902466 lr:0.00017702082828300973 tokens_per_second_per_gpu:880.573265136502 mfu:12.939773235536737 
Step 1150 | loss:2.1389236450195312 lr:0.00017698067513184326 tokens_per_second_per_gpu:883.9113017293021 mfu:12.988824732184279 
Step 1151 | loss:2.1353917121887207 lr:0.00017694049149244104 tokens_per_second_per_gpu:865.478531507356 mfu:12.71796042569439 
Step 1152 | loss:2.150986671447754 lr:0.00017690027738071789 tokens_per_second_per_gpu:883.2085849355534 mfu:12.978498509120373 
Step 1153 | loss:2.166945457458496 lr:0.00017686003281260063 tokens_per_second_per_gpu:872.74959483911 mfu:12.824806629660777 
Step 1154 | loss:2.1219429969787598 lr:0.00017681975780402807 tokens_per_second_per_gpu:869.8530906131455 mfu:12.782243325341124 
Step 1155 | loss:2.118797779083252 lr:0.00017677945237095123 tokens_per_second_per_gpu:878.7559873828585 mfu:12.913068856731316 
Step 1156 | loss:2.1114068031311035 lr:0.000176739116529333 tokens_per_second_per_gpu:873.0638100532825 mfu:12.829423932705877 
Step 1157 | loss:2.1699001789093018 lr:0.00017669875029514856 tokens_per_second_per_gpu:875.748376410204 mfu:12.86887287042593 
Step 1158 | loss:2.1933653354644775 lr:0.00017665835368438484 tokens_per_second_per_gpu:889.4653359345683 mfu:13.07043968235815 
Step 1159 | loss:2.129884958267212 lr:0.000176617926713041 tokens_per_second_per_gpu:869.4901221168612 mfu:12.776909606706328 
Step 1160 | loss:2.145028591156006 lr:0.00017657746939712815 tokens_per_second_per_gpu:882.6054762576845 mfu:12.969635998938669 
Step 1161 | loss:2.1291050910949707 lr:0.00017653698175266945 tokens_per_second_per_gpu:850.6774052123332 mfu:12.500462091971475 
Step 1162 | loss:2.0768606662750244 lr:0.0001764964637957 tokens_per_second_per_gpu:871.1029894401148 mfu:12.800610232478418 
Step 1163 | loss:2.1574087142944336 lr:0.000176455915542267 tokens_per_second_per_gpu:894.6076848836284 mfu:13.146005034990704 
Step 1164 | loss:2.1246230602264404 lr:0.00017641533700842965 tokens_per_second_per_gpu:888.2007953465136 mfu:13.05185761871348 
Step 1165 | loss:2.1659040451049805 lr:0.000176374728210259 tokens_per_second_per_gpu:878.679239771707 mfu:12.91194107245261 
Step 1166 | loss:2.0931177139282227 lr:0.00017633408916383826 tokens_per_second_per_gpu:849.7554967484846 mfu:12.486914909768215 
Step 1167 | loss:2.091488838195801 lr:0.0001762934198852625 tokens_per_second_per_gpu:895.9617919589768 mfu:13.165903252646595 
Step 1168 | loss:2.1378746032714844 lr:0.00017625272039063883 tokens_per_second_per_gpu:879.0134246939253 mfu:12.916851824667612 
Step 1169 | loss:2.128831386566162 lr:0.0001762119906960863 tokens_per_second_per_gpu:899.9273342887531 mfu:13.224175767308132 
Step 1170 | loss:2.1005845069885254 lr:0.00017617123081773591 tokens_per_second_per_gpu:877.7825271641806 mfu:12.898764136179125 
Step 1171 | loss:2.1678004264831543 lr:0.00017613044077173067 tokens_per_second_per_gpu:826.373783333663 mfu:12.143327293127143 
Step 1172 | loss:2.1560211181640625 lr:0.00017608962057422549 tokens_per_second_per_gpu:857.6443223667544 mfu:12.602838954520221 
Step 1173 | loss:2.1518120765686035 lr:0.00017604877024138718 tokens_per_second_per_gpu:895.700038341054 mfu:13.162056857810864 
Step 1174 | loss:2.136075735092163 lr:0.00017600788978939464 tokens_per_second_per_gpu:867.4790727358744 mfu:12.747357809047104 
Step 1175 | loss:2.13112211227417 lr:0.00017596697923443847 tokens_per_second_per_gpu:858.0105580249336 mfu:12.608220683168174 
Step 1176 | loss:2.1430163383483887 lr:0.0001759260385927214 tokens_per_second_per_gpu:887.4956844262837 mfu:13.041496214643075 
Step 1177 | loss:2.1423768997192383 lr:0.00017588506788045796 tokens_per_second_per_gpu:895.5856018913394 mfu:13.160375246787893 
Step 1178 | loss:2.124406576156616 lr:0.00017584406711387463 tokens_per_second_per_gpu:866.910452532321 mfu:12.739002097168903 
Step 1179 | loss:2.1189334392547607 lr:0.00017580303630920975 tokens_per_second_per_gpu:867.1888338091842 mfu:12.743092830715158 
Step 1180 | loss:2.0853781700134277 lr:0.00017576197548271365 tokens_per_second_per_gpu:885.2726771151355 mfu:13.008829755591837 
Step 1181 | loss:2.170222759246826 lr:0.00017572088465064848 tokens_per_second_per_gpu:874.6375789034571 mfu:12.852550017556128 
Step 1182 | loss:2.133776903152466 lr:0.00017567976382928824 tokens_per_second_per_gpu:889.357368070522 mfu:13.068853125358528 
Step 1183 | loss:2.154343366622925 lr:0.00017563861303491888 tokens_per_second_per_gpu:891.3212844732783 mfu:13.097712317331924 
Step 1184 | loss:2.1224164962768555 lr:0.0001755974322838382 tokens_per_second_per_gpu:869.0989756222797 mfu:12.771161820415115 
Step 1185 | loss:2.125124216079712 lr:0.00017555622159235584 tokens_per_second_per_gpu:879.4452966411726 mfu:12.923198059882127 
Step 1186 | loss:2.0905227661132812 lr:0.00017551498097679338 tokens_per_second_per_gpu:885.0457252165971 mfu:13.005494762106649 
Step 1187 | loss:2.1367926597595215 lr:0.0001754737104534841 tokens_per_second_per_gpu:875.9995836954979 mfu:12.872564289908572 
Step 1188 | loss:2.138549327850342 lr:0.00017543241003877325 tokens_per_second_per_gpu:867.977789824483 mfu:12.7546863145682 
Step 1189 | loss:2.1225054264068604 lr:0.00017539107974901788 tokens_per_second_per_gpu:883.2412469045479 mfu:12.978978467448599 
Step 1190 | loss:2.1644177436828613 lr:0.00017534971960058685 tokens_per_second_per_gpu:854.1491115837753 mfu:12.551477827930555 
Step 1191 | loss:2.1134610176086426 lr:0.0001753083296098609 tokens_per_second_per_gpu:872.2624074695008 mfu:12.817647550075293 
Step 1192 | loss:2.1507129669189453 lr:0.00017526690979323252 tokens_per_second_per_gpu:830.3115111516555 mfu:12.201191081463016 
Step 1193 | loss:2.176529884338379 lr:0.0001752254601671061 tokens_per_second_per_gpu:890.2174744119369 mfu:13.081492142981473 
Step 1194 | loss:2.1391782760620117 lr:0.00017518398074789775 tokens_per_second_per_gpu:901.0679387275998 mfu:13.24093662455246 
Step 1195 | loss:2.098098039627075 lr:0.00017514247155203541 tokens_per_second_per_gpu:898.3599494664988 mfu:13.201143493929214 
Step 1196 | loss:2.119081735610962 lr:0.00017510093259595885 tokens_per_second_per_gpu:844.902468786491 mfu:12.415601046606378 
Step 1197 | loss:2.1479382514953613 lr:0.0001750593638961196 tokens_per_second_per_gpu:857.935562259848 mfu:12.607118641768267 
Step 1198 | loss:2.120218276977539 lr:0.0001750177654689809 tokens_per_second_per_gpu:892.0202287365323 mfu:13.107983104135092 
Step 1199 | loss:2.1888134479522705 lr:0.0001749761373310179 tokens_per_second_per_gpu:859.3965360278784 mfu:12.62858723502433 
Step 1200 | loss:2.148991346359253 lr:0.00017493447949871739 tokens_per_second_per_gpu:882.4382175593914 mfu:12.967178180023115 
Step 1201 | loss:2.1142921447753906 lr:0.00017489279198857802 tokens_per_second_per_gpu:864.0432031308443 mfu:12.696868684159726 
Step 1202 | loss:2.1707139015197754 lr:0.00017485107481711012 tokens_per_second_per_gpu:881.8038657994462 mfu:12.957856561652175 
Step 1203 | loss:2.1603474617004395 lr:0.00017480932800083583 tokens_per_second_per_gpu:889.1691159589277 mfu:13.06608681421602 
Step 1204 | loss:2.10952091217041 lr:0.00017476755155628894 tokens_per_second_per_gpu:889.3104409535987 mfu:13.068163544745957 
Step 1205 | loss:2.1231303215026855 lr:0.00017472574550001508 tokens_per_second_per_gpu:880.463751082487 mfu:12.93816395771607 
Step 1206 | loss:2.109584331512451 lr:0.00017468390984857156 tokens_per_second_per_gpu:863.2719314389651 mfu:12.685535066400664 
Step 1207 | loss:2.119805335998535 lr:0.00017464204461852738 tokens_per_second_per_gpu:892.6652486543577 mfu:13.117461488046478 
Step 1208 | loss:2.11513352394104 lr:0.00017460014982646334 tokens_per_second_per_gpu:834.4338633870326 mfu:12.2617678730086 
Step 1209 | loss:2.1588587760925293 lr:0.0001745582254889718 tokens_per_second_per_gpu:871.876809904392 mfu:12.811981303721664 
Step 1210 | loss:2.096515417098999 lr:0.00017451627162265703 tokens_per_second_per_gpu:851.4716411178676 mfu:12.512133162307165 
Step 1211 | loss:2.1375226974487305 lr:0.00017447428824413482 tokens_per_second_per_gpu:842.0300889485652 mfu:12.37339224329536 
Step 1212 | loss:2.1384265422821045 lr:0.00017443227537003268 tokens_per_second_per_gpu:871.5518333535183 mfu:12.807205865899894 
Step 1213 | loss:2.09084415435791 lr:0.00017439023301698986 tokens_per_second_per_gpu:846.1939048264238 mfu:12.434578331253261 
Step 1214 | loss:2.114304304122925 lr:0.00017434816120165728 tokens_per_second_per_gpu:902.9490668004428 mfu:13.268579265606089 
Step 1215 | loss:2.07012939453125 lr:0.0001743060599406975 tokens_per_second_per_gpu:860.5377071138265 mfu:12.645356418986362 
Step 1216 | loss:2.1379811763763428 lr:0.0001742639292507847 tokens_per_second_per_gpu:843.7614402289638 mfu:12.398833957058885 
Step 1217 | loss:2.1297707557678223 lr:0.00017422176914860476 tokens_per_second_per_gpu:872.5935910260462 mfu:12.82251419807689 
Step 1218 | loss:2.164487838745117 lr:0.0001741795796508553 tokens_per_second_per_gpu:867.9151909406291 mfu:12.753766441805835 
Step 1219 | loss:2.1228511333465576 lr:0.0001741373607742454 tokens_per_second_per_gpu:890.8793586522091 mfu:13.09121834330618 
Step 1220 | loss:2.107919454574585 lr:0.00017409511253549593 tokens_per_second_per_gpu:850.1736593977479 mfu:12.49305969075495 
Step 1221 | loss:2.097139358520508 lr:0.00017405283495133925 tokens_per_second_per_gpu:855.6551453889036 mfu:12.57360856559313 
Step 1222 | loss:2.179814338684082 lr:0.00017401052803851948 tokens_per_second_per_gpu:883.3471638414175 mfu:12.980534886657717 
Step 1223 | loss:2.0773239135742188 lr:0.00017396819181379232 tokens_per_second_per_gpu:914.24777575227 mfu:13.43461057439027 
Step 1224 | loss:2.1452598571777344 lr:0.00017392582629392495 tokens_per_second_per_gpu:884.9721388385634 mfu:13.004413431247901 
Step 1225 | loss:2.0742721557617188 lr:0.00017388343149569635 tokens_per_second_per_gpu:842.4017559751001 mfu:12.378853784353778 
Step 1226 | loss:2.1412155628204346 lr:0.00017384100743589697 tokens_per_second_per_gpu:861.286081157615 mfu:12.656353562330796 
Step 1227 | loss:2.1440088748931885 lr:0.00017379855413132887 tokens_per_second_per_gpu:890.8744138579948 mfu:13.091145680964084 
Step 1228 | loss:2.1854586601257324 lr:0.00017375607159880572 tokens_per_second_per_gpu:885.6427961744059 mfu:13.014268549712353 
Step 1229 | loss:2.1496429443359375 lr:0.00017371355985515275 tokens_per_second_per_gpu:870.8392661491066 mfu:12.796734893857906 
Step 1230 | loss:2.1219398975372314 lr:0.00017367101891720672 tokens_per_second_per_gpu:875.4924751552064 mfu:12.865112474395913 
Step 1231 | loss:2.091142177581787 lr:0.00017362844880181605 tokens_per_second_per_gpu:890.8431079055902 mfu:13.090685648913286 
Step 1232 | loss:2.09539532661438 lr:0.0001735858495258406 tokens_per_second_per_gpu:877.365277007664 mfu:12.89263276401331 
Step 1233 | loss:2.1244242191314697 lr:0.00017354322110615188 tokens_per_second_per_gpu:859.1870470802475 mfu:12.62550885462713 
Step 1234 | loss:2.1403863430023193 lr:0.00017350056355963287 tokens_per_second_per_gpu:877.4104893705604 mfu:12.893297146804029 
Step 1235 | loss:2.134866237640381 lr:0.00017345787690317815 tokens_per_second_per_gpu:860.0592684106098 mfu:12.638325898560819 
Step 1236 | loss:2.1429872512817383 lr:0.0001734151611536937 tokens_per_second_per_gpu:857.1089891120937 mfu:12.594972384871781 
Step 1237 | loss:2.140146255493164 lr:0.00017337241632809722 tokens_per_second_per_gpu:883.1544377199423 mfu:12.977702831214758 
Step 1238 | loss:2.139746904373169 lr:0.00017332964244331776 tokens_per_second_per_gpu:876.8083747825128 mfu:12.88444924448901 
Step 1239 | loss:2.1225595474243164 lr:0.00017328683951629598 tokens_per_second_per_gpu:904.554433075803 mfu:13.292169665616608 
Step 1240 | loss:2.136268377304077 lr:0.00017324400756398397 tokens_per_second_per_gpu:894.0146074306905 mfu:13.137289930801234 
Step 1241 | loss:2.187481641769409 lr:0.00017320114660334535 tokens_per_second_per_gpu:873.8058486625281 mfu:12.840327978644815 
Step 1242 | loss:2.164484977722168 lr:0.00017315825665135522 tokens_per_second_per_gpu:896.3822184065123 mfu:13.17208129950393 
Step 1243 | loss:2.111224412918091 lr:0.0001731153377250002 tokens_per_second_per_gpu:872.7156807299432 mfu:12.824308271489482 
Step 1244 | loss:2.1142220497131348 lr:0.00017307238984127832 tokens_per_second_per_gpu:854.2861532840752 mfu:12.553491616670119 
Step 1245 | loss:2.1339523792266846 lr:0.0001730294130171991 tokens_per_second_per_gpu:863.469162767657 mfu:12.688433324580037 
Step 1246 | loss:2.121699810028076 lr:0.00017298640726978357 tokens_per_second_per_gpu:878.9593635337958 mfu:12.91605741132278 
Step 1247 | loss:2.111776113510132 lr:0.00017294337261606417 tokens_per_second_per_gpu:859.9244216283508 mfu:12.636344363516484 
Step 1248 | loss:2.138012647628784 lr:0.00017290030907308478 tokens_per_second_per_gpu:881.5840185423654 mfu:12.95462596884893 
Step 1249 | loss:2.09709095954895 lr:0.00017285721665790074 tokens_per_second_per_gpu:879.0796137683844 mfu:12.917824454257994 
Step 1250 | loss:2.124446392059326 lr:0.00017281409538757883 tokens_per_second_per_gpu:881.6137390431559 mfu:12.95506270313999 
Step 1251 | loss:2.1407480239868164 lr:0.00017277094527919727 tokens_per_second_per_gpu:865.8927721391752 mfu:12.724047573752257 
Step 1252 | loss:2.1267311573028564 lr:0.00017272776634984566 tokens_per_second_per_gpu:892.2437327547639 mfu:13.111267432001553 
Step 1253 | loss:2.1034910678863525 lr:0.00017268455861662503 tokens_per_second_per_gpu:867.0601989296042 mfu:12.741202577810776 
Step 1254 | loss:2.095609188079834 lr:0.00017264132209664785 tokens_per_second_per_gpu:863.2464577465649 mfu:12.685160737748888 
Step 1255 | loss:2.1059584617614746 lr:0.00017259805680703796 tokens_per_second_per_gpu:878.0831690451794 mfu:12.903181982960593 
Step 1256 | loss:2.1818647384643555 lr:0.00017255476276493056 tokens_per_second_per_gpu:874.7826324429141 mfu:12.854681537989348 
Step 1257 | loss:2.108381748199463 lr:0.00017251143998747232 tokens_per_second_per_gpu:875.103658712396 mfu:12.859398927551593 
Step 1258 | loss:2.115452289581299 lr:0.00017246808849182124 tokens_per_second_per_gpu:874.3896029919416 mfu:12.848906082190467 
Step 1259 | loss:2.150434732437134 lr:0.00017242470829514672 tokens_per_second_per_gpu:874.3598220358036 mfu:12.848468459525302 
Step 1260 | loss:2.1509714126586914 lr:0.00017238129941462944 tokens_per_second_per_gpu:853.5054422577396 mfu:12.542019290580704 
Step 1261 | loss:2.1572093963623047 lr:0.0001723378618674616 tokens_per_second_per_gpu:826.4528393329526 mfu:12.144488998511823 
Step 1262 | loss:2.131781816482544 lr:0.0001722943956708466 tokens_per_second_per_gpu:878.3715998957836 mfu:12.907420392129616 
Step 1263 | loss:2.114607572555542 lr:0.0001722509008419993 tokens_per_second_per_gpu:874.6586986653489 mfu:12.85286036643962 
Step 1264 | loss:2.049119472503662 lr:0.00017220737739814576 tokens_per_second_per_gpu:870.491376519768 mfu:12.791622754876558 
Step 1265 | loss:2.1620805263519287 lr:0.00017216382535652355 tokens_per_second_per_gpu:906.7854932247201 mfu:13.324954458824424 
Step 1266 | loss:2.1209826469421387 lr:0.00017212024473438147 tokens_per_second_per_gpu:879.0145572974351 mfu:12.916868467953483 
Step 1267 | loss:2.0918378829956055 lr:0.0001720766355489796 tokens_per_second_per_gpu:864.3726951422067 mfu:12.701710475386818 
Step 1268 | loss:2.118044137954712 lr:0.00017203299781758943 tokens_per_second_per_gpu:886.4529550678841 mfu:13.026173603819052 
Step 1269 | loss:2.1503562927246094 lr:0.00017198933155749367 tokens_per_second_per_gpu:876.521273897263 mfu:12.880230378781933 
Step 1270 | loss:2.11811900138855 lr:0.00017194563678598636 tokens_per_second_per_gpu:887.2897326832482 mfu:13.038469812459574 
Step 1271 | loss:2.0928139686584473 lr:0.0001719019135203729 tokens_per_second_per_gpu:877.8120267444472 mfu:12.89919762410603 
Step 1272 | loss:2.1726324558258057 lr:0.0001718581617779698 tokens_per_second_per_gpu:886.7521081097904 mfu:13.030569572534258 
Step 1273 | loss:2.1212410926818848 lr:0.00017181438157610508 tokens_per_second_per_gpu:872.6767501015958 mfu:12.823736196998151 
Step 1274 | loss:2.1493167877197266 lr:0.00017177057293211784 tokens_per_second_per_gpu:872.4549905544632 mfu:12.82047750363745 
Step 1275 | loss:2.1397130489349365 lr:0.00017172673586335853 tokens_per_second_per_gpu:840.8426524654529 mfu:12.355943202504081 
Step 1276 | loss:2.1524126529693604 lr:0.00017168287038718885 tokens_per_second_per_gpu:876.2787075518773 mfu:12.87666593544924 
Step 1277 | loss:2.10659122467041 lr:0.00017163897652098172 tokens_per_second_per_gpu:876.5891888325654 mfu:12.881228369405669 
Step 1278 | loss:2.081699848175049 lr:0.00017159505428212139 tokens_per_second_per_gpu:866.2831355572696 mfu:12.729783852957608 
Step 1279 | loss:2.1091952323913574 lr:0.00017155110368800324 tokens_per_second_per_gpu:859.5055304387417 mfu:12.630188876836945 
Step 1280 | loss:2.162234306335449 lr:0.0001715071247560339 tokens_per_second_per_gpu:891.8174199586584 mfu:13.105002886929137 
Step 1281 | loss:2.164613723754883 lr:0.00017146311750363126 tokens_per_second_per_gpu:885.2028583938296 mfu:13.007803789375211 
Step 1282 | loss:2.0880322456359863 lr:0.00017141908194822446 tokens_per_second_per_gpu:862.145947977847 mfu:12.668989060258207 
Step 1283 | loss:2.11008620262146 lr:0.0001713750181072538 tokens_per_second_per_gpu:885.4721866550873 mfu:13.011761491436555 
Step 1284 | loss:2.1297430992126465 lr:0.00017133092599817072 tokens_per_second_per_gpu:883.5314547428355 mfu:12.983242988945324 
Step 1285 | loss:2.1011033058166504 lr:0.000171286805638438 tokens_per_second_per_gpu:882.3666418513894 mfu:12.966126395387597 
Step 1286 | loss:2.1222314834594727 lr:0.0001712426570455295 tokens_per_second_per_gpu:893.9388527145124 mfu:13.136176736831265 
Step 1287 | loss:2.0731685161590576 lr:0.00017119848023693023 tokens_per_second_per_gpu:894.5719274772051 mfu:13.145479590091423 
Step 1288 | loss:2.09419846534729 lr:0.00017115427523013656 tokens_per_second_per_gpu:824.7982409242343 mfu:12.120175146328977 
Step 1289 | loss:2.1491312980651855 lr:0.00017111004204265582 tokens_per_second_per_gpu:861.3110914660044 mfu:12.656721081686568 
Step 1290 | loss:2.1752166748046875 lr:0.0001710657806920066 tokens_per_second_per_gpu:826.8412848371606 mfu:12.150197094519072 
Step 1291 | loss:2.107351541519165 lr:0.00017102149119571864 tokens_per_second_per_gpu:889.684713132633 mfu:13.073663367778085 
Step 1292 | loss:2.1197526454925537 lr:0.00017097717357133284 tokens_per_second_per_gpu:884.4506019881042 mfu:12.996749595828286 
Step 1293 | loss:2.132979393005371 lr:0.00017093282783640118 tokens_per_second_per_gpu:871.2215332112502 mfu:12.802352199419397 
Step 1294 | loss:2.1686649322509766 lr:0.00017088845400848682 tokens_per_second_per_gpu:883.6994258607037 mfu:12.98571127666355 
Step 1295 | loss:2.1123266220092773 lr:0.00017084405210516406 tokens_per_second_per_gpu:869.0038276381871 mfu:12.769763647898731 
Step 1296 | loss:2.0972580909729004 lr:0.00017079962214401829 tokens_per_second_per_gpu:884.0590360762927 mfu:12.990995646320382 
Step 1297 | loss:2.15327525138855 lr:0.00017075516414264596 tokens_per_second_per_gpu:880.8610437035607 mfu:12.94400205958491 
Step 1298 | loss:2.208012104034424 lr:0.00017071067811865476 tokens_per_second_per_gpu:873.5668847383788 mfu:12.83681647186578 
Step 1299 | loss:2.095804452896118 lr:0.00017066616408966336 tokens_per_second_per_gpu:841.1223055148967 mfu:12.36005262438605 
Step 1300 | loss:2.118440866470337 lr:0.00017062162207330162 tokens_per_second_per_gpu:875.1045354399198 mfu:12.859411810812755 
Step 1301 | loss:2.0917649269104004 lr:0.00017057705208721035 tokens_per_second_per_gpu:890.8974423420558 mfu:13.091484077976014 
Step 1302 | loss:2.1584761142730713 lr:0.00017053245414904157 tokens_per_second_per_gpu:847.2877458687273 mfu:12.450652013709353 
Step 1303 | loss:2.137915849685669 lr:0.00017048782827645828 tokens_per_second_per_gpu:878.6777022354233 mfu:12.911918478795002 
Step 1304 | loss:2.1057662963867188 lr:0.00017044317448713461 tokens_per_second_per_gpu:862.9816063477384 mfu:12.681268821905407 
Step 1305 | loss:2.1550192832946777 lr:0.0001703984927987557 tokens_per_second_per_gpu:864.3900240807803 mfu:12.701965119201743 
Step 1306 | loss:2.1194961071014404 lr:0.0001703537832290178 tokens_per_second_per_gpu:858.0850195619471 mfu:12.609314874238777 
Step 1307 | loss:2.1049253940582275 lr:0.00017030904579562806 tokens_per_second_per_gpu:863.7844590902622 mfu:12.69306651420552 
Step 1308 | loss:2.115048885345459 lr:0.00017026428051630484 tokens_per_second_per_gpu:898.7156528935876 mfu:13.206370454442169 
Step 1309 | loss:2.0556814670562744 lr:0.00017021948740877745 tokens_per_second_per_gpu:859.2319226456725 mfu:12.626168288274966 
Step 1310 | loss:2.170158863067627 lr:0.0001701746664907862 tokens_per_second_per_gpu:889.2686535418939 mfu:13.067549490637152 
Step 1311 | loss:2.11661434173584 lr:0.00017012981778008243 tokens_per_second_per_gpu:850.8043494253169 mfu:12.502327501011933 
Step 1312 | loss:2.1180830001831055 lr:0.00017008494129442853 tokens_per_second_per_gpu:838.3709889522426 mfu:12.31962281141143 
Step 1313 | loss:2.1306538581848145 lr:0.0001700400370515978 tokens_per_second_per_gpu:879.7047336392501 mfu:12.927010412649288 
Step 1314 | loss:2.083397150039673 lr:0.00016999510506937466 tokens_per_second_per_gpu:883.2164203179387 mfu:12.978613647832043 
Step 1315 | loss:2.0508506298065186 lr:0.0001699501453655544 tokens_per_second_per_gpu:896.0326666212135 mfu:13.166944735614335 
Step 1316 | loss:2.1215882301330566 lr:0.00016990515795794334 tokens_per_second_per_gpu:900.4259555503389 mfu:13.231502864678435 
Step 1317 | loss:2.1374011039733887 lr:0.00016986014286435875 tokens_per_second_per_gpu:857.7144107057088 mfu:12.603868882691371 
Step 1318 | loss:2.093755006790161 lr:0.0001698151001026289 tokens_per_second_per_gpu:841.6267712903285 mfu:12.36746560522208 
Step 1319 | loss:2.127263069152832 lr:0.00016977002969059302 tokens_per_second_per_gpu:889.5656911777152 mfu:13.071914374062668 
Step 1320 | loss:2.112964630126953 lr:0.00016972493164610122 tokens_per_second_per_gpu:863.7961787954466 mfu:12.693238731933992 
Step 1321 | loss:2.104294538497925 lr:0.00016967980598701462 tokens_per_second_per_gpu:895.2157450315709 mfu:13.154940305614351 
Step 1322 | loss:2.082183599472046 lr:0.0001696346527312053 tokens_per_second_per_gpu:862.7770888159703 mfu:12.67826349504784 
Step 1323 | loss:2.092012882232666 lr:0.0001695894718965562 tokens_per_second_per_gpu:881.0483334310784 mfu:12.946754228767618 
Step 1324 | loss:2.1234304904937744 lr:0.00016954426350096116 tokens_per_second_per_gpu:852.8620766008315 mfu:12.532565215562164 
Step 1325 | loss:2.134824275970459 lr:0.00016949902756232507 tokens_per_second_per_gpu:848.2787920939531 mfu:12.46521515561711 
Step 1326 | loss:2.107135772705078 lr:0.00016945376409856366 tokens_per_second_per_gpu:881.3923659112021 mfu:12.951809688040244 
Step 1327 | loss:2.1046085357666016 lr:0.00016940847312760346 tokens_per_second_per_gpu:891.1092964512561 mfu:13.094597213748589 
Step 1328 | loss:2.1257553100585938 lr:0.00016936315466738205 tokens_per_second_per_gpu:873.3925092015122 mfu:12.83425407303514 
Step 1329 | loss:2.110008478164673 lr:0.00016931780873584776 tokens_per_second_per_gpu:887.9688568307282 mfu:13.048449348308651 
Step 1330 | loss:2.1146585941314697 lr:0.00016927243535095997 tokens_per_second_per_gpu:871.1975793032211 mfu:12.802000203565932 
Step 1331 | loss:2.154569387435913 lr:0.00016922703453068873 tokens_per_second_per_gpu:846.0164265455353 mfu:12.431970338483262 
Step 1332 | loss:2.0672552585601807 lr:0.00016918160629301513 tokens_per_second_per_gpu:884.568706659091 mfu:12.998485110317691 
Step 1333 | loss:2.1206631660461426 lr:0.00016913615065593102 tokens_per_second_per_gpu:882.9706902737038 mfu:12.975002714846172 
Step 1334 | loss:2.126290798187256 lr:0.00016909066763743912 tokens_per_second_per_gpu:891.9744880904061 mfu:13.107310958372835 
Step 1335 | loss:2.089240074157715 lr:0.00016904515725555305 tokens_per_second_per_gpu:891.372132056612 mfu:13.098459508081365 
Step 1336 | loss:2.1568686962127686 lr:0.00016899961952829715 tokens_per_second_per_gpu:907.613543216379 mfu:13.337122417521298 
Step 1337 | loss:2.0592777729034424 lr:0.0001689540544737067 tokens_per_second_per_gpu:868.9951879304937 mfu:12.769636689855828 
Step 1338 | loss:2.1375699043273926 lr:0.00016890846210982776 tokens_per_second_per_gpu:890.6260320748747 mfu:13.087495781430839 
Step 1339 | loss:2.1677803993225098 lr:0.00016886284245471722 tokens_per_second_per_gpu:876.0810476237624 mfu:12.873761379123465 
Step 1340 | loss:2.1451215744018555 lr:0.00016881719552644273 tokens_per_second_per_gpu:835.42838384411 mfu:12.276382067763524 
Step 1341 | loss:2.111254930496216 lr:0.00016877152134308281 tokens_per_second_per_gpu:858.8915475808777 mfu:12.621166573678517 
Step 1342 | loss:2.0747554302215576 lr:0.00016872581992272671 tokens_per_second_per_gpu:877.1137415292902 mfu:12.888936521826873 
Step 1343 | loss:2.0895583629608154 lr:0.00016868009128347459 tokens_per_second_per_gpu:884.7257089140232 mfu:13.000792213720354 
Step 1344 | loss:2.14927339553833 lr:0.0001686343354434372 tokens_per_second_per_gpu:891.5857912135849 mfu:13.101599168516657 
Step 1345 | loss:2.1102607250213623 lr:0.0001685885524207362 tokens_per_second_per_gpu:868.3924883192838 mfu:12.760780190792127 
Step 1346 | loss:2.106316089630127 lr:0.00016854274223350397 tokens_per_second_per_gpu:898.8216331767479 mfu:13.20792780450698 
Step 1347 | loss:2.1225247383117676 lr:0.00016849690489988372 tokens_per_second_per_gpu:866.5058080794751 mfu:12.733055962226876 
Step 1348 | loss:2.0888099670410156 lr:0.00016845104043802924 tokens_per_second_per_gpu:869.5099618361994 mfu:12.777201145729208 
Step 1349 | loss:2.0970664024353027 lr:0.00016840514886610529 tokens_per_second_per_gpu:899.8610497924894 mfu:13.223201735521522 
Step 1350 | loss:2.155721426010132 lr:0.00016835923020228712 tokens_per_second_per_gpu:897.3678168567047 mfu:13.186564387909765 
Step 1351 | loss:2.161447048187256 lr:0.00016831328446476098 tokens_per_second_per_gpu:795.93506891193 mfu:11.696039057391946 
Step 1352 | loss:2.080582618713379 lr:0.0001682673116717236 tokens_per_second_per_gpu:882.0484643425086 mfu:12.961450867550708 
Step 1353 | loss:2.0735673904418945 lr:0.00016822131184138258 tokens_per_second_per_gpu:853.7234533011544 mfu:12.545222900747309 
Step 1354 | loss:2.101449489593506 lr:0.00016817528499195615 tokens_per_second_per_gpu:880.3025317556492 mfu:12.935794885643293 
Step 1355 | loss:2.1467318534851074 lr:0.00016812923114167328 tokens_per_second_per_gpu:879.2562520274133 mfu:12.920420103146107 
Step 1356 | loss:2.1269633769989014 lr:0.00016808315030877364 tokens_per_second_per_gpu:884.9314765207137 mfu:13.003815910072731 
Step 1357 | loss:2.0929453372955322 lr:0.0001680370425115075 tokens_per_second_per_gpu:874.5921293961256 mfu:12.851882149995506 
Step 1358 | loss:2.236607074737549 lr:0.00016799090776813597 tokens_per_second_per_gpu:864.9332239768178 mfu:12.709947286903828 
Step 1359 | loss:2.0624783039093018 lr:0.00016794474609693066 tokens_per_second_per_gpu:876.1369470303524 mfu:12.874582804976276 
Step 1360 | loss:2.098722457885742 lr:0.00016789855751617397 tokens_per_second_per_gpu:865.7716702145796 mfu:12.722268015475056 
Step 1361 | loss:2.092437744140625 lr:0.00016785234204415888 tokens_per_second_per_gpu:864.8864654229175 mfu:12.709260183276854 
Step 1362 | loss:2.1363537311553955 lr:0.0001678060996991891 tokens_per_second_per_gpu:873.4739699764116 mfu:12.83545111591223 
Step 1363 | loss:2.0719947814941406 lr:0.00016775983049957887 tokens_per_second_per_gpu:879.7654022217399 mfu:12.927901920183096 
Step 1364 | loss:2.1643033027648926 lr:0.00016771353446365318 tokens_per_second_per_gpu:884.643763406508 mfu:12.999588047835585 
Step 1365 | loss:2.062429904937744 lr:0.00016766721160974755 tokens_per_second_per_gpu:894.85558513055 mfu:13.149647858486714 
Step 1366 | loss:2.119926929473877 lr:0.00016762086195620826 tokens_per_second_per_gpu:893.5895230684163 mfu:13.131043437213958 
Step 1367 | loss:2.108137845993042 lr:0.000167574485521392 tokens_per_second_per_gpu:862.7745187995888 mfu:12.67822572938937 
Step 1368 | loss:2.0984833240509033 lr:0.0001675280823236663 tokens_per_second_per_gpu:876.8550574393105 mfu:12.885135232829686 
Step 1369 | loss:2.100973129272461 lr:0.00016748165238140902 tokens_per_second_per_gpu:898.1096589481067 mfu:13.197465546074985 
Step 1370 | loss:2.1332626342773438 lr:0.00016743519571300888 tokens_per_second_per_gpu:876.205527163947 mfu:12.875590570499385 
Step 1371 | loss:2.127923011779785 lr:0.00016738871233686506 tokens_per_second_per_gpu:876.6398611803942 mfu:12.881972985119292 
Step 1372 | loss:2.1258089542388916 lr:0.00016734220227138726 tokens_per_second_per_gpu:895.2415061226601 mfu:13.155318857507975 
Step 1373 | loss:2.089590072631836 lr:0.0001672956655349959 tokens_per_second_per_gpu:885.3794323504356 mfu:13.010398493357542 
Step 1374 | loss:2.0943896770477295 lr:0.00016724910214612179 tokens_per_second_per_gpu:890.1036435134931 mfu:13.07981943036189 
Step 1375 | loss:2.168403148651123 lr:0.00016720251212320645 tokens_per_second_per_gpu:889.3840826118353 mfu:13.069245687931534 
Step 1376 | loss:2.112276792526245 lr:0.00016715589548470185 tokens_per_second_per_gpu:846.8732246870137 mfu:12.444560743050724 
Step 1377 | loss:2.1038756370544434 lr:0.00016710925224907054 tokens_per_second_per_gpu:899.7208632624491 mfu:13.221141734404958 
Step 1378 | loss:2.1083855628967285 lr:0.00016706258243478562 tokens_per_second_per_gpu:852.1147145035143 mfu:12.521582942482794 
Step 1379 | loss:2.087250232696533 lr:0.00016701588606033064 tokens_per_second_per_gpu:875.34319485477 mfu:12.862918842914404 
Step 1380 | loss:2.0846893787384033 lr:0.0001669691631441998 tokens_per_second_per_gpu:865.0505507925616 mfu:12.711671371032068 
Step 1381 | loss:2.128211498260498 lr:0.00016692241370489766 tokens_per_second_per_gpu:903.4199884294609 mfu:13.27549932476807 
Step 1382 | loss:2.101421356201172 lr:0.00016687563776093941 tokens_per_second_per_gpu:864.6506222696144 mfu:12.705794535336222 
Step 1383 | loss:2.129429340362549 lr:0.00016682883533085066 tokens_per_second_per_gpu:827.9570319527697 mfu:12.166592680480848 
Step 1384 | loss:2.070110321044922 lr:0.00016678200643316753 tokens_per_second_per_gpu:899.4633785150969 mfu:13.217358069405963 
Step 1385 | loss:2.1041412353515625 lr:0.00016673515108643665 tokens_per_second_per_gpu:862.6415883473068 mfu:12.676272354268038 
Step 1386 | loss:2.101673126220703 lr:0.0001666882693092151 tokens_per_second_per_gpu:880.2324918187861 mfu:12.934765668727085 
Step 1387 | loss:2.13503360748291 lr:0.00016664136112007043 tokens_per_second_per_gpu:890.3743080699802 mfu:13.083796768900891 
Step 1388 | loss:2.10339093208313 lr:0.00016659442653758064 tokens_per_second_per_gpu:888.3560335530233 mfu:13.054138799927195 
Step 1389 | loss:2.1339240074157715 lr:0.00016654746558033423 tokens_per_second_per_gpu:844.7368711176589 mfu:12.413167636045488 
Step 1390 | loss:2.077061414718628 lr:0.00016650047826693008 tokens_per_second_per_gpu:877.0010219666034 mfu:12.887280139969594 
Step 1391 | loss:2.116713047027588 lr:0.00016645346461597753 tokens_per_second_per_gpu:830.4784720605744 mfu:12.203644524448562 
Step 1392 | loss:2.177018880844116 lr:0.00016640642464609638 tokens_per_second_per_gpu:857.4751271350578 mfu:12.600352678798068 
Step 1393 | loss:2.093113660812378 lr:0.00016635935837591682 tokens_per_second_per_gpu:814.9904652607803 mfu:11.97605267741614 
Step 1394 | loss:2.019226551055908 lr:0.00016631226582407952 tokens_per_second_per_gpu:900.392257867112 mfu:13.231007686824661 
Step 1395 | loss:2.1239986419677734 lr:0.00016626514700923545 tokens_per_second_per_gpu:874.5366568726281 mfu:12.851066997068113 
Step 1396 | loss:2.087184190750122 lr:0.00016621800195004607 tokens_per_second_per_gpu:879.6194098099143 mfu:12.925756603287926 
Step 1397 | loss:2.1125800609588623 lr:0.0001661708306651832 tokens_per_second_per_gpu:873.3343596458164 mfu:12.83339958188234 
Step 1398 | loss:2.1023125648498535 lr:0.00016612363317332904 tokens_per_second_per_gpu:865.4260850263676 mfu:12.717189739599476 
Step 1399 | loss:2.1173830032348633 lr:0.00016607640949317616 tokens_per_second_per_gpu:819.5603522917669 mfu:12.043205865270215 
Step 1400 | loss:2.1134095191955566 lr:0.00016602915964342757 tokens_per_second_per_gpu:885.7534571335962 mfu:13.015894680977793 
Step 1401 | loss:2.1076912879943848 lr:0.0001659818836427966 tokens_per_second_per_gpu:874.5136669905698 mfu:12.850729167301614 
Step 1402 | loss:2.139820098876953 lr:0.00016593458151000688 tokens_per_second_per_gpu:882.7108919249104 mfu:12.971185052133198 
Step 1403 | loss:2.1287856101989746 lr:0.0001658872532637925 tokens_per_second_per_gpu:866.3054441471586 mfu:12.730111671329793 
Step 1404 | loss:2.1140782833099365 lr:0.00016583989892289782 tokens_per_second_per_gpu:875.0501684238379 mfu:12.85861290300185 
Step 1405 | loss:2.0973048210144043 lr:0.00016579251850607754 tokens_per_second_per_gpu:853.3697389986143 mfu:12.540025169852848 
Step 1406 | loss:2.140547752380371 lr:0.00016574511203209667 tokens_per_second_per_gpu:851.6051678908807 mfu:12.514095300191732 
Step 1407 | loss:2.1449155807495117 lr:0.0001656976795197306 tokens_per_second_per_gpu:880.0497580808142 mfu:12.932080448512647 
Step 1408 | loss:2.1069352626800537 lr:0.00016565022098776505 tokens_per_second_per_gpu:866.2110140599157 mfu:12.72872404810307 
Step 1409 | loss:2.1159088611602783 lr:0.0001656027364549959 tokens_per_second_per_gpu:888.4977161621321 mfu:13.056220785499402 
Step 1410 | loss:2.1426806449890137 lr:0.0001655552259402295 tokens_per_second_per_gpu:866.5894252560372 mfu:12.734284692811993 
Step 1411 | loss:2.1329686641693115 lr:0.00016550768946228236 tokens_per_second_per_gpu:874.8249249024465 mfu:12.855303013632078 
Step 1412 | loss:2.1290700435638428 lr:0.00016546012703998138 tokens_per_second_per_gpu:839.3714145485527 mfu:12.334323780504867 
Step 1413 | loss:2.072786331176758 lr:0.0001654125386921636 tokens_per_second_per_gpu:894.4640329762469 mfu:13.143894111141476 
Step 1414 | loss:2.0559325218200684 lr:0.00016536492443767654 tokens_per_second_per_gpu:874.2334287044644 mfu:12.846611145533648 
Step 1415 | loss:2.0843656063079834 lr:0.00016531728429537766 tokens_per_second_per_gpu:878.8136668739849 mfu:12.9139164404192 
Step 1416 | loss:2.093942165374756 lr:0.00016526961828413508 tokens_per_second_per_gpu:901.6954521112793 mfu:13.250157754932587 
Step 1417 | loss:2.0928616523742676 lr:0.00016522192642282678 tokens_per_second_per_gpu:861.742941594623 mfu:12.663066996282549 
Step 1418 | loss:2.176703929901123 lr:0.00016517420873034123 tokens_per_second_per_gpu:877.2648813366412 mfu:12.891157478232676 
Step 1419 | loss:2.1629271507263184 lr:0.00016512646522557703 tokens_per_second_per_gpu:843.704344825124 mfu:12.397994956367256 
Step 1420 | loss:2.085453987121582 lr:0.00016507869592744299 tokens_per_second_per_gpu:852.1894436465549 mfu:12.522681065947719 
Step 1421 | loss:2.0828864574432373 lr:0.0001650309008548582 tokens_per_second_per_gpu:884.3729796719658 mfu:12.995608958009022 
Step 1422 | loss:2.0795531272888184 lr:0.0001649830800267519 tokens_per_second_per_gpu:892.02365462724 mfu:13.108033446622928 
Step 1423 | loss:2.152690887451172 lr:0.0001649352334620636 tokens_per_second_per_gpu:864.0051515347394 mfu:12.696309526796744 
Step 1424 | loss:2.074856758117676 lr:0.0001648873611797429 tokens_per_second_per_gpu:863.0576449685066 mfu:12.682386187772437 
Step 1425 | loss:2.103607654571533 lr:0.00016483946319874963 tokens_per_second_per_gpu:868.0940170912568 mfu:12.756394241137611 
Step 1426 | loss:2.068552017211914 lr:0.0001647915395380539 tokens_per_second_per_gpu:882.298963960972 mfu:12.965131888070905 
Step 1427 | loss:2.1169726848602295 lr:0.0001647435902166358 tokens_per_second_per_gpu:883.1749368899335 mfu:12.978004060677092 
Step 1428 | loss:2.100093126296997 lr:0.00016469561525348577 tokens_per_second_per_gpu:875.0320260285006 mfu:12.858346305671555 
Step 1429 | loss:2.136131525039673 lr:0.00016464761466760422 tokens_per_second_per_gpu:902.1286255295063 mfu:13.256523114892328 
Step 1430 | loss:2.0887112617492676 lr:0.00016459958847800187 tokens_per_second_per_gpu:889.9288120395548 mfu:13.077250331665889 
Step 1431 | loss:2.1283092498779297 lr:0.00016455153670369955 tokens_per_second_per_gpu:851.4926073148729 mfu:12.512441254598404 
Step 1432 | loss:2.1028120517730713 lr:0.00016450345936372813 tokens_per_second_per_gpu:892.7093655337262 mfu:13.118109773018881 
Step 1433 | loss:2.0660667419433594 lr:0.0001644553564771287 tokens_per_second_per_gpu:881.5361628731091 mfu:12.953922743424394 
Step 1434 | loss:2.1217007637023926 lr:0.00016440722806295238 tokens_per_second_per_gpu:890.9667627727367 mfu:13.092502721953881 
Step 1435 | loss:2.0955328941345215 lr:0.00016435907414026052 tokens_per_second_per_gpu:891.005516478772 mfu:13.093072196622245 
Step 1436 | loss:2.100081205368042 lr:0.00016431089472812444 tokens_per_second_per_gpu:858.3360498849025 mfu:12.613003693310276 
Step 1437 | loss:2.059950828552246 lr:0.00016426268984562567 tokens_per_second_per_gpu:862.9386190342093 mfu:12.680637135581176 
Step 1438 | loss:2.0694804191589355 lr:0.00016421445951185577 tokens_per_second_per_gpu:832.2650789927578 mfu:12.229898204271453 
Step 1439 | loss:2.1172373294830322 lr:0.0001641662037459164 tokens_per_second_per_gpu:876.6694052810946 mfu:12.882407127261287 
Step 1440 | loss:2.125270128250122 lr:0.00016411792256691924 tokens_per_second_per_gpu:884.3091347883555 mfu:12.99467077563525 
Step 1441 | loss:2.087444543838501 lr:0.0001640696159939861 tokens_per_second_per_gpu:817.6344313357669 mfu:12.01490500556112 
Step 1442 | loss:2.138306140899658 lr:0.00016402128404624882 tokens_per_second_per_gpu:900.3352109058028 mfu:13.230169397982218 
Step 1443 | loss:2.1332437992095947 lr:0.00016397292674284929 tokens_per_second_per_gpu:867.4079409638374 mfu:12.746312547924104 
Step 1444 | loss:2.120170831680298 lr:0.00016392454410293946 tokens_per_second_per_gpu:870.1431874852401 mfu:12.78650621622126 
Step 1445 | loss:2.035400629043579 lr:0.00016387613614568126 tokens_per_second_per_gpu:860.5601138441342 mfu:12.645685679504039 
Step 1446 | loss:2.0828726291656494 lr:0.00016382770289024675 tokens_per_second_per_gpu:899.960802183587 mfu:13.224667568486943 
Step 1447 | loss:2.0986058712005615 lr:0.00016377924435581793 tokens_per_second_per_gpu:865.845643990885 mfu:12.72335503904103 
Step 1448 | loss:2.1198787689208984 lr:0.00016373076056158675 tokens_per_second_per_gpu:876.9081315654282 mfu:12.885915141990944 
Step 1449 | loss:2.0973329544067383 lr:0.00016368225152675533 tokens_per_second_per_gpu:873.1573385449399 mfu:12.830798307242356 
Step 1450 | loss:2.092041254043579 lr:0.00016363371727053566 tokens_per_second_per_gpu:886.9395410828539 mfu:13.033323846669449 
Step 1451 | loss:2.107454538345337 lr:0.00016358515781214977 tokens_per_second_per_gpu:874.7273103105682 mfu:12.853868595017078 
Step 1452 | loss:2.122663974761963 lr:0.00016353657317082963 tokens_per_second_per_gpu:890.7171763842766 mfu:13.088835121088382 
Step 1453 | loss:2.076223373413086 lr:0.00016348796336581727 tokens_per_second_per_gpu:850.6580621779032 mfu:12.5001778515918 
Step 1454 | loss:2.129122734069824 lr:0.00016343932841636456 tokens_per_second_per_gpu:864.1278937141268 mfu:12.698113188150762 
Step 1455 | loss:2.0748157501220703 lr:0.00016339066834173346 tokens_per_second_per_gpu:868.0528114043359 mfu:12.75578873530876 
Step 1456 | loss:2.0914971828460693 lr:0.00016334198316119575 tokens_per_second_per_gpu:872.5486990508865 mfu:12.821854523292679 
Step 1457 | loss:2.077272415161133 lr:0.00016329327289403325 tokens_per_second_per_gpu:866.9484507533157 mfu:12.739560470199851 
Step 1458 | loss:2.1091318130493164 lr:0.00016324453755953773 tokens_per_second_per_gpu:848.4882197542083 mfu:12.468292635413787 
Step 1459 | loss:2.1105833053588867 lr:0.00016319577717701077 tokens_per_second_per_gpu:882.1983590388357 mfu:12.963653527404777 
Step 1460 | loss:2.095552921295166 lr:0.00016314699176576402 tokens_per_second_per_gpu:906.0741211739776 mfu:13.314501049225075 
Step 1461 | loss:2.155170202255249 lr:0.0001630981813451189 tokens_per_second_per_gpu:897.2051138622899 mfu:13.184173513764676 
Step 1462 | loss:2.119931697845459 lr:0.00016304934593440687 tokens_per_second_per_gpu:867.7818294518763 mfu:12.751806732726376 
Step 1463 | loss:2.1418025493621826 lr:0.00016300048555296915 tokens_per_second_per_gpu:874.1228875577965 mfu:12.844986774879088 
Step 1464 | loss:2.095198631286621 lr:0.00016295160022015693 tokens_per_second_per_gpu:874.6427967427342 mfu:12.852626692217623 
Step 1465 | loss:2.1346614360809326 lr:0.00016290268995533132 tokens_per_second_per_gpu:863.9103238362374 mfu:12.694916060785854 
Step 1466 | loss:2.0979528427124023 lr:0.00016285375477786322 tokens_per_second_per_gpu:874.5401232209199 mfu:12.851117934068617 
Step 1467 | loss:2.0879874229431152 lr:0.00016280479470713344 tokens_per_second_per_gpu:867.4893269178999 mfu:12.747508491330315 
Step 1468 | loss:2.0980992317199707 lr:0.00016275580976253263 tokens_per_second_per_gpu:837.4499357093939 mfu:12.306088196437093 
Step 1469 | loss:2.0792219638824463 lr:0.0001627067999634613 tokens_per_second_per_gpu:882.2422370816316 mfu:12.964298302741797 
Step 1470 | loss:2.1168019771575928 lr:0.00016265776532932983 tokens_per_second_per_gpu:861.5019313803982 mfu:12.659525419853887 
Step 1471 | loss:2.0833964347839355 lr:0.00016260870587955838 tokens_per_second_per_gpu:887.7081550660718 mfu:13.044618410156973 
Step 1472 | loss:2.097599983215332 lr:0.000162559621633577 tokens_per_second_per_gpu:871.0743411377395 mfu:12.800189253837575 
Step 1473 | loss:2.0922904014587402 lr:0.00016251051261082555 tokens_per_second_per_gpu:863.7990078700777 mfu:12.693280304379627 
Step 1474 | loss:2.063596487045288 lr:0.00016246137883075363 tokens_per_second_per_gpu:826.1844109162594 mfu:12.140544519409968 
Step 1475 | loss:2.0926454067230225 lr:0.0001624122203128207 tokens_per_second_per_gpu:869.2056246166487 mfu:12.772728997000609 
Step 1476 | loss:2.0975892543792725 lr:0.00016236303707649604 tokens_per_second_per_gpu:860.1934407722542 mfu:12.640297523186382 
Step 1477 | loss:2.077848434448242 lr:0.00016231382914125872 tokens_per_second_per_gpu:895.3770047727401 mfu:13.15730997156421 
Step 1478 | loss:2.109633445739746 lr:0.00016226459652659753 tokens_per_second_per_gpu:871.9115780414958 mfu:12.81249221159016 
Step 1479 | loss:2.124563694000244 lr:0.0001622153392520111 tokens_per_second_per_gpu:880.6264575269286 mfu:12.940554882558317 
Step 1480 | loss:2.076970338821411 lr:0.00016216605733700775 tokens_per_second_per_gpu:855.5932665005529 mfu:12.572699272959538 
Step 1481 | loss:2.088195323944092 lr:0.00016211675080110566 tokens_per_second_per_gpu:873.579095377679 mfu:12.836995903731202 
Step 1482 | loss:2.0906167030334473 lr:0.0001620674196638327 tokens_per_second_per_gpu:859.0681210248231 mfu:12.623761270127448 
Step 1483 | loss:2.127345085144043 lr:0.00016201806394472646 tokens_per_second_per_gpu:884.129767119066 mfu:12.992035018841028 
Step 1484 | loss:2.0527234077453613 lr:0.0001619686836633343 tokens_per_second_per_gpu:847.010305573219 mfu:12.446575107616002 
Step 1485 | loss:2.1208066940307617 lr:0.00016191927883921334 tokens_per_second_per_gpu:890.6931138330049 mfu:13.08848152875342 
Step 1486 | loss:2.068624973297119 lr:0.0001618698494919304 tokens_per_second_per_gpu:857.9452155015093 mfu:12.607260493404048 
Step 1487 | loss:2.1545796394348145 lr:0.00016182039564106192 tokens_per_second_per_gpu:882.3894018994854 mfu:12.966460847809504 
Step 1488 | loss:2.0838139057159424 lr:0.0001617709173061942 tokens_per_second_per_gpu:837.4276427604694 mfu:12.305760607904423 
Step 1489 | loss:2.066251277923584 lr:0.00016172141450692312 tokens_per_second_per_gpu:894.2816985806767 mfu:13.141214759149848 
Step 1490 | loss:2.160611152648926 lr:0.00016167188726285434 tokens_per_second_per_gpu:868.8022563879525 mfu:12.766801615808834 
Step 1491 | loss:2.078381299972534 lr:0.00016162233559360306 tokens_per_second_per_gpu:870.4801273092194 mfu:12.791457450932706 
Step 1492 | loss:2.0671775341033936 lr:0.0001615727595187943 tokens_per_second_per_gpu:882.2425776293217 mfu:12.96430330699307 
Step 1493 | loss:2.1005969047546387 lr:0.00016152315905806268 tokens_per_second_per_gpu:886.7658030144523 mfu:13.030770815256272 
Step 1494 | loss:2.112423896789551 lr:0.00016147353423105252 tokens_per_second_per_gpu:896.9019136279528 mfu:13.179718072709838 
Step 1495 | loss:2.0699477195739746 lr:0.0001614238850574177 tokens_per_second_per_gpu:840.201264923385 mfu:12.346518195319506 
Step 1496 | loss:2.078392505645752 lr:0.00016137421155682183 tokens_per_second_per_gpu:880.4329340632627 mfu:12.937711110399048 
Step 1497 | loss:2.078843116760254 lr:0.00016132451374893818 tokens_per_second_per_gpu:850.8111853974317 mfu:12.502427953674434 
Step 1498 | loss:2.0618276596069336 lr:0.0001612747916534495 tokens_per_second_per_gpu:886.9352726795256 mfu:13.033261123698706 
Step 1499 | loss:2.045801877975464 lr:0.0001612250452900483 tokens_per_second_per_gpu:883.87006397135 mfu:12.98821875508076 
Step 1500 | loss:2.0801172256469727 lr:0.0001611752746784366 tokens_per_second_per_gpu:880.6316174505007 mfu:12.940630706165027 
Step 1501 | loss:2.1071248054504395 lr:0.00016112547983832616 tokens_per_second_per_gpu:866.7729522252986 mfu:12.73698156933422 
Step 1502 | loss:2.085397720336914 lr:0.0001610756607894382 tokens_per_second_per_gpu:836.7405347425017 mfu:12.295663751353317 
Step 1503 | loss:2.13500714302063 lr:0.0001610258175515036 tokens_per_second_per_gpu:807.4650119505866 mfu:11.865468285198157 
Step 1504 | loss:2.0668911933898926 lr:0.00016097595014426274 tokens_per_second_per_gpu:863.0125560062638 mfu:12.681723618319166 
Step 1505 | loss:2.0747995376586914 lr:0.00016092605858746573 tokens_per_second_per_gpu:854.4842109774985 mfu:12.556402018043766 
Step 1506 | loss:2.0803580284118652 lr:0.00016087614290087208 tokens_per_second_per_gpu:886.1816178036404 mfu:13.022186380031238 
Step 1507 | loss:2.083134174346924 lr:0.00016082620310425093 tokens_per_second_per_gpu:891.6986462876981 mfu:13.103257541675736 
Step 1508 | loss:2.077472686767578 lr:0.00016077623921738102 tokens_per_second_per_gpu:864.0197261632972 mfu:12.696523696810752 
Step 1509 | loss:2.1042230129241943 lr:0.00016072625126005048 tokens_per_second_per_gpu:878.7321388587676 mfu:12.912718409464794 
Step 1510 | loss:2.1389107704162598 lr:0.0001606762392520571 tokens_per_second_per_gpu:861.9898248636218 mfu:12.666694875577747 
Step 1511 | loss:2.033344030380249 lr:0.00016062620321320823 tokens_per_second_per_gpu:882.757584976405 mfu:12.971871193220984 
Step 1512 | loss:2.123516082763672 lr:0.00016057614316332056 tokens_per_second_per_gpu:873.7047560685348 mfu:12.8388424517797 
Step 1513 | loss:2.0896506309509277 lr:0.0001605260591222205 tokens_per_second_per_gpu:893.5008949752455 mfu:13.129741072637003 
Step 1514 | loss:2.1047792434692383 lr:0.00016047595110974376 tokens_per_second_per_gpu:869.8737982000622 mfu:12.782547617430797 
Step 1515 | loss:2.0527188777923584 lr:0.00016042581914573574 tokens_per_second_per_gpu:877.9825031278771 mfu:12.901702725987878 
Step 1516 | loss:2.083631992340088 lr:0.00016037566325005113 tokens_per_second_per_gpu:885.0490220292583 mfu:13.005543207829366 
Step 1517 | loss:2.0641751289367676 lr:0.00016032548344255428 tokens_per_second_per_gpu:902.0257878403851 mfu:13.255011944351525 
Step 1518 | loss:2.1100974082946777 lr:0.00016027527974311892 tokens_per_second_per_gpu:863.5965883007324 mfu:12.690305806482105 
Step 1519 | loss:2.099987030029297 lr:0.00016022505217162822 tokens_per_second_per_gpu:861.7014511705524 mfu:12.662457306322413 
Step 1520 | loss:2.056304931640625 lr:0.0001601748007479748 tokens_per_second_per_gpu:880.8612783239399 mfu:12.944005507264535 
Step 1521 | loss:2.109665870666504 lr:0.00016012452549206088 tokens_per_second_per_gpu:870.801365934805 mfu:12.796177961007388 
Step 1522 | loss:2.085113763809204 lr:0.0001600742264237979 tokens_per_second_per_gpu:869.4420630973924 mfu:12.776203393108357 
Step 1523 | loss:2.0688328742980957 lr:0.00016002390356310685 tokens_per_second_per_gpu:868.9216501255125 mfu:12.768556072764248 
Step 1524 | loss:2.09371280670166 lr:0.00015997355692991817 tokens_per_second_per_gpu:846.5293646537019 mfu:12.439507817834867 
Step 1525 | loss:2.0787203311920166 lr:0.00015992318654417162 tokens_per_second_per_gpu:867.2946939499785 mfu:12.744648415322134 
Step 1526 | loss:2.110629081726074 lr:0.0001598727924258164 tokens_per_second_per_gpu:901.0109769089744 mfu:13.240099586857497 
Step 1527 | loss:2.099991798400879 lr:0.00015982237459481123 tokens_per_second_per_gpu:865.9418272750017 mfu:12.724768424996286 
Step 1528 | loss:2.0933773517608643 lr:0.00015977193307112399 tokens_per_second_per_gpu:882.9127828457475 mfu:12.974151781691516 
Step 1529 | loss:2.126152515411377 lr:0.00015972146787473213 tokens_per_second_per_gpu:857.7958520470329 mfu:12.60506563999761 
Step 1530 | loss:2.0651350021362305 lr:0.00015967097902562242 tokens_per_second_per_gpu:885.5972904822055 mfu:13.01359985653109 
Step 1531 | loss:2.1320464611053467 lr:0.00015962046654379098 tokens_per_second_per_gpu:852.0327786855416 mfu:12.520378918983091 
Step 1532 | loss:2.0720338821411133 lr:0.00015956993044924334 tokens_per_second_per_gpu:866.7579044770255 mfu:12.736760446960798 
Step 1533 | loss:2.0923845767974854 lr:0.0001595193707619943 tokens_per_second_per_gpu:874.2057337617081 mfu:12.846204176240773 
Step 1534 | loss:2.057480812072754 lr:0.00015946878750206807 tokens_per_second_per_gpu:865.4604501474126 mfu:12.717694725261817 
Step 1535 | loss:2.0683798789978027 lr:0.00015941818068949818 tokens_per_second_per_gpu:891.9225052198345 mfu:13.106547084900903 
Step 1536 | loss:2.087841510772705 lr:0.0001593675503443275 tokens_per_second_per_gpu:882.127674106483 mfu:12.962614832463624 
Step 1537 | loss:2.0710818767547607 lr:0.00015931689648660818 tokens_per_second_per_gpu:878.4592309293727 mfu:12.908708105200104 
Step 1538 | loss:2.073676109313965 lr:0.0001592662191364017 tokens_per_second_per_gpu:875.5681402846761 mfu:12.866224351914731 
Step 1539 | loss:2.1179966926574707 lr:0.00015921551831377885 tokens_per_second_per_gpu:872.5889155356795 mfu:12.822445493078106 
Step 1540 | loss:2.1250529289245605 lr:0.00015916479403881972 tokens_per_second_per_gpu:854.3289058903002 mfu:12.55411985403739 
Step 1541 | loss:2.0952725410461426 lr:0.0001591140463316137 tokens_per_second_per_gpu:884.919533665394 mfu:13.003640413216605 
Step 1542 | loss:2.0897514820098877 lr:0.00015906327521225948 tokens_per_second_per_gpu:852.3094214720235 mfu:12.524444105908529 
Step 1543 | loss:2.0803284645080566 lr:0.00015901248070086487 tokens_per_second_per_gpu:837.7922257076465 mfu:12.311118050435095 
Step 1544 | loss:2.0921683311462402 lr:0.0001589616628175472 tokens_per_second_per_gpu:906.3599807181109 mfu:13.318701673778135 
Step 1545 | loss:2.118565082550049 lr:0.00015891082158243282 tokens_per_second_per_gpu:881.3428709503817 mfu:12.951082373693243 
Step 1546 | loss:2.0819132328033447 lr:0.00015885995701565747 tokens_per_second_per_gpu:870.4348642631819 mfu:12.790792323367672 
Step 1547 | loss:2.073211908340454 lr:0.0001588090691373661 tokens_per_second_per_gpu:868.6682089902148 mfu:12.764831827492277 
Step 1548 | loss:2.081813097000122 lr:0.00015875815796771286 tokens_per_second_per_gpu:861.6990149794631 mfu:12.662421507188482 
Step 1549 | loss:2.0889992713928223 lr:0.00015870722352686112 tokens_per_second_per_gpu:871.7042998976581 mfu:12.809446318324792 
Step 1550 | loss:2.0377345085144043 lr:0.00015865626583498355 tokens_per_second_per_gpu:893.2706278670752 mfu:13.126357363090852 
Step 1551 | loss:2.073972463607788 lr:0.0001586052849122619 tokens_per_second_per_gpu:873.4868883254514 mfu:12.835640947370635 
Step 1552 | loss:2.111741065979004 lr:0.00015855428077888724 tokens_per_second_per_gpu:860.1798732821667 mfu:12.640098152785237 
Step 1553 | loss:2.099161148071289 lr:0.00015850325345505975 tokens_per_second_per_gpu:868.9582531673435 mfu:12.769093944034902 
Step 1554 | loss:2.0845041275024414 lr:0.0001584522029609889 tokens_per_second_per_gpu:893.2364668344843 mfu:13.125855376450197 
Step 1555 | loss:2.08096981048584 lr:0.00015840112931689318 tokens_per_second_per_gpu:874.2773858235923 mfu:12.847257082874837 
Step 1556 | loss:2.092280149459839 lr:0.00015835003254300039 tokens_per_second_per_gpu:887.3934812777748 mfu:13.039994368495773 
Step 1557 | loss:2.064026355743408 lr:0.00015829891265954738 tokens_per_second_per_gpu:880.6058398797511 mfu:12.940251912107486 
Step 1558 | loss:2.102177858352661 lr:0.00015824776968678024 tokens_per_second_per_gpu:883.2409209545808 mfu:12.978973677706701 
Step 1559 | loss:2.0933949947357178 lr:0.00015819660364495416 tokens_per_second_per_gpu:862.876145513407 mfu:12.679719104993133 
Step 1560 | loss:2.083961248397827 lr:0.00015814541455433346 tokens_per_second_per_gpu:874.6479227296998 mfu:12.852702017135568 
Step 1561 | loss:2.1042098999023438 lr:0.0001580942024351917 tokens_per_second_per_gpu:879.8731660295377 mfu:12.92948547863429 
Step 1562 | loss:2.110182762145996 lr:0.00015804296730781135 tokens_per_second_per_gpu:865.3331396008978 mfu:12.715823933054494 
Step 1563 | loss:2.122896432876587 lr:0.00015799170919248413 tokens_per_second_per_gpu:825.3385434954357 mfu:12.128114738668112 
Step 1564 | loss:2.1019537448883057 lr:0.0001579404281095109 tokens_per_second_per_gpu:872.5378976908463 mfu:12.821695800384443 
Step 1565 | loss:2.027167797088623 lr:0.00015788912407920148 tokens_per_second_per_gpu:888.8725869620487 mfu:13.061729405094836 
Step 1566 | loss:2.0424749851226807 lr:0.00015783779712187496 tokens_per_second_per_gpu:884.7325116686957 mfu:13.000892178262005 
Step 1567 | loss:2.126100540161133 lr:0.0001577864472578593 tokens_per_second_per_gpu:862.2207468700603 mfu:12.670088208667352 
Step 1568 | loss:2.087627410888672 lr:0.00015773507450749172 tokens_per_second_per_gpu:903.0435666928914 mfu:13.269967914600421 
Step 1569 | loss:2.105266571044922 lr:0.00015768367889111836 tokens_per_second_per_gpu:885.4048185866869 mfu:13.01077153686613 
Step 1570 | loss:2.11543869972229 lr:0.00015763226042909455 tokens_per_second_per_gpu:888.4276165222497 mfu:13.055190691264334 
Step 1571 | loss:2.0792460441589355 lr:0.00015758081914178456 tokens_per_second_per_gpu:872.6350349760957 mfu:12.823123205114529 
Step 1572 | loss:2.1136693954467773 lr:0.0001575293550495617 tokens_per_second_per_gpu:844.8476011056794 mfu:12.41479478166992 
Step 1573 | loss:2.079827308654785 lr:0.0001574778681728084 tokens_per_second_per_gpu:855.055045616093 mfu:12.564790270413951 
Step 1574 | loss:2.1336851119995117 lr:0.00015742635853191608 tokens_per_second_per_gpu:857.6843570261891 mfu:12.603427252433816 
Step 1575 | loss:2.0961008071899414 lr:0.0001573748261472851 tokens_per_second_per_gpu:858.953006137781 mfu:12.622069689661252 
Step 1576 | loss:2.075052499771118 lr:0.00015732327103932495 tokens_per_second_per_gpu:837.5466159257373 mfu:12.307508884669835 
Step 1577 | loss:2.0916085243225098 lr:0.000157271693228454 tokens_per_second_per_gpu:855.7746417505857 mfu:12.575364530580778 
Step 1578 | loss:2.078397035598755 lr:0.00015722009273509973 tokens_per_second_per_gpu:895.785975479003 mfu:13.163319679567552 
Step 1579 | loss:2.0859365463256836 lr:0.0001571684695796985 tokens_per_second_per_gpu:851.779136027457 mfu:12.516651712391184 
Step 1580 | loss:2.0445022583007812 lr:0.00015711682378269565 tokens_per_second_per_gpu:879.1668171374096 mfu:12.919105882919565 
Step 1581 | loss:2.0840938091278076 lr:0.0001570651553645456 tokens_per_second_per_gpu:853.2854719985097 mfu:12.538786890295924 
Step 1582 | loss:2.086397171020508 lr:0.0001570134643457116 tokens_per_second_per_gpu:891.5696202156059 mfu:13.101361540308845 
Step 1583 | loss:2.0416486263275146 lr:0.00015696175074666598 tokens_per_second_per_gpu:880.1155296808577 mfu:12.93304694343544 
Step 1584 | loss:2.1156482696533203 lr:0.00015691001458788983 tokens_per_second_per_gpu:873.845607484062 mfu:12.840912223199052 
Step 1585 | loss:2.059068202972412 lr:0.00015685825588987335 tokens_per_second_per_gpu:886.9213015104483 mfu:13.033055821349823 
Step 1586 | loss:2.1082639694213867 lr:0.00015680647467311557 tokens_per_second_per_gpu:870.2255562434548 mfu:12.787716601654466 
Step 1587 | loss:2.0685272216796875 lr:0.00015675467095812453 tokens_per_second_per_gpu:893.2175823411042 mfu:13.125577874200603 
Step 1588 | loss:2.0976104736328125 lr:0.00015670284476541703 tokens_per_second_per_gpu:908.0942392918795 mfu:13.344186109389373 
Step 1589 | loss:2.109185218811035 lr:0.0001566509961155189 tokens_per_second_per_gpu:902.9909513119504 mfu:13.26919474656883 
Step 1590 | loss:2.079190969467163 lr:0.0001565991250289648 tokens_per_second_per_gpu:886.3876252782215 mfu:13.025213601173924 
Step 1591 | loss:2.0540685653686523 lr:0.0001565472315262984 tokens_per_second_per_gpu:870.8633472272867 mfu:12.797088758440506 
Step 1592 | loss:2.0387024879455566 lr:0.000156495315628072 tokens_per_second_per_gpu:864.7570002063649 mfu:12.707357728807242 
Step 1593 | loss:2.105023145675659 lr:0.00015644337735484703 tokens_per_second_per_gpu:848.2010957016412 mfu:12.46407342926958 
Step 1594 | loss:2.0884387493133545 lr:0.0001563914167271936 tokens_per_second_per_gpu:844.7204865010734 mfu:12.41292686877312 
Step 1595 | loss:2.0915591716766357 lr:0.00015633943376569081 tokens_per_second_per_gpu:840.9148157876236 mfu:12.357003621962384 
Step 1596 | loss:2.092940330505371 lr:0.00015628742849092646 tokens_per_second_per_gpu:854.116427056784 mfu:12.550997538118994 
Step 1597 | loss:2.0347957611083984 lr:0.00015623540092349732 tokens_per_second_per_gpu:901.6000159335979 mfu:13.248755347493526 
Step 1598 | loss:2.104334592819214 lr:0.00015618335108400893 tokens_per_second_per_gpu:875.115145041286 mfu:12.859567715881912 
Step 1599 | loss:2.1248178482055664 lr:0.00015613127899307566 tokens_per_second_per_gpu:884.3658225693513 mfu:12.995503786425326 
Step 1600 | loss:2.0761537551879883 lr:0.00015607918467132063 tokens_per_second_per_gpu:870.2988340682374 mfu:12.788793398411103 
Step 1601 | loss:2.116124153137207 lr:0.0001560270681393759 tokens_per_second_per_gpu:885.5318302473686 mfu:13.012637937031293 
Step 1602 | loss:2.1083285808563232 lr:0.00015597492941788222 tokens_per_second_per_gpu:789.2121389420843 mfu:11.597247517002955 
Step 1603 | loss:2.103865146636963 lr:0.00015592276852748914 tokens_per_second_per_gpu:879.7951068899825 mfu:12.928338421819376 
Step 1604 | loss:2.053187370300293 lr:0.00015587058548885505 tokens_per_second_per_gpu:875.1870597638266 mfu:12.86062448223948 
Step 1605 | loss:2.1044700145721436 lr:0.00015581838032264702 tokens_per_second_per_gpu:881.3907361862775 mfu:12.951785739696822 
Step 1606 | loss:2.1244051456451416 lr:0.00015576615304954095 tokens_per_second_per_gpu:872.337196136631 mfu:12.818746548229754 
Step 1607 | loss:2.102386236190796 lr:0.0001557139036902215 tokens_per_second_per_gpu:879.7108042947837 mfu:12.927099619202684 
Step 1608 | loss:2.112980604171753 lr:0.00015566163226538203 tokens_per_second_per_gpu:911.4939060179923 mfu:13.394143243286099 
Step 1609 | loss:2.052046298980713 lr:0.00015560933879572462 tokens_per_second_per_gpu:860.8187944366905 mfu:12.649486917107584 
Step 1610 | loss:2.0452778339385986 lr:0.00015555702330196023 tokens_per_second_per_gpu:891.5835357216928 mfu:13.101566024705944 
Step 1611 | loss:2.0657899379730225 lr:0.00015550468580480836 tokens_per_second_per_gpu:888.5908946356498 mfu:13.057590016619049 
Step 1612 | loss:2.066983222961426 lr:0.00015545232632499737 tokens_per_second_per_gpu:873.9103273413182 mfu:12.84186326306125 
Step 1613 | loss:2.05222749710083 lr:0.00015539994488326418 tokens_per_second_per_gpu:872.6916487071412 mfu:12.823955127761685 
Step 1614 | loss:2.041968584060669 lr:0.00015534754150035453 tokens_per_second_per_gpu:856.3297624744904 mfu:12.58352187145185 
Step 1615 | loss:2.0738325119018555 lr:0.00015529511619702283 tokens_per_second_per_gpu:847.6610067437499 mfu:12.456136975917177 
Step 1616 | loss:2.128988265991211 lr:0.00015524266899403206 tokens_per_second_per_gpu:819.9636587110754 mfu:12.049132338190647 
Step 1617 | loss:2.019049644470215 lr:0.00015519019991215403 tokens_per_second_per_gpu:888.8839636116988 mfu:13.061896581719974 
Step 1618 | loss:2.072061538696289 lr:0.00015513770897216918 tokens_per_second_per_gpu:874.7323892462827 mfu:12.853943228530294 
Step 1619 | loss:2.0714077949523926 lr:0.0001550851961948665 tokens_per_second_per_gpu:879.9792860013645 mfu:12.931044881384254 
Step 1620 | loss:2.0681204795837402 lr:0.00015503266160104374 tokens_per_second_per_gpu:856.5286673258244 mfu:12.586444721569622 
Step 1621 | loss:2.1053712368011475 lr:0.00015498010521150724 tokens_per_second_per_gpu:873.4128488818194 mfu:12.834552958842009 
Step 1622 | loss:2.0543437004089355 lr:0.000154927527047072 tokens_per_second_per_gpu:905.1260356081484 mfu:13.300569201966672 
Step 1623 | loss:2.077106475830078 lr:0.0001548749271285616 tokens_per_second_per_gpu:888.975796963337 mfu:13.063246046656856 
Step 1624 | loss:2.0537209510803223 lr:0.00015482230547680828 tokens_per_second_per_gpu:871.7238102531518 mfu:12.80973301743982 
Step 1625 | loss:2.0833733081817627 lr:0.0001547696621126529 tokens_per_second_per_gpu:893.2216754597257 mfu:13.125638021412522 
Step 1626 | loss:2.1173787117004395 lr:0.00015471699705694487 tokens_per_second_per_gpu:887.8175465306119 mfu:13.046225886560238 
Step 1627 | loss:2.0978245735168457 lr:0.00015466431033054216 tokens_per_second_per_gpu:875.5139966794691 mfu:12.865428727062975 
Step 1628 | loss:2.089749574661255 lr:0.00015461160195431148 tokens_per_second_per_gpu:861.2853423631921 mfu:12.656342705957254 
Step 1629 | loss:2.0621559619903564 lr:0.0001545588719491279 tokens_per_second_per_gpu:883.4434045517766 mfu:12.981949116475244 
Step 1630 | loss:2.0457820892333984 lr:0.00015450612033587527 tokens_per_second_per_gpu:860.3305350527063 mfu:12.642312084576302 
Step 1631 | loss:2.0793349742889404 lr:0.0001544533471354458 tokens_per_second_per_gpu:857.4863102233497 mfu:12.600517011094196 
Step 1632 | loss:2.0958969593048096 lr:0.00015440055236874041 tokens_per_second_per_gpu:881.3427418794836 mfu:12.951080477033171 
Step 1633 | loss:2.070528268814087 lr:0.00015434773605666843 tokens_per_second_per_gpu:863.4096168846789 mfu:12.68755831479567 
Step 1634 | loss:2.089200735092163 lr:0.0001542948982201479 tokens_per_second_per_gpu:889.6121830318635 mfu:13.072597558612777 
Step 1635 | loss:2.0821874141693115 lr:0.00015424203888010513 tokens_per_second_per_gpu:871.5323317233753 mfu:12.806919295001407 
Step 1636 | loss:2.121281385421753 lr:0.00015418915805747517 tokens_per_second_per_gpu:851.2453011920767 mfu:12.508807161587134 
Step 1637 | loss:2.083970069885254 lr:0.0001541362557732015 tokens_per_second_per_gpu:859.8389985770169 mfu:12.63508909611613 
Step 1638 | loss:2.064859628677368 lr:0.00015408333204823608 tokens_per_second_per_gpu:883.9995615518567 mfu:12.99012168512946 
Step 1639 | loss:2.093351364135742 lr:0.00015403038690353936 tokens_per_second_per_gpu:899.7269797190885 mfu:13.221231613992552 
Step 1640 | loss:2.121124029159546 lr:0.00015397742036008034 tokens_per_second_per_gpu:853.1666787297771 mfu:12.537041257058842 
Step 1641 | loss:2.0559427738189697 lr:0.00015392443243883642 tokens_per_second_per_gpu:862.2827582564319 mfu:12.670999448321606 
Step 1642 | loss:2.025053024291992 lr:0.00015387142316079347 tokens_per_second_per_gpu:858.4196840544012 mfu:12.614232673601753 
Step 1643 | loss:2.0750784873962402 lr:0.00015381839254694583 tokens_per_second_per_gpu:855.4224705786618 mfu:12.570189475551048 
Step 1644 | loss:2.0707385540008545 lr:0.0001537653406182964 tokens_per_second_per_gpu:895.6720241368773 mfu:13.16164519706238 
Step 1645 | loss:2.0257201194763184 lr:0.0001537122673958563 tokens_per_second_per_gpu:894.8614701809087 mfu:13.149734337624949 
Step 1646 | loss:2.0906195640563965 lr:0.0001536591729006453 tokens_per_second_per_gpu:884.9421008291067 mfu:13.003972031257456 
Step 1647 | loss:2.1243643760681152 lr:0.00015360605715369145 tokens_per_second_per_gpu:903.1885224602972 mfu:13.272097998301208 
Step 1648 | loss:2.106813669204712 lr:0.0001535529201760313 tokens_per_second_per_gpu:890.4330249966587 mfu:13.084659597408624 
Step 1649 | loss:2.0705394744873047 lr:0.00015349976198870973 tokens_per_second_per_gpu:865.3182118529287 mfu:12.715604574051348 
Step 1650 | loss:2.1199443340301514 lr:0.0001534465826127801 tokens_per_second_per_gpu:886.2054059401339 mfu:13.022535939919221 
Step 1651 | loss:2.042407274246216 lr:0.00015339338206930416 tokens_per_second_per_gpu:892.61762093703 mfu:13.116761612310581 
Step 1652 | loss:2.0805866718292236 lr:0.00015334016037935196 tokens_per_second_per_gpu:895.8816684589154 mfu:13.164725860642227 
Step 1653 | loss:2.109363317489624 lr:0.00015328691756400203 tokens_per_second_per_gpu:881.9499858554765 mfu:12.960003754242564 
Step 1654 | loss:2.0295257568359375 lr:0.00015323365364434114 tokens_per_second_per_gpu:898.444119293129 mfu:13.202380345549619 
Step 1655 | loss:2.1086642742156982 lr:0.00015318036864146457 tokens_per_second_per_gpu:876.8336518726991 mfu:12.884820684127272 
Step 1656 | loss:2.0604100227355957 lr:0.0001531270625764758 tokens_per_second_per_gpu:854.4732136772537 mfu:12.556240415850054 
Step 1657 | loss:2.0439534187316895 lr:0.0001530737354704868 tokens_per_second_per_gpu:860.8365444871472 mfu:12.649747749041644 
Step 1658 | loss:2.0860648155212402 lr:0.0001530203873446177 tokens_per_second_per_gpu:903.5220822477703 mfu:13.276999564339242 
Step 1659 | loss:2.1454672813415527 lr:0.00015296701821999715 tokens_per_second_per_gpu:868.6843531479658 mfu:12.765069061290584 
Step 1660 | loss:2.0744516849517822 lr:0.000152913628117762 tokens_per_second_per_gpu:879.1542703197313 mfu:12.918921511008662 
Step 1661 | loss:2.0723729133605957 lr:0.0001528602170590574 tokens_per_second_per_gpu:887.684895448429 mfu:13.044276616702914 
Step 1662 | loss:2.063612461090088 lr:0.0001528067850650368 tokens_per_second_per_gpu:831.8633139959277 mfu:12.223994382115153 
Step 1663 | loss:2.089625835418701 lr:0.00015275333215686204 tokens_per_second_per_gpu:880.509080946222 mfu:12.93883006714813 
Step 1664 | loss:2.0576372146606445 lr:0.0001526998583557031 tokens_per_second_per_gpu:848.828877903625 mfu:12.473298509858097 
Step 1665 | loss:2.082340717315674 lr:0.0001526463636827384 tokens_per_second_per_gpu:882.1018161025476 mfu:12.962234856463333 
Step 1666 | loss:2.070044994354248 lr:0.0001525928481591544 tokens_per_second_per_gpu:859.1220575545522 mfu:12.624553852064054 
Step 1667 | loss:2.110908031463623 lr:0.0001525393118061461 tokens_per_second_per_gpu:891.1973296659041 mfu:13.095890836755148 
Step 1668 | loss:2.130211353302002 lr:0.00015248575464491646 tokens_per_second_per_gpu:885.5853513993748 mfu:13.013424415110613 
Step 1669 | loss:2.087196111679077 lr:0.00015243217669667694 tokens_per_second_per_gpu:879.5484125030454 mfu:12.924713318092259 
Step 1670 | loss:2.0564846992492676 lr:0.000152378577982647 tokens_per_second_per_gpu:878.9725449745341 mfu:12.916251108838734 
Step 1671 | loss:2.0688705444335938 lr:0.00015232495852405452 tokens_per_second_per_gpu:868.4821616609288 mfu:12.762097914997597 
Step 1672 | loss:2.0548605918884277 lr:0.0001522713183421355 tokens_per_second_per_gpu:807.260270928683 mfu:11.862459674216726 
Step 1673 | loss:2.0825090408325195 lr:0.00015221765745813417 tokens_per_second_per_gpu:854.7635178328574 mfu:12.560506352702296 
Step 1674 | loss:2.028698682785034 lr:0.00015216397589330288 tokens_per_second_per_gpu:867.9085700880761 mfu:12.753669150264 
Step 1675 | loss:2.1037333011627197 lr:0.00015211027366890235 tokens_per_second_per_gpu:861.9045988179182 mfu:12.665442503118998 
Step 1676 | loss:2.0438694953918457 lr:0.0001520565508062013 tokens_per_second_per_gpu:868.6944079096752 mfu:12.765216813149069 
Step 1677 | loss:2.0140161514282227 lr:0.0001520028073264767 tokens_per_second_per_gpu:868.5488042675926 mfu:12.763077209114503 
Step 1678 | loss:2.072622537612915 lr:0.00015194904325101374 tokens_per_second_per_gpu:893.8091793024751 mfu:13.134271222988323 
Step 1679 | loss:2.1109609603881836 lr:0.00015189525860110563 tokens_per_second_per_gpu:893.2092611427473 mfu:13.12545559656165 
Step 1680 | loss:2.0773699283599854 lr:0.00015184145339805383 tokens_per_second_per_gpu:871.7570390879224 mfu:12.810221305699114 
Step 1681 | loss:2.0490922927856445 lr:0.00015178762766316796 tokens_per_second_per_gpu:888.9180628002891 mfu:13.062397659580663 
Step 1682 | loss:2.1457741260528564 lr:0.00015173378141776568 tokens_per_second_per_gpu:845.7115813245734 mfu:12.427490724818666 
Step 1683 | loss:2.086247682571411 lr:0.0001516799146831729 tokens_per_second_per_gpu:856.1815577169135 mfu:12.581344044766215 
Step 1684 | loss:2.0778934955596924 lr:0.00015162602748072345 tokens_per_second_per_gpu:882.2191366604936 mfu:12.963958848635016 
Step 1685 | loss:2.077293872833252 lr:0.00015157211983175947 tokens_per_second_per_gpu:843.0529249524907 mfu:12.388422526943465 
Step 1686 | loss:2.0912792682647705 lr:0.0001515181917576311 tokens_per_second_per_gpu:886.8323310154551 mfu:13.031748425275646 
Step 1687 | loss:2.078580379486084 lr:0.00015146424327969657 tokens_per_second_per_gpu:871.3939373607463 mfu:12.804885629274322 
Step 1688 | loss:2.084529399871826 lr:0.00015141027441932216 tokens_per_second_per_gpu:894.6128278504758 mfu:13.146080609423176 
Step 1689 | loss:2.1292600631713867 lr:0.00015135628519788235 tokens_per_second_per_gpu:876.1442635851347 mfu:12.874690319664145 
Step 1690 | loss:2.0927467346191406 lr:0.00015130227563675956 tokens_per_second_per_gpu:856.0288946088698 mfu:12.579100703890754 
Step 1691 | loss:2.0672855377197266 lr:0.00015124824575734428 tokens_per_second_per_gpu:885.4739169306815 mfu:13.011786917343418 
Step 1692 | loss:2.073045253753662 lr:0.00015119419558103515 tokens_per_second_per_gpu:881.2964907323224 mfu:12.950400829603655 
Step 1693 | loss:2.075164556503296 lr:0.00015114012512923864 tokens_per_second_per_gpu:863.4570497320818 mfu:12.688255326973541 
Step 1694 | loss:2.0835952758789062 lr:0.0001510860344233695 tokens_per_second_per_gpu:859.2663481025268 mfu:12.626674160554833 
Step 1695 | loss:2.060595989227295 lr:0.0001510319234848503 tokens_per_second_per_gpu:836.6699599381307 mfu:12.294626674711475 
Step 1696 | loss:2.0542662143707275 lr:0.00015097779233511175 tokens_per_second_per_gpu:891.7409731842004 mfu:13.103879523359927 
Step 1697 | loss:2.0929412841796875 lr:0.0001509236409955925 tokens_per_second_per_gpu:829.940508966767 mfu:12.195739310063164 
Step 1698 | loss:2.0467779636383057 lr:0.00015086946948773922 tokens_per_second_per_gpu:838.2436950119965 mfu:12.317752263228494 
Step 1699 | loss:2.078746795654297 lr:0.0001508152778330066 tokens_per_second_per_gpu:879.4235878209668 mfu:12.922879054954546 
Step 1700 | loss:2.081805467605591 lr:0.00015076106605285724 tokens_per_second_per_gpu:879.525677723045 mfu:12.924379236977815 
Step 1701 | loss:2.082425355911255 lr:0.00015070683416876172 tokens_per_second_per_gpu:892.5592171660247 mfu:13.115903385536242 
Step 1702 | loss:2.086052656173706 lr:0.00015065258220219862 tokens_per_second_per_gpu:868.0639333418574 mfu:12.75595216901174 
Step 1703 | loss:2.0546460151672363 lr:0.00015059831017465449 tokens_per_second_per_gpu:859.3068682693691 mfu:12.627269592861452 
Step 1704 | loss:2.119518756866455 lr:0.00015054401810762379 tokens_per_second_per_gpu:872.4464348934938 mfu:12.820351780637212 
Step 1705 | loss:2.131821632385254 lr:0.00015048970602260885 tokens_per_second_per_gpu:842.7028152356056 mfu:12.383277764408176 
Step 1706 | loss:2.058413505554199 lr:0.00015043537394112007 tokens_per_second_per_gpu:873.6147138836986 mfu:12.837519307528627 
Step 1707 | loss:2.1481659412384033 lr:0.00015038102188467568 tokens_per_second_per_gpu:868.1070298340836 mfu:12.756585459685821 
Step 1708 | loss:2.018136978149414 lr:0.00015032664987480186 tokens_per_second_per_gpu:874.5701653988018 mfu:12.851559395312881 
Step 1709 | loss:2.0139901638031006 lr:0.00015027225793303264 tokens_per_second_per_gpu:894.3227303305399 mfu:13.141817709023195 
Step 1710 | loss:2.082998514175415 lr:0.00015021784608091 tokens_per_second_per_gpu:890.9463882293217 mfu:13.092203323843574 
Step 1711 | loss:2.119992733001709 lr:0.00015016341433998374 tokens_per_second_per_gpu:888.6590495389559 mfu:13.058591533504226 
Step 1712 | loss:2.0835092067718506 lr:0.00015010896273181165 tokens_per_second_per_gpu:879.1434592518165 mfu:12.918762645445977 
Step 1713 | loss:2.0518312454223633 lr:0.00015005449127795926 tokens_per_second_per_gpu:887.7841283933943 mfu:13.045734816555425 
Step 1714 | loss:2.0824146270751953 lr:0.00015000000000000001 tokens_per_second_per_gpu:854.9247512584353 mfu:12.562875631952041 
Step 1715 | loss:2.085972785949707 lr:0.00014994548891951524 tokens_per_second_per_gpu:872.103109259764 mfu:12.815306708270947 
Step 1716 | loss:2.0050926208496094 lr:0.0001498909580580941 tokens_per_second_per_gpu:842.3249784406046 mfu:12.377725560360057 
Step 1717 | loss:2.069965362548828 lr:0.00014983640743733347 tokens_per_second_per_gpu:892.4103825205716 mfu:13.113716302827735 
Step 1718 | loss:2.0965278148651123 lr:0.00014978183707883827 tokens_per_second_per_gpu:869.1326572864814 mfu:12.771656762873874 
Step 1719 | loss:2.0024242401123047 lr:0.00014972724700422108 tokens_per_second_per_gpu:863.3743140696822 mfu:12.68703954998788 
Step 1720 | loss:2.066256046295166 lr:0.00014967263723510228 tokens_per_second_per_gpu:880.5690350326822 mfu:12.939711075366361 
Step 1721 | loss:2.0500359535217285 lr:0.00014961800779311014 tokens_per_second_per_gpu:866.8131102293376 mfu:12.737571679761631 
Step 1722 | loss:2.0478568077087402 lr:0.0001495633586998807 tokens_per_second_per_gpu:886.750847030987 mfu:13.030551041340553 
Step 1723 | loss:2.0547406673431396 lr:0.00014950868997705769 tokens_per_second_per_gpu:872.5515555880563 mfu:12.821896499292496 
Step 1724 | loss:2.0295658111572266 lr:0.00014945400164629278 tokens_per_second_per_gpu:875.7602920722079 mfu:12.86904796768403 
Step 1725 | loss:2.097301483154297 lr:0.00014939929372924523 tokens_per_second_per_gpu:850.2573651901455 mfu:12.49428972352452 
Step 1726 | loss:2.0744848251342773 lr:0.00014934456624758215 tokens_per_second_per_gpu:848.9901108164711 mfu:12.47566778157339 
Step 1727 | loss:2.038386821746826 lr:0.00014928981922297842 tokens_per_second_per_gpu:879.7613032364543 mfu:12.92784168676222 
Step 1728 | loss:2.068718910217285 lr:0.0001492350526771166 tokens_per_second_per_gpu:889.3463634935198 mfu:13.068691416234936 
Step 1729 | loss:2.0730199813842773 lr:0.00014918026663168706 tokens_per_second_per_gpu:898.681244897568 mfu:13.205864838744294 
Step 1730 | loss:2.0877583026885986 lr:0.00014912546110838775 tokens_per_second_per_gpu:866.8275329722137 mfu:12.737783617858824 
Step 1731 | loss:2.1297364234924316 lr:0.0001490706361289245 tokens_per_second_per_gpu:828.6522761064411 mfu:12.176809095227945 
Step 1732 | loss:2.070704698562622 lr:0.00014901579171501075 tokens_per_second_per_gpu:863.054394502998 mfu:12.682338423107922 
Step 1733 | loss:2.0470433235168457 lr:0.00014896092788836763 tokens_per_second_per_gpu:857.4264456464977 mfu:12.599637318194153 
Step 1734 | loss:2.0838325023651123 lr:0.00014890604467072404 tokens_per_second_per_gpu:862.5699629038052 mfu:12.675219838783526 
Step 1735 | loss:2.0807712078094482 lr:0.0001488511420838165 tokens_per_second_per_gpu:898.4017634377844 mfu:13.20175793832349 
Step 1736 | loss:2.053546667098999 lr:0.00014879622014938915 tokens_per_second_per_gpu:867.6549173348255 mfu:12.749941795326507 
Step 1737 | loss:2.0413198471069336 lr:0.0001487412788891939 tokens_per_second_per_gpu:869.1985140008542 mfu:12.772624508527485 
Step 1738 | loss:2.05350399017334 lr:0.00014868631832499026 tokens_per_second_per_gpu:872.7103041958543 mfu:12.824229264852946 
Step 1739 | loss:2.0662195682525635 lr:0.00014863133847854533 tokens_per_second_per_gpu:862.1614761421264 mfu:12.66921724220796 
Step 1740 | loss:2.080078125 lr:0.00014857633937163402 tokens_per_second_per_gpu:863.426888972488 mfu:12.687812123204806 
Step 1741 | loss:2.0859575271606445 lr:0.00014852132102603866 tokens_per_second_per_gpu:867.3486692234783 mfu:12.745441566587413 
Step 1742 | loss:2.0912222862243652 lr:0.00014846628346354933 tokens_per_second_per_gpu:850.7945877456501 mfu:12.50218405591056 
Step 1743 | loss:2.0436365604400635 lr:0.00014841122670596367 tokens_per_second_per_gpu:891.7705312117432 mfu:13.104313870152904 
Step 1744 | loss:2.061602830886841 lr:0.00014835615077508696 tokens_per_second_per_gpu:880.1833514448298 mfu:12.934043564933024 
Step 1745 | loss:2.1005446910858154 lr:0.00014830105569273204 tokens_per_second_per_gpu:867.9291435171762 mfu:12.753971470942782 
Step 1746 | loss:2.093554973602295 lr:0.00014824594148071934 tokens_per_second_per_gpu:880.8321878545988 mfu:12.943578031106114 
Step 1747 | loss:2.049189805984497 lr:0.00014819080816087687 tokens_per_second_per_gpu:869.390191734402 mfu:12.775441158208562 
Step 1748 | loss:2.077268600463867 lr:0.00014813565575504022 tokens_per_second_per_gpu:889.6014072912677 mfu:13.072439212174979 
Step 1749 | loss:2.080483913421631 lr:0.00014808048428505252 tokens_per_second_per_gpu:872.7375018410174 mfu:12.82462892649938 
Step 1750 | loss:2.052715301513672 lr:0.00014802529377276445 tokens_per_second_per_gpu:877.6149357758198 mfu:12.896301428477818 
Step 1751 | loss:2.000492572784424 lr:0.00014797008424003428 tokens_per_second_per_gpu:893.1649255199268 mfu:13.124804097216545 
Step 1752 | loss:2.1109538078308105 lr:0.00014791485570872772 tokens_per_second_per_gpu:844.6689525821314 mfu:12.41216959251747 
Step 1753 | loss:2.0580666065216064 lr:0.0001478596082007181 tokens_per_second_per_gpu:881.8670685018883 mfu:12.958785307356655 
Step 1754 | loss:2.0785090923309326 lr:0.00014780434173788617 tokens_per_second_per_gpu:873.6176981028309 mfu:12.837563159778501 
Step 1755 | loss:2.0944299697875977 lr:0.00014774905634212034 tokens_per_second_per_gpu:861.9222006115621 mfu:12.665701156461438 
Step 1756 | loss:2.0088560581207275 lr:0.00014769375203531633 tokens_per_second_per_gpu:905.3298831555674 mfu:13.303564683595123 
Step 1757 | loss:2.0818958282470703 lr:0.00014763842883937743 tokens_per_second_per_gpu:874.0122953772365 mfu:12.843361654296022 
Step 1758 | loss:2.097806215286255 lr:0.0001475830867762145 tokens_per_second_per_gpu:852.7955956732433 mfu:12.531588297273203 
Step 1759 | loss:2.1057372093200684 lr:0.00014752772586774574 tokens_per_second_per_gpu:895.6678871940788 mfu:13.161584405866668 
Step 1760 | loss:2.0504188537597656 lr:0.00014747234613589685 tokens_per_second_per_gpu:890.9379676312682 mfu:13.092079585554401 
Step 1761 | loss:2.0549988746643066 lr:0.00014741694760260108 tokens_per_second_per_gpu:899.3010946241147 mfu:13.214973353866405 
Step 1762 | loss:2.0893807411193848 lr:0.00014736153028979893 tokens_per_second_per_gpu:892.7723273116189 mfu:13.119034978405752 
Step 1763 | loss:2.0458319187164307 lr:0.00014730609421943855 tokens_per_second_per_gpu:866.7073097800621 mfu:12.736016972304519 
Step 1764 | loss:2.076601505279541 lr:0.0001472506394134754 tokens_per_second_per_gpu:864.1250026421217 mfu:12.69807070467138 
Step 1765 | loss:2.077500343322754 lr:0.00014719516589387237 tokens_per_second_per_gpu:879.0962620944088 mfu:12.91806909666543 
Step 1766 | loss:2.0321927070617676 lr:0.0001471396736825998 tokens_per_second_per_gpu:853.6579110919457 mfu:12.544259776657475 
Step 1767 | loss:2.0701541900634766 lr:0.00014708416280163534 tokens_per_second_per_gpu:890.3721365174326 mfu:13.083764858554929 
Step 1768 | loss:2.090871572494507 lr:0.00014702863327296418 tokens_per_second_per_gpu:890.8616187028381 mfu:13.090957659804692 
Step 1769 | loss:2.1069464683532715 lr:0.0001469730851185788 tokens_per_second_per_gpu:856.8368131349605 mfu:12.590972836437025 
Step 1770 | loss:2.074047565460205 lr:0.00014691751836047907 tokens_per_second_per_gpu:826.0790912689256 mfu:12.138996877200396 
Step 1771 | loss:2.0849013328552246 lr:0.0001468619330206722 tokens_per_second_per_gpu:886.3162196652064 mfu:13.024164316035774 
Step 1772 | loss:2.0660691261291504 lr:0.00014680632912117286 tokens_per_second_per_gpu:865.2892583002749 mfu:12.715179109844636 
Step 1773 | loss:2.075936794281006 lr:0.00014675070668400294 tokens_per_second_per_gpu:835.9874220987574 mfu:12.284596975632667 
Step 1774 | loss:2.0954864025115967 lr:0.00014669506573119177 tokens_per_second_per_gpu:889.5488362718036 mfu:13.07166669602265 
Step 1775 | loss:2.019930839538574 lr:0.00014663940628477598 tokens_per_second_per_gpu:875.1434886553925 mfu:12.859984217215457 
Step 1776 | loss:2.0510573387145996 lr:0.0001465837283667995 tokens_per_second_per_gpu:838.8371721253461 mfu:12.326473240313842 
Step 1777 | loss:2.0846056938171387 lr:0.0001465280319993136 tokens_per_second_per_gpu:892.2014676839165 mfu:13.110646358827745 
Step 1778 | loss:1.9917298555374146 lr:0.00014647231720437686 tokens_per_second_per_gpu:855.2120159073704 mfu:12.567096904119815 
Step 1779 | loss:2.067983865737915 lr:0.00014641658400405515 tokens_per_second_per_gpu:887.8989366293548 mfu:13.047421890871348 
Step 1780 | loss:2.089608907699585 lr:0.00014636083242042166 tokens_per_second_per_gpu:864.1315338400137 mfu:12.698166678763515 
Step 1781 | loss:2.051276206970215 lr:0.0001463050624755568 tokens_per_second_per_gpu:824.6785895480539 mfu:12.118416903447445 
Step 1782 | loss:2.0732879638671875 lr:0.0001462492741915483 tokens_per_second_per_gpu:872.4119961170131 mfu:12.81984571262923 
Step 1783 | loss:2.096242666244507 lr:0.0001461934675904911 tokens_per_second_per_gpu:859.1870958919018 mfu:12.625509571900482 
Step 1784 | loss:2.0625574588775635 lr:0.00014613764269448751 tokens_per_second_per_gpu:877.0991429463355 mfu:12.888721999809825 
Step 1785 | loss:2.0833210945129395 lr:0.00014608179952564697 tokens_per_second_per_gpu:890.2126273303243 mfu:13.081420916498221 
Step 1786 | loss:2.0552139282226562 lr:0.00014602593810608618 tokens_per_second_per_gpu:906.5101832034225 mfu:13.320908856503634 
Step 1787 | loss:2.043921947479248 lr:0.00014597005845792905 tokens_per_second_per_gpu:859.9467984245641 mfu:12.636673184161173 
Step 1788 | loss:2.103025197982788 lr:0.00014591416060330686 tokens_per_second_per_gpu:856.5123239995601 mfu:12.586204561046758 
Step 1789 | loss:2.0448896884918213 lr:0.00014585824456435787 tokens_per_second_per_gpu:882.6264806719822 mfu:12.969944652822132 
Step 1790 | loss:2.1316990852355957 lr:0.00014580231036322768 tokens_per_second_per_gpu:862.2216790657313 mfu:12.670101907017132 
Step 1791 | loss:2.0782299041748047 lr:0.00014574635802206914 tokens_per_second_per_gpu:883.6888980983477 mfu:12.985556574195332 
Step 1792 | loss:2.0162885189056396 lr:0.00014569038756304207 tokens_per_second_per_gpu:884.1025152927012 mfu:12.991634561017273 
Step 1793 | loss:2.088155746459961 lr:0.00014563439900831373 tokens_per_second_per_gpu:890.3362304096848 mfu:13.083237228532054 
Step 1794 | loss:2.072232961654663 lr:0.00014557839238005832 tokens_per_second_per_gpu:899.6241561181025 mfu:13.219720650472881 
Step 1795 | loss:2.067157030105591 lr:0.0001455223677004573 tokens_per_second_per_gpu:851.4772028051809 mfu:12.51221488971758 
Step 1796 | loss:2.0424985885620117 lr:0.00014546632499169937 tokens_per_second_per_gpu:866.4262800524166 mfu:12.731887320528621 
Step 1797 | loss:2.0840847492218018 lr:0.00014541026427598015 tokens_per_second_per_gpu:894.1021588825504 mfu:13.138576474440887 
Step 1798 | loss:2.0692267417907715 lr:0.0001453541855755026 tokens_per_second_per_gpu:866.6247546942413 mfu:12.734803848840231 
Step 1799 | loss:2.1057674884796143 lr:0.00014529808891247667 tokens_per_second_per_gpu:866.588309419093 mfu:12.734268295906025 
Step 1800 | loss:2.0889456272125244 lr:0.0001452419743091195 tokens_per_second_per_gpu:878.474944896151 mfu:12.90893901746464 
Step 1801 | loss:2.0866332054138184 lr:0.00014518584178765527 tokens_per_second_per_gpu:889.7000328816913 mfu:13.073888487125547 
Step 1802 | loss:2.1064884662628174 lr:0.00014512969137031538 tokens_per_second_per_gpu:836.5593753060793 mfu:12.293001665051595 
Step 1803 | loss:2.051730155944824 lr:0.0001450735230793381 tokens_per_second_per_gpu:893.5755581028004 mfu:13.130838226023174 
Step 1804 | loss:2.078751564025879 lr:0.00014501733693696905 tokens_per_second_per_gpu:871.9149236011417 mfu:12.812541373635929 
Step 1805 | loss:2.0974860191345215 lr:0.00014496113296546067 tokens_per_second_per_gpu:864.9417365702157 mfu:12.710072377038376 
Step 1806 | loss:2.0550951957702637 lr:0.00014490491118707263 tokens_per_second_per_gpu:883.5507390938316 mfu:12.983526366988654 
Step 1807 | loss:2.067026376724243 lr:0.0001448486716240716 tokens_per_second_per_gpu:851.4489965887846 mfu:12.511800407404237 
Step 1808 | loss:2.036841869354248 lr:0.0001447924142987312 tokens_per_second_per_gpu:897.0911475517613 mfu:13.182498811303091 
Step 1809 | loss:2.073139190673828 lr:0.00014473613923333232 tokens_per_second_per_gpu:888.8527792885006 mfu:13.06143833697571 
Step 1810 | loss:2.03310227394104 lr:0.00014467984645016258 tokens_per_second_per_gpu:830.9846574853218 mfu:12.211082775041318 
Step 1811 | loss:2.0169517993927 lr:0.00014462353597151684 tokens_per_second_per_gpu:873.9429690163338 mfu:12.842342923175238 
Step 1812 | loss:2.0709927082061768 lr:0.00014456720781969693 tokens_per_second_per_gpu:896.1729168452471 mfu:13.169005672695983 
Step 1813 | loss:2.059490203857422 lr:0.00014451086201701157 tokens_per_second_per_gpu:874.4331864610218 mfu:12.849546528850665 
Step 1814 | loss:2.102923631668091 lr:0.0001444544985857766 tokens_per_second_per_gpu:843.0232744904714 mfu:12.387986821852193 
Step 1815 | loss:2.0444929599761963 lr:0.00014439811754831473 tokens_per_second_per_gpu:877.4673710875752 mfu:12.894133007428648 
Step 1816 | loss:2.084272861480713 lr:0.00014434171892695573 tokens_per_second_per_gpu:895.5852940551907 mfu:13.1603707232234 
Step 1817 | loss:2.082387924194336 lr:0.00014428530274403632 tokens_per_second_per_gpu:836.9857439020177 mfu:12.299267030086657 
Step 1818 | loss:2.0574159622192383 lr:0.00014422886902190014 tokens_per_second_per_gpu:854.2960343308089 mfu:12.553636815836532 
Step 1819 | loss:2.085360050201416 lr:0.0001441724177828978 tokens_per_second_per_gpu:884.975434413774 mfu:13.004461858786634 
Step 1820 | loss:2.033325672149658 lr:0.00014411594904938682 tokens_per_second_per_gpu:863.1324229568368 mfu:12.683485029004975 
Step 1821 | loss:2.035817861557007 lr:0.00014405946284373167 tokens_per_second_per_gpu:864.1082377702942 mfu:12.697824349656573 
Step 1822 | loss:2.0808634757995605 lr:0.00014400295918830377 tokens_per_second_per_gpu:893.1369427034851 mfu:13.124392897701886 
Step 1823 | loss:2.100435733795166 lr:0.0001439464381054814 tokens_per_second_per_gpu:865.6895241600573 mfu:12.721060902609159 
Step 1824 | loss:2.1250064373016357 lr:0.0001438898996176498 tokens_per_second_per_gpu:868.1849891423981 mfu:12.757731049509095 
Step 1825 | loss:2.0867397785186768 lr:0.00014383334374720104 tokens_per_second_per_gpu:865.6916085205617 mfu:12.721091531692888 
Step 1826 | loss:2.059840679168701 lr:0.00014377677051653404 tokens_per_second_per_gpu:894.1323002452168 mfu:13.139019393177298 
Step 1827 | loss:2.071058988571167 lr:0.0001437201799480548 tokens_per_second_per_gpu:897.8760586453035 mfu:13.19403285618341 
Step 1828 | loss:2.115842342376709 lr:0.0001436635720641759 tokens_per_second_per_gpu:844.2568447686879 mfu:12.406113785617944 
Step 1829 | loss:2.0608341693878174 lr:0.000143606946887317 tokens_per_second_per_gpu:892.203698687872 mfu:13.110679142795206 
Step 1830 | loss:2.042166233062744 lr:0.0001435503044399045 tokens_per_second_per_gpu:859.4783626168659 mfu:12.629789653435218 
Step 1831 | loss:2.0579466819763184 lr:0.00014349364474437173 tokens_per_second_per_gpu:902.4327598462347 mfu:13.260992282021768 
Step 1832 | loss:2.0329136848449707 lr:0.0001434369678231587 tokens_per_second_per_gpu:882.8588832327969 mfu:12.97335974223645 
Step 1833 | loss:2.065032482147217 lr:0.0001433802736987124 tokens_per_second_per_gpu:865.7282991996343 mfu:12.721630690767839 
Step 1834 | loss:2.0934619903564453 lr:0.00014332356239348654 tokens_per_second_per_gpu:889.0232996605289 mfu:13.063944085257475 
Step 1835 | loss:2.106207847595215 lr:0.00014326683392994167 tokens_per_second_per_gpu:882.9268613714264 mfu:12.97435866161507 
Step 1836 | loss:2.0605247020721436 lr:0.0001432100883305451 tokens_per_second_per_gpu:866.3624394098496 mfu:12.730949200475772 
Step 1837 | loss:2.0365960597991943 lr:0.000143153325617771 tokens_per_second_per_gpu:834.396213006098 mfu:12.261214611388228 
Step 1838 | loss:2.04243803024292 lr:0.00014309654581410024 tokens_per_second_per_gpu:900.6715469695089 mfu:13.235111760608472 
Step 1839 | loss:2.071894884109497 lr:0.0001430397489420205 tokens_per_second_per_gpu:888.0160672918556 mfu:13.049143092583568 
Step 1840 | loss:2.039379835128784 lr:0.0001429829350240262 tokens_per_second_per_gpu:896.333114833802 mfu:13.171359736493693 
Step 1841 | loss:2.053377866744995 lr:0.00014292610408261856 tokens_per_second_per_gpu:879.7823775453934 mfu:12.928151367727523 
Step 1842 | loss:2.0547666549682617 lr:0.00014286925614030542 tokens_per_second_per_gpu:879.0905193347672 mfu:12.917984708448742 
Step 1843 | loss:2.050100326538086 lr:0.00014281239121960153 tokens_per_second_per_gpu:859.1341616950057 mfu:12.62473171895927 
Step 1844 | loss:2.107468366622925 lr:0.00014275550934302823 tokens_per_second_per_gpu:889.0573283641191 mfu:13.064444127361172 
Step 1845 | loss:2.0381009578704834 lr:0.00014269861053311356 tokens_per_second_per_gpu:887.5909692904494 mfu:13.042896398573134 
Step 1846 | loss:2.058676242828369 lr:0.00014264169481239245 tokens_per_second_per_gpu:858.4403532619848 mfu:12.61453640171806 
Step 1847 | loss:2.0749011039733887 lr:0.0001425847622034063 tokens_per_second_per_gpu:852.4446329858384 mfu:12.526431000579159 
Step 1848 | loss:2.066648483276367 lr:0.00014252781272870336 tokens_per_second_per_gpu:848.318602043087 mfu:12.46580015147686 
Step 1849 | loss:2.054727792739868 lr:0.00014247084641083845 tokens_per_second_per_gpu:861.8695344551126 mfu:12.664927242298216 
Step 1850 | loss:2.116119861602783 lr:0.0001424138632723731 tokens_per_second_per_gpu:900.6391710235373 mfu:13.234636005307076 
Step 1851 | loss:2.0917394161224365 lr:0.00014235686333587556 tokens_per_second_per_gpu:887.8220318188689 mfu:13.046291796593213 
Step 1852 | loss:2.06032395362854 lr:0.00014229984662392068 tokens_per_second_per_gpu:873.959753418817 mfu:12.842589565187465 
Step 1853 | loss:2.0846519470214844 lr:0.0001422428131590899 tokens_per_second_per_gpu:860.2988601473403 mfu:12.641846630866858 
Step 1854 | loss:2.0061750411987305 lr:0.0001421857629639714 tokens_per_second_per_gpu:882.6687782869445 mfu:12.970566204222436 
Step 1855 | loss:2.068629741668701 lr:0.00014212869606115996 tokens_per_second_per_gpu:888.5855572418902 mfu:13.057511585138498 
Step 1856 | loss:2.0582823753356934 lr:0.00014207161247325691 tokens_per_second_per_gpu:886.0370303639628 mfu:13.020061708801475 
Step 1857 | loss:2.0529379844665527 lr:0.00014201451222287025 tokens_per_second_per_gpu:836.9880087360746 mfu:12.299300311177818 
Step 1858 | loss:2.045802116394043 lr:0.00014195739533261458 tokens_per_second_per_gpu:871.3113584897507 mfu:12.803672156293667 
Step 1859 | loss:2.0518798828125 lr:0.00014190026182511102 tokens_per_second_per_gpu:846.4496050161804 mfu:12.43833577268685 
Step 1860 | loss:2.116187810897827 lr:0.00014184311172298742 tokens_per_second_per_gpu:865.8739077965834 mfu:12.723770367612754 
Step 1861 | loss:2.0530548095703125 lr:0.00014178594504887798 tokens_per_second_per_gpu:862.4936250998718 mfu:12.674098076505127 
Step 1862 | loss:2.108381748199463 lr:0.00014172876182542372 tokens_per_second_per_gpu:885.161273491668 mfu:13.007192711086445 
Step 1863 | loss:2.025848865509033 lr:0.00014167156207527202 tokens_per_second_per_gpu:880.4440223207696 mfu:12.937874049183812 
Step 1864 | loss:1.9987175464630127 lr:0.00014161434582107686 tokens_per_second_per_gpu:871.6095395845308 mfu:12.808053842522787 
Step 1865 | loss:2.0416417121887207 lr:0.00014155711308549878 tokens_per_second_per_gpu:897.0396279015574 mfu:13.181741744722482 
Step 1866 | loss:2.0101118087768555 lr:0.00014149986389120484 tokens_per_second_per_gpu:871.2527713817736 mfu:12.802811235434765 
Step 1867 | loss:2.042935371398926 lr:0.00014144259826086858 tokens_per_second_per_gpu:825.5106216960965 mfu:12.130643378797771 
Step 1868 | loss:2.063390016555786 lr:0.00014138531621717018 tokens_per_second_per_gpu:873.3327025812357 mfu:12.83337523179046 
Step 1869 | loss:2.0851125717163086 lr:0.0001413280177827961 tokens_per_second_per_gpu:830.9041826852374 mfu:12.209900220783204 
Step 1870 | loss:2.045267105102539 lr:0.00014127070298043947 tokens_per_second_per_gpu:875.8314368268976 mfu:12.870093419583414 
Step 1871 | loss:2.0257060527801514 lr:0.00014121337183279988 tokens_per_second_per_gpu:888.9569447231025 mfu:13.06296901835805 
Step 1872 | loss:2.0165786743164062 lr:0.0001411560243625833 tokens_per_second_per_gpu:871.6441925879193 mfu:12.808563058534139 
Step 1873 | loss:2.068344831466675 lr:0.00014109866059250226 tokens_per_second_per_gpu:889.8688581375393 mfu:13.076369326158021 
Step 1874 | loss:2.0630791187286377 lr:0.0001410412805452757 tokens_per_second_per_gpu:887.6696795805435 mfu:13.04405302385969 
Step 1875 | loss:2.1089274883270264 lr:0.000140983884243629 tokens_per_second_per_gpu:882.4321735207867 mfu:12.967089364597905 
Step 1876 | loss:2.0152647495269775 lr:0.00014092647171029405 tokens_per_second_per_gpu:878.3338156046292 mfu:12.906865162736718 
Step 1877 | loss:2.1046342849731445 lr:0.00014086904296800902 tokens_per_second_per_gpu:869.3959047929873 mfu:12.77552510997669 
Step 1878 | loss:2.053088665008545 lr:0.0001408115980395187 tokens_per_second_per_gpu:857.1350119507794 mfu:12.595354783071759 
Step 1879 | loss:2.090214490890503 lr:0.00014075413694757412 tokens_per_second_per_gpu:871.0371315458157 mfu:12.799642469486127 
Step 1880 | loss:2.0022051334381104 lr:0.00014069665971493274 tokens_per_second_per_gpu:850.3248509764671 mfu:12.49528140792626 
Step 1881 | loss:2.0594663619995117 lr:0.00014063916636435856 tokens_per_second_per_gpu:890.4498111792568 mfu:13.084906265579132 
Step 1882 | loss:2.0566370487213135 lr:0.00014058165691862174 tokens_per_second_per_gpu:848.0277178162107 mfu:12.46152569064254 
Step 1883 | loss:2.033376932144165 lr:0.000140524131400499 tokens_per_second_per_gpu:896.3219984113634 mfu:13.171196383833285 
Step 1884 | loss:2.0566797256469727 lr:0.0001404665898327733 tokens_per_second_per_gpu:862.1124855746174 mfu:12.668497339776959 
Step 1885 | loss:2.104295492172241 lr:0.00014040903223823406 tokens_per_second_per_gpu:876.8967387373906 mfu:12.88574772762901 
Step 1886 | loss:2.049069404602051 lr:0.00014035145863967692 tokens_per_second_per_gpu:880.8660636945193 mfu:12.944075826921736 
Step 1887 | loss:2.0253610610961914 lr:0.000140293869059904 tokens_per_second_per_gpu:861.3979335421577 mfu:12.657997201252327 
Step 1888 | loss:2.102871894836426 lr:0.00014023626352172364 tokens_per_second_per_gpu:874.5259066120018 mfu:12.850909025051205 
Step 1889 | loss:2.086185932159424 lr:0.00014017864204795058 tokens_per_second_per_gpu:889.8467282615566 mfu:13.076044133935767 
Step 1890 | loss:2.0397424697875977 lr:0.00014012100466140578 tokens_per_second_per_gpu:856.8795789188372 mfu:12.591601267446135 
Step 1891 | loss:2.066640853881836 lr:0.00014006335138491664 tokens_per_second_per_gpu:876.19199793471 mfu:12.875391762330537 
Step 1892 | loss:2.1285247802734375 lr:0.0001400056822413167 tokens_per_second_per_gpu:867.769930498788 mfu:12.75163188100103 
Step 1893 | loss:2.0869877338409424 lr:0.00013994799725344589 tokens_per_second_per_gpu:870.4604473597279 mfu:12.7911682596822 
Step 1894 | loss:2.038761615753174 lr:0.00013989029644415036 tokens_per_second_per_gpu:833.0747261660961 mfu:12.241795738796496 
Step 1895 | loss:2.0671045780181885 lr:0.00013983257983628253 tokens_per_second_per_gpu:853.6506183316743 mfu:12.544152611623161 
Step 1896 | loss:2.01121187210083 lr:0.00013977484745270112 tokens_per_second_per_gpu:850.313768746524 mfu:12.49511855771483 
Step 1897 | loss:2.0334715843200684 lr:0.00013971709931627109 tokens_per_second_per_gpu:838.1034466831181 mfu:12.315691353995613 
Step 1898 | loss:2.037745952606201 lr:0.0001396593354498635 tokens_per_second_per_gpu:877.470167555932 mfu:12.894174100734372 
Step 1899 | loss:2.113788366317749 lr:0.00013960155587635593 tokens_per_second_per_gpu:863.9151296370097 mfu:12.694986680658921 
Step 1900 | loss:2.0471744537353516 lr:0.00013954376061863194 tokens_per_second_per_gpu:859.2316534133208 mfu:12.626164331982269 
Step 1901 | loss:2.0847575664520264 lr:0.0001394859496995813 tokens_per_second_per_gpu:852.0188466010303 mfu:12.52017419097077 
Step 1902 | loss:2.0381221771240234 lr:0.00013942812314210015 tokens_per_second_per_gpu:876.3824239031626 mfu:12.878190017680193 
Step 1903 | loss:2.0146894454956055 lr:0.00013937028096909067 tokens_per_second_per_gpu:889.2678735764367 mfu:13.06753802926699 
Step 1904 | loss:2.0219688415527344 lr:0.0001393124232034613 tokens_per_second_per_gpu:877.0297844308409 mfu:12.887702796186474 
Step 1905 | loss:2.0921478271484375 lr:0.0001392545498681267 tokens_per_second_per_gpu:848.8143280065325 mfu:12.473084703265924 
Step 1906 | loss:2.036616325378418 lr:0.00013919666098600753 tokens_per_second_per_gpu:882.3238578899039 mfu:12.965497697263705 
Step 1907 | loss:2.0676255226135254 lr:0.00013913875658003074 tokens_per_second_per_gpu:877.1830147858353 mfu:12.889954472594253 
Step 1908 | loss:2.0829336643218994 lr:0.00013908083667312946 tokens_per_second_per_gpu:878.1884451669498 mfu:12.904728985574412 
Step 1909 | loss:2.0394554138183594 lr:0.00013902290128824283 tokens_per_second_per_gpu:871.4832085514952 mfu:12.806197443986955 
Step 1910 | loss:2.0718178749084473 lr:0.0001389649504483162 tokens_per_second_per_gpu:850.2733202998124 mfu:12.494524179315098 
Step 1911 | loss:2.0807199478149414 lr:0.00013890698417630106 tokens_per_second_per_gpu:858.467183385987 mfu:12.614930662745751 
Step 1912 | loss:2.0780322551727295 lr:0.00013884900249515493 tokens_per_second_per_gpu:854.8516200343797 mfu:12.561800989451317 
Step 1913 | loss:2.0573625564575195 lr:0.0001387910054278416 tokens_per_second_per_gpu:877.8374639437883 mfu:12.899571416502704 
Step 1914 | loss:2.0806002616882324 lr:0.00013873299299733066 tokens_per_second_per_gpu:877.0100881435732 mfu:12.887413364857002 
Step 1915 | loss:2.0995397567749023 lr:0.00013867496522659812 tokens_per_second_per_gpu:833.6003163636509 mfu:12.249519136996787 
Step 1916 | loss:2.080674648284912 lr:0.00013861692213862584 tokens_per_second_per_gpu:855.5368500881114 mfu:12.571870249853047 
Step 1917 | loss:2.0046284198760986 lr:0.00013855886375640182 tokens_per_second_per_gpu:892.6294688026586 mfu:13.116935713320265 
Step 1918 | loss:2.0574004650115967 lr:0.00013850079010292013 tokens_per_second_per_gpu:892.5787483363875 mfu:13.116190390519844 
Step 1919 | loss:2.009324789047241 lr:0.00013844270120118085 tokens_per_second_per_gpu:902.5145455915674 mfu:13.262194100246786 
Step 1920 | loss:2.038400411605835 lr:0.00013838459707419008 tokens_per_second_per_gpu:890.6512192574098 mfu:13.08786589990178 
Step 1921 | loss:2.04702091217041 lr:0.0001383264777449601 tokens_per_second_per_gpu:892.829263285601 mfu:13.119871636321044 
Step 1922 | loss:2.070034980773926 lr:0.000138268343236509 tokens_per_second_per_gpu:851.7969450988342 mfu:12.516913411620857 
Step 1923 | loss:2.0282092094421387 lr:0.00013821019357186098 tokens_per_second_per_gpu:875.3074331185506 mfu:12.862393334390003 
Step 1924 | loss:2.0741515159606934 lr:0.00013815202877404635 tokens_per_second_per_gpu:900.3279814579653 mfu:13.230063163306083 
Step 1925 | loss:2.023756265640259 lr:0.00013809384886610118 tokens_per_second_per_gpu:847.5499087012853 mfu:12.454504421837555 
Step 1926 | loss:2.058187246322632 lr:0.00013803565387106773 tokens_per_second_per_gpu:860.2876600541119 mfu:12.641682048688034 
Step 1927 | loss:2.0537993907928467 lr:0.00013797744381199416 tokens_per_second_per_gpu:884.9300520447488 mfu:13.003794977804294 
Step 1928 | loss:2.062279224395752 lr:0.00013791921871193457 tokens_per_second_per_gpu:853.1590088012374 mfu:12.536928549644292 
Step 1929 | loss:2.0273241996765137 lr:0.000137860978593949 tokens_per_second_per_gpu:877.0795914597815 mfu:12.888434696285584 
Step 1930 | loss:2.0740551948547363 lr:0.00013780272348110355 tokens_per_second_per_gpu:881.6114483538373 mfu:12.955029042113123 
Step 1931 | loss:2.0725042819976807 lr:0.00013774445339647014 tokens_per_second_per_gpu:894.4396228515351 mfu:13.143535411313843 
Step 1932 | loss:2.03645396232605 lr:0.0001376861683631267 tokens_per_second_per_gpu:865.8011911521149 mfu:12.722701817240942 
Step 1933 | loss:2.034783363342285 lr:0.00013762786840415702 tokens_per_second_per_gpu:868.4688813863662 mfu:12.761902765146754 
Step 1934 | loss:2.032823085784912 lr:0.00013756955354265085 tokens_per_second_per_gpu:820.8852785809416 mfu:12.062675279587564 
Step 1935 | loss:2.0451533794403076 lr:0.0001375112238017038 tokens_per_second_per_gpu:887.0167933884587 mfu:13.034459047289346 
Step 1936 | loss:2.0750133991241455 lr:0.0001374528792044174 tokens_per_second_per_gpu:870.6613911960198 mfu:12.794121072102975 
Step 1937 | loss:2.0416419506073 lr:0.0001373945197738991 tokens_per_second_per_gpu:857.4083948274512 mfu:12.59937206655136 
Step 1938 | loss:1.9993168115615845 lr:0.00013733614553326212 tokens_per_second_per_gpu:881.1700160050701 mfu:12.948542319522254 
Step 1939 | loss:2.047508478164673 lr:0.0001372777565056256 tokens_per_second_per_gpu:855.4963579896576 mfu:12.571275230003403 
Step 1940 | loss:2.0077943801879883 lr:0.00013721935271411464 tokens_per_second_per_gpu:870.4781562059139 mfu:12.791428486131245 
Step 1941 | loss:2.076582431793213 lr:0.00013716093418185996 tokens_per_second_per_gpu:849.7242788933842 mfu:12.486456172282201 
Step 1942 | loss:2.0106375217437744 lr:0.00013710250093199836 tokens_per_second_per_gpu:859.862142499361 mfu:12.635429189460739 
Step 1943 | loss:2.0579819679260254 lr:0.00013704405298767229 tokens_per_second_per_gpu:826.2746381196418 mfu:12.14187038245586 
Step 1944 | loss:2.06016206741333 lr:0.00013698559037203013 tokens_per_second_per_gpu:849.8505140798655 mfu:12.488311162380228 
Step 1945 | loss:2.0394768714904785 lr:0.000136927113108226 tokens_per_second_per_gpu:859.991270699326 mfu:12.637326691567623 
Step 1946 | loss:2.065173625946045 lr:0.0001368686212194199 tokens_per_second_per_gpu:868.7181370628033 mfu:12.765565506293303 
Step 1947 | loss:2.080702066421509 lr:0.0001368101147287775 tokens_per_second_per_gpu:874.3528116409973 mfu:12.848365443771046 
Step 1948 | loss:2.0394911766052246 lr:0.00013675159365947036 tokens_per_second_per_gpu:863.5809404761167 mfu:12.690075866157802 
Step 1949 | loss:2.0201821327209473 lr:0.0001366930580346758 tokens_per_second_per_gpu:874.2902049062575 mfu:12.847445455642147 
Step 1950 | loss:2.0033254623413086 lr:0.00013663450787757686 tokens_per_second_per_gpu:900.3224786675338 mfu:13.229982301368564 
Step 1951 | loss:2.0373916625976562 lr:0.00013657594321136234 tokens_per_second_per_gpu:869.418366968567 mfu:12.775855185246844 
Step 1952 | loss:2.027034044265747 lr:0.00013651736405922686 tokens_per_second_per_gpu:878.8457713508278 mfu:12.914388206559101 
Step 1953 | loss:2.0722057819366455 lr:0.00013645877044437068 tokens_per_second_per_gpu:887.4569216362935 mfu:13.040926606488583 
Step 1954 | loss:2.04073429107666 lr:0.00013640016238999984 tokens_per_second_per_gpu:901.6135022227287 mfu:13.24895352466975 
Step 1955 | loss:2.06316876411438 lr:0.00013634153991932607 tokens_per_second_per_gpu:884.5142754310519 mfu:12.997685258930371 
Step 1956 | loss:2.042742967605591 lr:0.0001362829030555669 tokens_per_second_per_gpu:891.3319963446805 mfu:13.097869725230122 
Step 1957 | loss:2.1290621757507324 lr:0.0001362242518219454 tokens_per_second_per_gpu:875.5339064652675 mfu:12.865721295692525 
Step 1958 | loss:2.0073108673095703 lr:0.0001361655862416905 tokens_per_second_per_gpu:881.3557377208222 mfu:12.951271447218828 
Step 1959 | loss:2.0809736251831055 lr:0.0001361069063380367 tokens_per_second_per_gpu:838.5957002779148 mfu:12.32292488031674 
Step 1960 | loss:2.0165135860443115 lr:0.0001360482121342242 tokens_per_second_per_gpu:847.5468943367127 mfu:12.454460126609023 
Step 1961 | loss:2.0537712574005127 lr:0.00013598950365349883 tokens_per_second_per_gpu:878.6070153873713 mfu:12.910879755703192 
Step 1962 | loss:2.040301561355591 lr:0.00013593078091911218 tokens_per_second_per_gpu:884.9520517112355 mfu:13.004118256635103 
Step 1963 | loss:2.071603298187256 lr:0.00013587204395432137 tokens_per_second_per_gpu:887.0600710046865 mfu:13.035094999529022 
Step 1964 | loss:2.0221011638641357 lr:0.00013581329278238927 tokens_per_second_per_gpu:894.9461307382602 mfu:13.150978400393484 
Step 1965 | loss:2.070392370223999 lr:0.0001357545274265843 tokens_per_second_per_gpu:884.9868990202575 mfu:13.004630327912379 
Step 1966 | loss:2.0906717777252197 lr:0.00013569574791018042 tokens_per_second_per_gpu:885.6080547893696 mfu:13.013758034957867 
Step 1967 | loss:2.037543296813965 lr:0.00013563695425645737 tokens_per_second_per_gpu:877.3626468264092 mfu:12.892594114249173 
Step 1968 | loss:2.0174717903137207 lr:0.00013557814648870037 tokens_per_second_per_gpu:851.2587687687934 mfu:12.509005063789765 
Step 1969 | loss:2.0444860458374023 lr:0.0001355193246302003 tokens_per_second_per_gpu:865.0747265936768 mfu:12.712026627541212 
Step 1970 | loss:2.063868522644043 lr:0.00013546048870425356 tokens_per_second_per_gpu:887.438125500064 mfu:13.040650402622145 
Step 1971 | loss:1.9993736743927002 lr:0.00013540163873416216 tokens_per_second_per_gpu:895.5668964946287 mfu:13.16010037631283 
Step 1972 | loss:2.031784772872925 lr:0.00013534277474323367 tokens_per_second_per_gpu:864.612017690778 mfu:12.705227252049557 
Step 1973 | loss:2.0849270820617676 lr:0.0001352838967547812 tokens_per_second_per_gpu:883.5585074921943 mfu:12.983640521389198 
Step 1974 | loss:2.0556795597076416 lr:0.00013522500479212337 tokens_per_second_per_gpu:882.785641009232 mfu:12.972283468629564 
Step 1975 | loss:2.1005735397338867 lr:0.0001351660988785844 tokens_per_second_per_gpu:899.6148200150922 mfu:13.219583459099216 
Step 1976 | loss:1.9860750436782837 lr:0.000135107179037494 tokens_per_second_per_gpu:881.4280676618584 mfu:12.952334315093884 
Step 1977 | loss:2.0472490787506104 lr:0.00013504824529218747 tokens_per_second_per_gpu:848.5633644112712 mfu:12.469396864738878 
Step 1978 | loss:2.0822134017944336 lr:0.00013498929766600544 tokens_per_second_per_gpu:846.3627443560656 mfu:12.43705938003507 
Step 1979 | loss:2.0255844593048096 lr:0.00013493033618229417 tokens_per_second_per_gpu:883.1784215900666 mfu:12.978055267352676 
Step 1980 | loss:2.0094006061553955 lr:0.00013487136086440547 tokens_per_second_per_gpu:847.2004039230477 mfu:12.44936854870333 
Step 1981 | loss:2.0364837646484375 lr:0.00013481237173569647 tokens_per_second_per_gpu:882.273076736167 mfu:12.964751482678265 
Step 1982 | loss:2.101639747619629 lr:0.00013475336881952986 tokens_per_second_per_gpu:853.9407374086001 mfu:12.548415828796966 
Step 1983 | loss:2.0444743633270264 lr:0.0001346943521392738 tokens_per_second_per_gpu:844.3396271463506 mfu:12.407330249071087 
Step 1984 | loss:2.031278610229492 lr:0.0001346353217183018 tokens_per_second_per_gpu:837.5180546255863 mfu:12.307089184501887 
Step 1985 | loss:2.086026191711426 lr:0.00013457627757999303 tokens_per_second_per_gpu:891.5570827816083 mfu:13.101177306288456 
Step 1986 | loss:1.9977893829345703 lr:0.0001345172197477318 tokens_per_second_per_gpu:879.5186301878866 mfu:12.92427567545667 
Step 1987 | loss:2.0543863773345947 lr:0.00013445814824490805 tokens_per_second_per_gpu:847.7736673357161 mfu:12.457792491216518 
Step 1988 | loss:2.06022047996521 lr:0.00013439906309491712 tokens_per_second_per_gpu:856.6312928133189 mfu:12.587952773867984 
Step 1989 | loss:2.0717549324035645 lr:0.00013433996432115968 tokens_per_second_per_gpu:885.4255311980875 mfu:13.01107590278916 
Step 1990 | loss:2.067723274230957 lr:0.0001342808519470418 tokens_per_second_per_gpu:896.7783101346395 mfu:13.177901754593085 
Step 1991 | loss:2.0732779502868652 lr:0.00013422172599597505 tokens_per_second_per_gpu:860.8141220000151 mfu:12.649418256981923 
Step 1992 | loss:2.056600570678711 lr:0.0001341625864913762 tokens_per_second_per_gpu:880.3433959136433 mfu:12.936395372801877 
Step 1993 | loss:2.0563642978668213 lr:0.00013410343345666753 tokens_per_second_per_gpu:836.2555260343487 mfu:12.288536686577183 
Step 1994 | loss:2.0677242279052734 lr:0.0001340442669152766 tokens_per_second_per_gpu:871.4944745485388 mfu:12.80636299460357 
Step 1995 | loss:2.0590782165527344 lr:0.0001339850868906364 tokens_per_second_per_gpu:877.8978555487746 mfu:12.900458853931015 
Step 1996 | loss:2.0354950428009033 lr:0.0001339258934061852 tokens_per_second_per_gpu:884.7714635970194 mfu:13.001464565750418 
Step 1997 | loss:2.027038097381592 lr:0.00013386668648536655 tokens_per_second_per_gpu:898.8203232135405 mfu:13.207908554970887 
Step 1998 | loss:1.9960901737213135 lr:0.00013380746615162942 tokens_per_second_per_gpu:801.3462775226732 mfu:11.77555522614861 
Step 1999 | loss:2.0111782550811768 lr:0.0001337482324284281 tokens_per_second_per_gpu:891.8339668932173 mfu:13.105246039417876 
Step 2000 | loss:2.0682148933410645 lr:0.000133688985339222 tokens_per_second_per_gpu:874.1216585862655 mfu:12.844968715492602 
Step 2001 | loss:2.070192337036133 lr:0.0001336297249074761 tokens_per_second_per_gpu:894.6963922457898 mfu:13.14730856440289 
Step 2002 | loss:2.0212674140930176 lr:0.0001335704511566605 tokens_per_second_per_gpu:867.4923944884641 mfu:12.747553568405735 
Step 2003 | loss:1.993485450744629 lr:0.00013351116411025054 tokens_per_second_per_gpu:870.2940634384006 mfu:12.788723295364914 
Step 2004 | loss:2.07989501953125 lr:0.00013345186379172693 tokens_per_second_per_gpu:866.9875188698021 mfu:12.740134565040211 
Step 2005 | loss:2.0524206161499023 lr:0.00013339255022457556 tokens_per_second_per_gpu:858.64018603267 mfu:12.617472887346313 
Step 2006 | loss:2.052722215652466 lr:0.0001333332234322876 tokens_per_second_per_gpu:880.9239495698976 mfu:12.944926443367397 
Step 2007 | loss:2.062894344329834 lr:0.00013327388343835957 tokens_per_second_per_gpu:876.9733448355457 mfu:12.886873432414555 
Step 2008 | loss:2.0428695678710938 lr:0.00013321453026629294 tokens_per_second_per_gpu:877.6453304568621 mfu:12.896748069655589 
Step 2009 | loss:2.0339794158935547 lr:0.00013315516393959463 tokens_per_second_per_gpu:862.0620631048695 mfu:12.667756395950539 
Step 2010 | loss:2.0737738609313965 lr:0.00013309578448177672 tokens_per_second_per_gpu:896.2068461251292 mfu:13.169504253796617 
Step 2011 | loss:2.0567803382873535 lr:0.00013303639191635644 tokens_per_second_per_gpu:896.8219558453097 mfu:13.178543115875716 
Step 2012 | loss:2.0395960807800293 lr:0.0001329769862668563 tokens_per_second_per_gpu:881.7142049129999 mfu:12.956539020472302 
Step 2013 | loss:2.0578362941741943 lr:0.00013291756755680388 tokens_per_second_per_gpu:902.5985976239635 mfu:13.263429220914482 
Step 2014 | loss:2.007322311401367 lr:0.00013285813580973205 tokens_per_second_per_gpu:877.4475003657784 mfu:12.893841012833471 
Step 2015 | loss:2.087463140487671 lr:0.00013279869104917873 tokens_per_second_per_gpu:854.2016481165814 mfu:12.552249837311269 
Step 2016 | loss:2.0722579956054688 lr:0.00013273923329868708 tokens_per_second_per_gpu:869.2864008494794 mfu:12.773915980727041 
Step 2017 | loss:2.051548957824707 lr:0.00013267976258180534 tokens_per_second_per_gpu:887.3667862126462 mfu:13.039602092119749 
Step 2018 | loss:2.0264892578125 lr:0.00013262027892208694 tokens_per_second_per_gpu:862.9493352823318 mfu:12.680794607794029 
Step 2019 | loss:2.1125619411468506 lr:0.00013256078234309042 tokens_per_second_per_gpu:841.93537319075 mfu:12.372000422220973 
Step 2020 | loss:2.090275287628174 lr:0.00013250127286837943 tokens_per_second_per_gpu:832.5734804634287 mfu:12.234430076012268 
Step 2021 | loss:2.0173442363739014 lr:0.0001324417505215227 tokens_per_second_per_gpu:881.6875351928265 mfu:12.956147116533174 
Step 2022 | loss:2.018979072570801 lr:0.00013238221532609412 tokens_per_second_per_gpu:901.5321854272715 mfu:13.247758597529538 
Step 2023 | loss:2.0483808517456055 lr:0.00013232266730567262 tokens_per_second_per_gpu:860.9746295002351 mfu:12.651776868965365 
Step 2024 | loss:2.0662806034088135 lr:0.0001322631064838422 tokens_per_second_per_gpu:843.6329436955456 mfu:12.396945737111931 
Step 2025 | loss:2.0511722564697266 lr:0.00013220353288419202 tokens_per_second_per_gpu:864.0577954164138 mfu:12.697083113638492 
Step 2026 | loss:2.075723171234131 lr:0.00013214394653031616 tokens_per_second_per_gpu:880.989379396379 mfu:12.945887916025075 
Step 2027 | loss:2.0594050884246826 lr:0.00013208434744581385 tokens_per_second_per_gpu:881.5604370932208 mfu:12.954279446172649 
Step 2028 | loss:2.0963878631591797 lr:0.00013202473565428942 tokens_per_second_per_gpu:868.5749140451225 mfu:12.763460884856027 
Step 2029 | loss:2.0851073265075684 lr:0.000131965111179352 tokens_per_second_per_gpu:890.2803012430398 mfu:13.082415365363717 
Step 2030 | loss:2.071361780166626 lr:0.00013190547404461598 tokens_per_second_per_gpu:898.5835683255502 mfu:13.2044295093488 
Step 2031 | loss:2.0195040702819824 lr:0.0001318458242737007 tokens_per_second_per_gpu:882.4700446796348 mfu:12.96764587048681 
Step 2032 | loss:2.060518503189087 lr:0.00013178616189023044 tokens_per_second_per_gpu:864.4714856372017 mfu:12.70316217356308 
Step 2033 | loss:2.0984244346618652 lr:0.00013172648691783454 tokens_per_second_per_gpu:887.5041174379954 mfu:13.04162013534742 
Step 2034 | loss:2.0881543159484863 lr:0.00013166679938014726 tokens_per_second_per_gpu:877.1781610041069 mfu:12.889883147654707 
Step 2035 | loss:2.051649570465088 lr:0.00013160709930080792 tokens_per_second_per_gpu:873.5625368667376 mfu:12.836752581130819 
Step 2036 | loss:2.0482304096221924 lr:0.0001315473867034608 tokens_per_second_per_gpu:888.5479591636084 mfu:13.056959092090707 
Step 2037 | loss:2.0531580448150635 lr:0.00013148766161175498 tokens_per_second_per_gpu:881.2852413099041 mfu:12.950235522546441 
Step 2038 | loss:2.0772643089294434 lr:0.00013142792404934476 tokens_per_second_per_gpu:897.0227139816294 mfu:13.181493199488306 
Step 2039 | loss:2.0322458744049072 lr:0.00013136817403988917 tokens_per_second_per_gpu:827.3863187640087 mfu:12.158206212781362 
Step 2040 | loss:2.066791296005249 lr:0.0001313084116070522 tokens_per_second_per_gpu:880.067414465685 mfu:12.932339904057612 
Step 2041 | loss:2.0373032093048096 lr:0.00013124863677450285 tokens_per_second_per_gpu:892.7539328189748 mfu:13.11876467657736 
Step 2042 | loss:2.027803659439087 lr:0.0001311888495659149 tokens_per_second_per_gpu:896.5237378491064 mfu:13.174160887390695 
Step 2043 | loss:2.0848560333251953 lr:0.0001311290500049672 tokens_per_second_per_gpu:856.8359159224843 mfu:12.590959652155323 
Step 2044 | loss:2.0204715728759766 lr:0.0001310692381153433 tokens_per_second_per_gpu:809.2764096821136 mfu:11.892086258753931 
Step 2045 | loss:2.024458408355713 lr:0.0001310094139207318 tokens_per_second_per_gpu:858.3622768321088 mfu:12.613389090826809 
Step 2046 | loss:2.0814390182495117 lr:0.0001309495774448261 tokens_per_second_per_gpu:855.510340843761 mfu:12.571480704060415 
Step 2047 | loss:2.042524576187134 lr:0.00013088972871132444 tokens_per_second_per_gpu:875.060867548601 mfu:12.858770123591814 
Step 2048 | loss:2.0341711044311523 lr:0.0001308298677439299 tokens_per_second_per_gpu:878.9712162367042 mfu:12.916231583414913 
Step 2049 | loss:2.0801467895507812 lr:0.00013076999456635056 tokens_per_second_per_gpu:879.9453669249272 mfu:12.930546450220337 
Step 2050 | loss:2.1014955043792725 lr:0.00013071010920229909 tokens_per_second_per_gpu:878.0501139609336 mfu:12.902696247915756 
Step 2051 | loss:2.0223772525787354 lr:0.00013065021167549322 tokens_per_second_per_gpu:830.6256407403157 mfu:12.20580712626561 
Step 2052 | loss:2.037026882171631 lr:0.00013059030200965536 tokens_per_second_per_gpu:868.0224616099812 mfu:12.755342753728074 
Step 2053 | loss:2.073895215988159 lr:0.00013053038022851275 tokens_per_second_per_gpu:875.870813483887 mfu:12.870672048338555 
Step 2054 | loss:2.0709784030914307 lr:0.00013047044635579747 tokens_per_second_per_gpu:855.4839410048111 mfu:12.57109276594897 
Step 2055 | loss:2.0499603748321533 lr:0.00013041050041524637 tokens_per_second_per_gpu:883.6179520084268 mfu:12.98451404161812 
Step 2056 | loss:2.0191822052001953 lr:0.00013035054243060098 tokens_per_second_per_gpu:846.496280013639 mfu:12.43902164847572 
Step 2057 | loss:2.0651297569274902 lr:0.00013029057242560784 tokens_per_second_per_gpu:874.854214493619 mfu:12.855733415829079 
Step 2058 | loss:2.039053440093994 lr:0.00013023059042401798 tokens_per_second_per_gpu:870.8347194741727 mfu:12.796668081765205 
Step 2059 | loss:2.005948066711426 lr:0.00013017059644958735 tokens_per_second_per_gpu:887.1683397331086 mfu:13.036685977644927 
Step 2060 | loss:1.9989964962005615 lr:0.00013011059052607656 tokens_per_second_per_gpu:836.8870677207985 mfu:12.297817011718763 
Step 2061 | loss:2.041004180908203 lr:0.00013005057267725104 tokens_per_second_per_gpu:879.0170245760107 mfu:12.916904723909168 
Step 2062 | loss:2.0200109481811523 lr:0.00012999054292688086 tokens_per_second_per_gpu:871.7776880101175 mfu:12.810524735727416 
Step 2063 | loss:2.020503044128418 lr:0.00012993050129874082 tokens_per_second_per_gpu:882.3822129003895 mfu:12.966355207516102 
Step 2064 | loss:2.0279524326324463 lr:0.00012987044781661046 tokens_per_second_per_gpu:846.6428326677561 mfu:12.441175197971738 
Step 2065 | loss:1.9976965188980103 lr:0.00012981038250427403 tokens_per_second_per_gpu:851.8410466799708 mfu:12.517561471790101 
Step 2066 | loss:2.0629453659057617 lr:0.00012975030538552032 tokens_per_second_per_gpu:864.9606868483907 mfu:12.710350845976787 
Step 2067 | loss:2.060637950897217 lr:0.00012969021648414296 tokens_per_second_per_gpu:867.7109788789573 mfu:12.750765603744297 
Step 2068 | loss:2.005977153778076 lr:0.00012963011582394025 tokens_per_second_per_gpu:868.1747400347762 mfu:12.757580441792799 
Step 2069 | loss:2.0372841358184814 lr:0.00012957000342871502 tokens_per_second_per_gpu:893.5991969251969 mfu:13.131185591783044 
Step 2070 | loss:2.089169979095459 lr:0.0001295098793222748 tokens_per_second_per_gpu:886.7481578439081 mfu:13.030511524502641 
Step 2071 | loss:2.0024728775024414 lr:0.00012944974352843184 tokens_per_second_per_gpu:880.5730956902905 mfu:12.93977074557294 
Step 2072 | loss:2.053431272506714 lr:0.00012938959607100288 tokens_per_second_per_gpu:879.2001266398255 mfu:12.919595356566923 
Step 2073 | loss:2.0534157752990723 lr:0.00012932943697380943 tokens_per_second_per_gpu:867.0298975960056 mfu:12.740757308347096 
Step 2074 | loss:2.0298922061920166 lr:0.00012926926626067743 tokens_per_second_per_gpu:886.0320060028871 mfu:13.019987877247024 
Step 2075 | loss:2.059589385986328 lr:0.0001292090839554376 tokens_per_second_per_gpu:886.2697589730225 mfu:13.023481589401854 
Step 2076 | loss:2.0071892738342285 lr:0.00012914889008192517 tokens_per_second_per_gpu:882.9859019073723 mfu:12.975226245468786 
Step 2077 | loss:2.0366439819335938 lr:0.0001290886846639799 tokens_per_second_per_gpu:854.0981503492928 mfu:12.550728967109867 
Step 2078 | loss:2.0619874000549316 lr:0.00012902846772544624 tokens_per_second_per_gpu:877.419206124713 mfu:12.893425237022697 
Step 2079 | loss:2.0375912189483643 lr:0.0001289682392901731 tokens_per_second_per_gpu:861.1653499097295 mfu:12.654579451042238 
Step 2080 | loss:2.0604910850524902 lr:0.000128907999382014 tokens_per_second_per_gpu:886.98501025832 mfu:13.033992003247706 
Step 2081 | loss:2.034550189971924 lr:0.00012884774802482697 tokens_per_second_per_gpu:882.422960603556 mfu:12.966953983404172 
Step 2082 | loss:2.060234785079956 lr:0.00012878748524247462 tokens_per_second_per_gpu:856.3699443421618 mfu:12.584112332548541 
Step 2083 | loss:2.009690761566162 lr:0.000128727211058824 tokens_per_second_per_gpu:901.1424147716106 mfu:13.242031028799255 
Step 2084 | loss:2.025503635406494 lr:0.00012866692549774682 tokens_per_second_per_gpu:865.8113488160755 mfu:12.722851081218689 
Step 2085 | loss:2.0201632976531982 lr:0.00012860662858311912 tokens_per_second_per_gpu:904.4391112928416 mfu:13.290475044873828 
Step 2086 | loss:2.014986753463745 lr:0.00012854632033882155 tokens_per_second_per_gpu:855.3933365738924 mfu:12.569761359651912 
Step 2087 | loss:2.0475006103515625 lr:0.00012848600078873925 tokens_per_second_per_gpu:849.8325810199366 mfu:12.488047641174115 
Step 2088 | loss:2.024923086166382 lr:0.00012842566995676177 tokens_per_second_per_gpu:853.7069417187507 mfu:12.544980267748416 
Step 2089 | loss:2.0523841381073 lr:0.00012836532786678322 tokens_per_second_per_gpu:881.4674472971521 mfu:12.95291298761436 
Step 2090 | loss:2.045668125152588 lr:0.00012830497454270205 tokens_per_second_per_gpu:881.5992258940088 mfu:12.954849436548404 
Step 2091 | loss:2.0127220153808594 lr:0.00012824461000842126 tokens_per_second_per_gpu:887.7183167263944 mfu:13.044767732860123 
Step 2092 | loss:2.0047242641448975 lr:0.00012818423428784828 tokens_per_second_per_gpu:864.0058715547352 mfu:12.69632010728543 
Step 2093 | loss:2.0224106311798096 lr:0.00012812384740489485 tokens_per_second_per_gpu:866.6380785432182 mfu:12.734999639004673 
Step 2094 | loss:2.0591845512390137 lr:0.00012806344938347735 tokens_per_second_per_gpu:888.3523203891056 mfu:13.054084236041389 
Step 2095 | loss:2.068732976913452 lr:0.00012800304024751635 tokens_per_second_per_gpu:865.2079941947892 mfu:12.713984956968543 
Step 2096 | loss:2.0510497093200684 lr:0.00012794262002093697 tokens_per_second_per_gpu:869.1246203490603 mfu:12.771538662368382 
Step 2097 | loss:2.0271902084350586 lr:0.00012788218872766867 tokens_per_second_per_gpu:897.7662850326203 mfu:13.192419764222066 
Step 2098 | loss:2.0916833877563477 lr:0.0001278217463916453 tokens_per_second_per_gpu:864.3191557054057 mfu:12.70092372861765 
Step 2099 | loss:2.042095184326172 lr:0.000127761293036805 tokens_per_second_per_gpu:873.5148118659488 mfu:12.836051275842182 
Step 2100 | loss:1.9896057844161987 lr:0.00012770082868709048 tokens_per_second_per_gpu:868.9491728026627 mfu:12.768960510663124 
Step 2101 | loss:2.0317182540893555 lr:0.00012764035336644856 tokens_per_second_per_gpu:895.934612375645 mfu:13.165503856413624 
Step 2102 | loss:1.99092698097229 lr:0.0001275798670988306 tokens_per_second_per_gpu:896.9654566914452 mfu:13.180651819922973 
Step 2103 | loss:2.0372862815856934 lr:0.00012751936990819217 tokens_per_second_per_gpu:881.2438316035137 mfu:12.949627018709613 
Step 2104 | loss:2.029531955718994 lr:0.00012745886181849325 tokens_per_second_per_gpu:852.7891141223992 mfu:12.531493052730294 
Step 2105 | loss:2.0272114276885986 lr:0.00012739834285369807 tokens_per_second_per_gpu:884.3315778536788 mfu:12.995000570085628 
Step 2106 | loss:2.002532958984375 lr:0.00012733781303777522 tokens_per_second_per_gpu:862.1461739731616 mfu:12.668992381194963 
Step 2107 | loss:2.0431699752807617 lr:0.00012727727239469753 tokens_per_second_per_gpu:867.8225933363997 mfu:12.752405746394876 
Step 2108 | loss:2.1076526641845703 lr:0.0001272167209484422 tokens_per_second_per_gpu:855.6120340599232 mfu:12.572975056897175 
Step 2109 | loss:2.05305814743042 lr:0.00012715615872299063 tokens_per_second_per_gpu:855.4141495736168 mfu:12.570067200752758 
Step 2110 | loss:2.0002450942993164 lr:0.0001270955857423285 tokens_per_second_per_gpu:895.3246876037792 mfu:13.1565411856727 
Step 2111 | loss:2.0426487922668457 lr:0.00012703500203044586 tokens_per_second_per_gpu:858.7042125381626 mfu:12.618413738601896 
Step 2112 | loss:2.019155263900757 lr:0.00012697440761133682 tokens_per_second_per_gpu:853.6224064380581 mfu:12.543738045884691 
Step 2113 | loss:2.0424888134002686 lr:0.00012691380250899986 tokens_per_second_per_gpu:839.6063122800429 mfu:12.337775535741331 
Step 2114 | loss:1.980059027671814 lr:0.0001268531867474377 tokens_per_second_per_gpu:880.4278725162166 mfu:12.937636732407356 
Step 2115 | loss:2.0412845611572266 lr:0.00012679256035065715 tokens_per_second_per_gpu:876.6220032322781 mfu:12.881710567659868 
Step 2116 | loss:2.050551652908325 lr:0.00012673192334266948 tokens_per_second_per_gpu:884.4763196238341 mfu:12.99712750915779 
Step 2117 | loss:2.0327811241149902 lr:0.00012667127574748986 tokens_per_second_per_gpu:872.4244568189068 mfu:12.820028819093217 
Step 2118 | loss:2.0551226139068604 lr:0.00012661061758913785 tokens_per_second_per_gpu:882.9689046832102 mfu:12.974976476102626 
Step 2119 | loss:2.0699868202209473 lr:0.0001265499488916372 tokens_per_second_per_gpu:886.2987503470299 mfu:13.023907609382583 
Step 2120 | loss:2.0477499961853027 lr:0.00012648926967901567 tokens_per_second_per_gpu:872.1750953832099 mfu:12.816364523844475 
Step 2121 | loss:2.0956645011901855 lr:0.0001264285799753054 tokens_per_second_per_gpu:867.2650963143635 mfu:12.744213486499822 
Step 2122 | loss:2.107697010040283 lr:0.0001263678798045425 tokens_per_second_per_gpu:898.2559440063197 mfu:13.199615163325438 
Step 2123 | loss:2.020004987716675 lr:0.00012630716919076736 tokens_per_second_per_gpu:897.6262584343697 mfu:13.190362113257581 
Step 2124 | loss:2.0334181785583496 lr:0.0001262464481580244 tokens_per_second_per_gpu:877.9116376010197 mfu:12.900661377261933 
Step 2125 | loss:2.0269432067871094 lr:0.00012618571673036225 tokens_per_second_per_gpu:879.2066165241869 mfu:12.919690723568495 
Step 2126 | loss:2.0654425621032715 lr:0.00012612497493183364 tokens_per_second_per_gpu:876.421807628624 mfu:12.878768750304518 
Step 2127 | loss:2.045348644256592 lr:0.00012606422278649534 tokens_per_second_per_gpu:863.1242957210779 mfu:12.683365601591136 
Step 2128 | loss:2.062105178833008 lr:0.00012600346031840828 tokens_per_second_per_gpu:885.2744981375798 mfu:13.008856514997804 
Step 2129 | loss:2.0672667026519775 lr:0.00012594268755163754 tokens_per_second_per_gpu:830.2895982090587 mfu:12.200869077015058 
Step 2130 | loss:2.076700210571289 lr:0.00012588190451025207 tokens_per_second_per_gpu:900.2764940645783 mfu:13.229306570730207 
Step 2131 | loss:2.0425920486450195 lr:0.00012582111121832513 tokens_per_second_per_gpu:850.784803564244 mfu:12.502040280152535 
Step 2132 | loss:2.0361390113830566 lr:0.00012576030769993393 tokens_per_second_per_gpu:876.0707506479756 mfu:12.873610067998126 
Step 2133 | loss:2.0018672943115234 lr:0.00012569949397915966 tokens_per_second_per_gpu:881.0622448681617 mfu:12.946958653371867 
Step 2134 | loss:2.028665542602539 lr:0.0001256386700800877 tokens_per_second_per_gpu:887.4722127368349 mfu:13.041151304854251 
Step 2135 | loss:2.033795118331909 lr:0.0001255778360268074 tokens_per_second_per_gpu:878.4363463764906 mfu:12.90837182321584 
Step 2136 | loss:2.001352071762085 lr:0.000125516991843412 tokens_per_second_per_gpu:889.987833804817 mfu:13.078117639689754 
Step 2137 | loss:2.0264463424682617 lr:0.000125456137553999 tokens_per_second_per_gpu:899.4004481803906 mfu:13.21643332606776 
Step 2138 | loss:2.0848121643066406 lr:0.0001253952731826697 tokens_per_second_per_gpu:849.8202798333602 mfu:12.487866878742267 
Step 2139 | loss:2.020550489425659 lr:0.0001253343987535295 tokens_per_second_per_gpu:867.06577771533 mfu:12.741284556477494 
Step 2140 | loss:2.0292797088623047 lr:0.0001252735142906877 tokens_per_second_per_gpu:887.2701986626546 mfu:13.038182765592644 
Step 2141 | loss:1.979280948638916 lr:0.00012521261981825768 tokens_per_second_per_gpu:894.9215665881404 mfu:13.150617437206368 
Step 2142 | loss:2.036281108856201 lr:0.0001251517153603567 tokens_per_second_per_gpu:901.5232033721351 mfu:13.247626608788503 
Step 2143 | loss:2.017444133758545 lr:0.00012509080094110604 tokens_per_second_per_gpu:882.67195245779 mfu:12.970612847758616 
Step 2144 | loss:1.9932751655578613 lr:0.00012502987658463075 tokens_per_second_per_gpu:874.4412356291352 mfu:12.849664809082698 
Step 2145 | loss:2.047319173812866 lr:0.00012496894231506017 tokens_per_second_per_gpu:877.9659799146987 mfu:12.901459922078066 
Step 2146 | loss:2.077096939086914 lr:0.0001249079981565272 tokens_per_second_per_gpu:897.2554657984625 mfu:13.184913421120307 
Step 2147 | loss:2.01611065864563 lr:0.00012484704413316878 tokens_per_second_per_gpu:878.8136419980785 mfu:12.913916074874844 
Step 2148 | loss:2.081258773803711 lr:0.0001247860802691259 tokens_per_second_per_gpu:870.8872491304014 mfu:12.797439990096574 
Step 2149 | loss:2.043156147003174 lr:0.00012472510658854326 tokens_per_second_per_gpu:862.8332972757354 mfu:12.679089462349 
Step 2150 | loss:2.081580638885498 lr:0.00012466412311556952 tokens_per_second_per_gpu:819.8566496986124 mfu:12.047559871241841 
Step 2151 | loss:2.0642945766448975 lr:0.00012460312987435724 tokens_per_second_per_gpu:879.4346653283995 mfu:12.923041835770034 
Step 2152 | loss:2.0513617992401123 lr:0.00012454212688906276 tokens_per_second_per_gpu:864.3357675208907 mfu:12.701167834513113 
Step 2153 | loss:2.0923285484313965 lr:0.00012448111418384645 tokens_per_second_per_gpu:899.2225776380421 mfu:13.21381956912737 
Step 2154 | loss:2.030954360961914 lr:0.0001244200917828723 tokens_per_second_per_gpu:867.4569543741208 mfu:12.747032786023167 
Step 2155 | loss:2.0307459831237793 lr:0.0001243590597103084 tokens_per_second_per_gpu:907.9741072203561 mfu:13.342420802826737 
Step 2156 | loss:2.056518077850342 lr:0.0001242980179903264 tokens_per_second_per_gpu:905.4877020701114 mfu:13.305883787578097 
Step 2157 | loss:2.0401175022125244 lr:0.00012423696664710197 tokens_per_second_per_gpu:900.4810760643043 mfu:13.232312844926048 
Step 2158 | loss:2.0221376419067383 lr:0.00012417590570481456 tokens_per_second_per_gpu:883.0948981674344 mfu:12.976827914454848 
Step 2159 | loss:2.1076712608337402 lr:0.0001241148351876473 tokens_per_second_per_gpu:873.7468774454569 mfu:12.839461413412215 
Step 2160 | loss:2.0257773399353027 lr:0.00012405375511978728 tokens_per_second_per_gpu:891.0762115144856 mfu:13.094111040029409 
Step 2161 | loss:2.0698163509368896 lr:0.00012399266552542526 tokens_per_second_per_gpu:889.4124910311589 mfu:13.069663141559282 
Step 2162 | loss:2.0584895610809326 lr:0.0001239315664287558 tokens_per_second_per_gpu:880.8636548643046 mfu:12.944040429848062 
Step 2163 | loss:2.030303716659546 lr:0.0001238704578539772 tokens_per_second_per_gpu:899.0887845529493 mfu:13.211853517862668 
Step 2164 | loss:1.9994865655899048 lr:0.0001238093398252916 tokens_per_second_per_gpu:906.4200974132871 mfu:13.319585071485113 
Step 2165 | loss:2.0452051162719727 lr:0.00012374821236690482 tokens_per_second_per_gpu:835.6905224769572 mfu:12.280234120283867 
Step 2166 | loss:2.0671463012695312 lr:0.0001236870755030264 tokens_per_second_per_gpu:855.1607344439507 mfu:12.566343337626133 
Step 2167 | loss:2.0305233001708984 lr:0.0001236259292578696 tokens_per_second_per_gpu:856.0889936103262 mfu:12.579983841593565 
Step 2168 | loss:2.050987720489502 lr:0.00012356477365565148 tokens_per_second_per_gpu:857.3541919783332 mfu:12.598575571127215 
Step 2169 | loss:2.0576589107513428 lr:0.0001235036087205927 tokens_per_second_per_gpu:875.8232094333085 mfu:12.869972520378797 
Step 2170 | loss:2.033029079437256 lr:0.00012344243447691766 tokens_per_second_per_gpu:872.3524375357231 mfu:12.818970516246788 
Step 2171 | loss:2.002016305923462 lr:0.0001233812509488545 tokens_per_second_per_gpu:855.4319011716642 mfu:12.570328055428226 
Step 2172 | loss:2.061467409133911 lr:0.00012332005816063498 tokens_per_second_per_gpu:842.1113792760476 mfu:12.374586781496225 
Step 2173 | loss:2.0863349437713623 lr:0.00012325885613649447 tokens_per_second_per_gpu:852.3929942968135 mfu:12.525672184756992 
Step 2174 | loss:2.081911563873291 lr:0.0001231976449006721 tokens_per_second_per_gpu:864.4098457084968 mfu:12.7022563923734 
Step 2175 | loss:1.998650312423706 lr:0.00012313642447741064 tokens_per_second_per_gpu:878.8263620826073 mfu:12.914102992892749 
Step 2176 | loss:2.0756406784057617 lr:0.00012307519489095648 tokens_per_second_per_gpu:893.4872472587358 mfu:13.129540523331443 
Step 2177 | loss:2.0327260494232178 lr:0.00012301395616555957 tokens_per_second_per_gpu:851.8544233513832 mfu:12.517758038165184 
Step 2178 | loss:2.052485466003418 lr:0.00012295270832547356 tokens_per_second_per_gpu:878.2648331374897 mfu:12.905851485036802 
Step 2179 | loss:2.1111483573913574 lr:0.0001228914513949557 tokens_per_second_per_gpu:886.2429172892714 mfu:13.023087158506948 
Step 2180 | loss:2.087996244430542 lr:0.00012283018539826685 tokens_per_second_per_gpu:886.1224690905148 mfu:13.02131720654469 
Step 2181 | loss:2.1282365322113037 lr:0.00012276891035967137 tokens_per_second_per_gpu:853.6954097414076 mfu:12.544810808627087 
Step 2182 | loss:2.0248196125030518 lr:0.00012270762630343734 tokens_per_second_per_gpu:867.7035935535328 mfu:12.75065707849143 
Step 2183 | loss:2.0419156551361084 lr:0.0001226463332538363 tokens_per_second_per_gpu:878.8807902795968 mfu:12.91490279973966 
Step 2184 | loss:2.048584222793579 lr:0.0001225850312351434 tokens_per_second_per_gpu:882.0921667773025 mfu:12.962093062378173 
Step 2185 | loss:2.0397839546203613 lr:0.00012252372027163737 tokens_per_second_per_gpu:856.8165084245519 mfu:12.59067446450285 
Step 2186 | loss:2.0327165126800537 lr:0.00012246240038760043 tokens_per_second_per_gpu:902.5033166837012 mfu:13.262029094645065 
Step 2187 | loss:2.0320169925689697 lr:0.00012240107160731828 tokens_per_second_per_gpu:872.7258736589131 mfu:12.824458053676496 
Step 2188 | loss:2.0334813594818115 lr:0.00012233973395508034 tokens_per_second_per_gpu:870.8333471533217 mfu:12.796647915901305 
Step 2189 | loss:2.023629665374756 lr:0.00012227838745517932 tokens_per_second_per_gpu:870.3591140294718 mfu:12.789679195266292 
Step 2190 | loss:2.0244827270507812 lr:0.0001222170321319116 tokens_per_second_per_gpu:872.8673056660868 mfu:12.82653635672467 
Step 2191 | loss:2.0399746894836426 lr:0.00012215566800957695 tokens_per_second_per_gpu:888.5702317327344 mfu:13.057286381148044 
Step 2192 | loss:2.0798192024230957 lr:0.00012209429511247864 tokens_per_second_per_gpu:865.3136466798999 mfu:12.715537490134414 
Step 2193 | loss:2.1010937690734863 lr:0.00012203291346492352 tokens_per_second_per_gpu:855.9001567667024 mfu:12.577208937980485 
Step 2194 | loss:2.0045251846313477 lr:0.00012197152309122173 tokens_per_second_per_gpu:861.1673725873075 mfu:12.65460917371294 
Step 2195 | loss:2.04988169670105 lr:0.00012191012401568698 tokens_per_second_per_gpu:868.2040215450669 mfu:12.758010725243542 
Step 2196 | loss:2.048454761505127 lr:0.00012184871626263646 tokens_per_second_per_gpu:852.0750944281856 mfu:12.521000736764513 
Step 2197 | loss:2.0083744525909424 lr:0.00012178729985639069 tokens_per_second_per_gpu:879.7461837368579 mfu:12.927619510023545 
Step 2198 | loss:2.037355422973633 lr:0.0001217258748212737 tokens_per_second_per_gpu:851.5492993235982 mfu:12.513274327513761 
Step 2199 | loss:2.06307315826416 lr:0.00012166444118161287 tokens_per_second_per_gpu:869.4097052654207 mfu:12.775727903987026 
Step 2200 | loss:2.068427085876465 lr:0.00012160299896173903 tokens_per_second_per_gpu:880.7156494331512 mfu:12.941865532207425 
Step 2201 | loss:2.025698661804199 lr:0.00012154154818598647 tokens_per_second_per_gpu:889.2299903375855 mfu:13.06698134586588 
Step 2202 | loss:2.031978130340576 lr:0.00012148008887869269 tokens_per_second_per_gpu:826.8151907504827 mfu:12.149813649350147 
Step 2203 | loss:2.0347652435302734 lr:0.00012141862106419876 tokens_per_second_per_gpu:901.8367180721642 mfu:13.252233617977858 
Step 2204 | loss:2.060981035232544 lr:0.00012135714476684903 tokens_per_second_per_gpu:872.543845821599 mfu:12.821783206471096 
Step 2205 | loss:2.065709114074707 lr:0.0001212956600109912 tokens_per_second_per_gpu:860.6543691032913 mfu:12.647070733681852 
Step 2206 | loss:2.048572063446045 lr:0.00012123416682097634 tokens_per_second_per_gpu:846.8081683121236 mfu:12.443604758157777 
Step 2207 | loss:1.9910027980804443 lr:0.00012117266522115889 tokens_per_second_per_gpu:885.1089415122523 mfu:13.006423707559518 
Step 2208 | loss:2.0324864387512207 lr:0.00012111115523589651 tokens_per_second_per_gpu:864.2320403975419 mfu:12.699643593989753 
Step 2209 | loss:2.052751064300537 lr:0.00012104963688955037 tokens_per_second_per_gpu:878.0240406240198 mfu:12.902313107658703 
Step 2210 | loss:2.0660974979400635 lr:0.00012098811020648475 tokens_per_second_per_gpu:893.3473323416808 mfu:13.127484513490307 
Step 2211 | loss:2.0221354961395264 lr:0.0001209265752110674 tokens_per_second_per_gpu:847.5119567680832 mfu:12.453946728992532 
Step 2212 | loss:2.085679292678833 lr:0.00012086503192766922 tokens_per_second_per_gpu:885.1830478967379 mfu:13.007512679764917 
Step 2213 | loss:1.9839818477630615 lr:0.00012080348038066452 tokens_per_second_per_gpu:865.9245811173486 mfu:12.724514997623402 
Step 2214 | loss:2.01108455657959 lr:0.00012074192059443077 tokens_per_second_per_gpu:886.2087370688531 mfu:13.022584889906634 
Step 2215 | loss:2.0739800930023193 lr:0.00012068035259334878 tokens_per_second_per_gpu:879.4544326156023 mfu:12.923332310423321 
Step 2216 | loss:2.0529518127441406 lr:0.00012061877640180255 tokens_per_second_per_gpu:876.9753364557315 mfu:12.886902698705725 
Step 2217 | loss:2.040743827819824 lr:0.00012055719204417943 tokens_per_second_per_gpu:859.2371612226297 mfu:12.626245267670761 
Step 2218 | loss:1.9928473234176636 lr:0.00012049559954486989 tokens_per_second_per_gpu:844.5301288412987 mfu:12.41012961720002 
Step 2219 | loss:2.0788381099700928 lr:0.00012043399892826768 tokens_per_second_per_gpu:848.8393165458839 mfu:12.47345190273188 
Step 2220 | loss:2.0237789154052734 lr:0.00012037239021876976 tokens_per_second_per_gpu:879.7828219447938 mfu:12.928157898050094 
Step 2221 | loss:2.027122974395752 lr:0.0001203107734407763 tokens_per_second_per_gpu:882.6704539743191 mfu:12.970590827970964 
Step 2222 | loss:2.032973527908325 lr:0.00012024914861869063 tokens_per_second_per_gpu:861.4579850045959 mfu:12.658879640382809 
Step 2223 | loss:2.043083667755127 lr:0.00012018751577691934 tokens_per_second_per_gpu:838.7970086513812 mfu:12.325883049507429 
Step 2224 | loss:2.0240721702575684 lr:0.00012012587493987206 tokens_per_second_per_gpu:888.4416630786623 mfu:13.055397101408632 
Step 2225 | loss:2.0235471725463867 lr:0.00012006422613196178 tokens_per_second_per_gpu:851.2840226623892 mfu:12.509376162560738 
Step 2226 | loss:2.0389657020568848 lr:0.00012000256937760445 tokens_per_second_per_gpu:839.3183437612904 mfu:12.33354392040714 
Step 2227 | loss:2.0897703170776367 lr:0.00011994090470121933 tokens_per_second_per_gpu:859.4628387863997 mfu:12.629561535169616 
Step 2228 | loss:2.0301337242126465 lr:0.00011987923212722872 tokens_per_second_per_gpu:871.0356948556616 mfu:12.79962135773366 
Step 2229 | loss:2.0083532333374023 lr:0.00011981755168005806 tokens_per_second_per_gpu:894.537592549652 mfu:13.144975048113842 
Step 2230 | loss:2.0716845989227295 lr:0.00011975586338413594 tokens_per_second_per_gpu:883.5180768814195 mfu:12.983046405083476 
Step 2231 | loss:2.048454999923706 lr:0.00011969416726389404 tokens_per_second_per_gpu:852.0242080607673 mfu:12.520252976094001 
Step 2232 | loss:2.0262398719787598 lr:0.0001196324633437671 tokens_per_second_per_gpu:870.6238807991476 mfu:12.793569867508515 
Step 2233 | loss:2.061283588409424 lr:0.00011957075164819309 tokens_per_second_per_gpu:898.72610204465 mfu:13.206524001739828 
Step 2234 | loss:2.0570220947265625 lr:0.00011950903220161285 tokens_per_second_per_gpu:871.9644373889791 mfu:12.81326896464058 
Step 2235 | loss:2.0445234775543213 lr:0.00011944730502847041 tokens_per_second_per_gpu:868.3077460848134 mfu:12.759534927801603 
Step 2236 | loss:2.0170698165893555 lr:0.00011938557015321297 tokens_per_second_per_gpu:884.2656362801731 mfu:12.994031577451237 
Step 2237 | loss:2.0971627235412598 lr:0.00011932382760029049 tokens_per_second_per_gpu:845.7155922003196 mfu:12.427549663494965 
Step 2238 | loss:2.066802740097046 lr:0.00011926207739415624 tokens_per_second_per_gpu:896.027848407153 mfu:13.166873933331537 
Step 2239 | loss:2.064934492111206 lr:0.00011920031955926643 tokens_per_second_per_gpu:856.9792298827062 mfu:12.593065609967331 
Step 2240 | loss:2.0821259021759033 lr:0.00011913855412008023 tokens_per_second_per_gpu:861.3847111045188 mfu:12.657802901298602 
Step 2241 | loss:2.0324225425720215 lr:0.00011907678110105991 tokens_per_second_per_gpu:873.6039518646686 mfu:12.837361162725326 
Step 2242 | loss:2.052290201187134 lr:0.00011901500052667068 tokens_per_second_per_gpu:896.3340062216758 mfu:13.171372835184522 
Step 2243 | loss:2.101457357406616 lr:0.00011895321242138075 tokens_per_second_per_gpu:884.9847077003569 mfu:13.004598127090796 
Step 2244 | loss:2.067018508911133 lr:0.00011889141680966142 tokens_per_second_per_gpu:857.7347353751176 mfu:12.604167547917365 
Step 2245 | loss:2.0622477531433105 lr:0.00011882961371598676 tokens_per_second_per_gpu:899.1033031719196 mfu:13.212066864831748 
Step 2246 | loss:2.0356838703155518 lr:0.00011876780316483401 tokens_per_second_per_gpu:871.2908765558809 mfu:12.803371180111226 
Step 2247 | loss:2.030488967895508 lr:0.0001187059851806832 tokens_per_second_per_gpu:868.5015115556963 mfu:12.762382256187973 
Step 2248 | loss:2.0559659004211426 lr:0.00011864415978801742 tokens_per_second_per_gpu:887.9582895201637 mfu:13.048294064690776 
Step 2249 | loss:2.043475389480591 lr:0.00011858232701132264 tokens_per_second_per_gpu:900.9022985303026 mfu:13.238502589047892 
Step 2250 | loss:2.047377586364746 lr:0.00011852048687508774 tokens_per_second_per_gpu:903.5745140318116 mfu:13.277770034466705 
Step 2251 | loss:2.058749198913574 lr:0.00011845863940380454 tokens_per_second_per_gpu:870.0397535618398 mfu:12.784986284187605 
Step 2252 | loss:2.045081615447998 lr:0.00011839678462196784 tokens_per_second_per_gpu:887.4091208913277 mfu:13.040224188160845 
Step 2253 | loss:1.9813404083251953 lr:0.00011833492255407512 tokens_per_second_per_gpu:875.0649380340982 mfu:12.858829938216422 
Step 2254 | loss:2.0498037338256836 lr:0.000118273053224627 tokens_per_second_per_gpu:869.6590949170675 mfu:12.77939261386111 
Step 2255 | loss:1.9655296802520752 lr:0.00011821117665812682 tokens_per_second_per_gpu:870.0019001499061 mfu:12.78443003908455 
Step 2256 | loss:2.0073888301849365 lr:0.00011814929287908081 tokens_per_second_per_gpu:877.465884559499 mfu:12.894111163322115 
Step 2257 | loss:2.009749174118042 lr:0.00011808740191199808 tokens_per_second_per_gpu:866.344473492606 mfu:12.730685196440781 
Step 2258 | loss:2.019216537475586 lr:0.0001180255037813906 tokens_per_second_per_gpu:881.3994283848947 mfu:12.951913469078894 
Step 2259 | loss:2.041443347930908 lr:0.0001179635985117731 tokens_per_second_per_gpu:905.1401221353638 mfu:13.300776199470526 
Step 2260 | loss:2.0616683959960938 lr:0.0001179016861276633 tokens_per_second_per_gpu:826.363363272434 mfu:12.143174173296297 
Step 2261 | loss:2.0599846839904785 lr:0.0001178397666535815 tokens_per_second_per_gpu:876.8205366835649 mfu:12.884627960159765 
Step 2262 | loss:2.0296287536621094 lr:0.00011777784011405105 tokens_per_second_per_gpu:876.0124429526434 mfu:12.872753253028424 
Step 2263 | loss:2.0675456523895264 lr:0.00011771590653359792 tokens_per_second_per_gpu:873.349636815283 mfu:12.833624075534834 
Step 2264 | loss:1.9863046407699585 lr:0.00011765396593675097 tokens_per_second_per_gpu:885.5511703662867 mfu:13.012922134568349 
Step 2265 | loss:2.0861599445343018 lr:0.00011759201834804179 tokens_per_second_per_gpu:873.2765485575025 mfu:12.83255006441128 
Step 2266 | loss:1.9924317598342896 lr:0.00011753006379200477 tokens_per_second_per_gpu:832.4914033653556 mfu:12.233223976441742 
Step 2267 | loss:2.0560426712036133 lr:0.000117468102293177 tokens_per_second_per_gpu:856.9898012081106 mfu:12.593220952582135 
Step 2268 | loss:2.0573723316192627 lr:0.00011740613387609845 tokens_per_second_per_gpu:889.8439097497858 mfu:13.076002716708354 
Step 2269 | loss:2.069349765777588 lr:0.00011734415856531162 tokens_per_second_per_gpu:866.3310908500388 mfu:12.73048854232128 
Step 2270 | loss:2.0563321113586426 lr:0.00011728217638536197 tokens_per_second_per_gpu:888.8845180815949 mfu:13.061904729497117 
Step 2271 | loss:2.0117039680480957 lr:0.00011722018736079752 tokens_per_second_per_gpu:859.5764464560227 mfu:12.631230967505278 
Step 2272 | loss:2.0499911308288574 lr:0.00011715819151616909 tokens_per_second_per_gpu:876.300400074024 mfu:12.876984700881485 
Step 2273 | loss:2.029618501663208 lr:0.00011709618887603014 tokens_per_second_per_gpu:879.6602174823739 mfu:12.926356260407672 
Step 2274 | loss:2.0801796913146973 lr:0.00011703417946493683 tokens_per_second_per_gpu:881.1352948303418 mfu:12.948032101752483 
Step 2275 | loss:2.0015869140625 lr:0.00011697216330744807 tokens_per_second_per_gpu:866.8042187846207 mfu:12.737441022514895 
Step 2276 | loss:2.036742925643921 lr:0.00011691014042812536 tokens_per_second_per_gpu:878.7384257832817 mfu:12.912810794029241 
Step 2277 | loss:2.0284698009490967 lr:0.00011684811085153289 tokens_per_second_per_gpu:873.1037347005472 mfu:12.830010614021978 
Step 2278 | loss:1.9859375953674316 lr:0.00011678607460223752 tokens_per_second_per_gpu:867.3983916195315 mfu:12.746172223030358 
Step 2279 | loss:2.0307064056396484 lr:0.00011672403170480872 tokens_per_second_per_gpu:864.7749879811811 mfu:12.707622054033033 
Step 2280 | loss:2.0010323524475098 lr:0.00011666198218381861 tokens_per_second_per_gpu:883.066112631972 mfu:12.976404919212891 
Step 2281 | loss:2.035625457763672 lr:0.000116599926063842 tokens_per_second_per_gpu:886.558611673347 mfu:13.027726197532322 
Step 2282 | loss:2.017479419708252 lr:0.00011653786336945614 tokens_per_second_per_gpu:886.7581917272072 mfu:13.030658969558836 
Step 2283 | loss:1.998329758644104 lr:0.00011647579412524106 tokens_per_second_per_gpu:887.9362243652836 mfu:13.047969823526683 
Step 2284 | loss:1.9680290222167969 lr:0.0001164137183557793 tokens_per_second_per_gpu:865.8480163557213 mfu:12.723389900266357 
Step 2285 | loss:2.1008312702178955 lr:0.000116351636085656 tokens_per_second_per_gpu:872.9807745716349 mfu:12.82820374996179 
Step 2286 | loss:2.0639255046844482 lr:0.0001162895473394589 tokens_per_second_per_gpu:880.9746916722139 mfu:12.945672084103341 
Step 2287 | loss:2.0289828777313232 lr:0.00011622745214177824 tokens_per_second_per_gpu:872.3711856405478 mfu:12.819246014305419 
Step 2288 | loss:2.031435012817383 lr:0.00011616535051720685 tokens_per_second_per_gpu:895.84353020322 mfu:13.16416542984125 
Step 2289 | loss:2.028085470199585 lr:0.00011610324249034017 tokens_per_second_per_gpu:833.3395373450114 mfu:12.245687063619842 
Step 2290 | loss:2.015054225921631 lr:0.00011604112808577603 tokens_per_second_per_gpu:848.8071095182311 mfu:12.472978629637048 
Step 2291 | loss:2.0148205757141113 lr:0.00011597900732811496 tokens_per_second_per_gpu:864.9262021995823 mfu:12.70984410388802 
Step 2292 | loss:2.0107266902923584 lr:0.00011591688024195985 tokens_per_second_per_gpu:870.1105635555597 mfu:12.786026816869919 
Step 2293 | loss:2.040811061859131 lr:0.0001158547468519162 tokens_per_second_per_gpu:852.1371035691365 mfu:12.52191194342295 
Step 2294 | loss:2.0850956439971924 lr:0.00011579260718259197 tokens_per_second_per_gpu:863.2982189961765 mfu:12.685921354563956 
Step 2295 | loss:2.0336623191833496 lr:0.00011573046125859759 tokens_per_second_per_gpu:852.8479329762978 mfu:12.532357379029486 
Step 2296 | loss:2.045433521270752 lr:0.00011566830910454599 tokens_per_second_per_gpu:869.0985361408138 mfu:12.771155362360192 
Step 2297 | loss:2.0426034927368164 lr:0.0001156061507450526 tokens_per_second_per_gpu:886.5847819645821 mfu:13.028110762505504 
Step 2298 | loss:2.0833559036254883 lr:0.00011554398620473516 tokens_per_second_per_gpu:875.3646161377052 mfu:12.863233622563717 
Step 2299 | loss:2.034576416015625 lr:0.00011548181550821411 tokens_per_second_per_gpu:849.5923753769904 mfu:12.484517887691151 
Step 2300 | loss:2.057864189147949 lr:0.00011541963868011212 tokens_per_second_per_gpu:840.269314403096 mfu:12.347518163034993 
Step 2301 | loss:2.0145041942596436 lr:0.00011535745574505434 tokens_per_second_per_gpu:869.0525111385972 mfu:12.770479038066204 
Step 2302 | loss:2.01741623878479 lr:0.00011529526672766837 tokens_per_second_per_gpu:874.5752124487927 mfu:12.851633560274477 
Step 2303 | loss:1.9989820718765259 lr:0.00011523307165258419 tokens_per_second_per_gpu:875.9507696846159 mfu:12.871846981926899 
Step 2304 | loss:2.052180528640747 lr:0.00011517087054443418 tokens_per_second_per_gpu:820.5397777055975 mfu:12.057598242665554 
Step 2305 | loss:1.9756076335906982 lr:0.0001151086634278532 tokens_per_second_per_gpu:889.4980268013026 mfu:13.070920065330428 
Step 2306 | loss:2.030022621154785 lr:0.00011504645032747832 tokens_per_second_per_gpu:857.6594206541711 mfu:12.603060819551958 
Step 2307 | loss:2.031148672103882 lr:0.00011498423126794911 tokens_per_second_per_gpu:861.8896671590533 mfu:12.665223086646353 
Step 2308 | loss:2.046142816543579 lr:0.00011492200627390743 tokens_per_second_per_gpu:893.3461275162111 mfu:13.127466808923314 
Step 2309 | loss:1.9928317070007324 lr:0.00011485977536999757 tokens_per_second_per_gpu:863.029175707012 mfu:12.681967840086324 
Step 2310 | loss:2.0311038494110107 lr:0.00011479753858086608 tokens_per_second_per_gpu:866.5238534916639 mfu:12.733321134417437 
Step 2311 | loss:2.0813350677490234 lr:0.00011473529593116188 tokens_per_second_per_gpu:853.89246670796 mfu:12.547706504604497 
Step 2312 | loss:1.997220516204834 lr:0.00011467304744553618 tokens_per_second_per_gpu:880.7302352358948 mfu:12.942079866422912 
Step 2313 | loss:2.025953531265259 lr:0.00011461079314864256 tokens_per_second_per_gpu:900.9557552339359 mfu:13.239288120076735 
Step 2314 | loss:2.0984175205230713 lr:0.00011454853306513686 tokens_per_second_per_gpu:859.0840194921522 mfu:12.623994893575006 
Step 2315 | loss:2.0770835876464844 lr:0.00011448626721967717 tokens_per_second_per_gpu:830.9853035121963 mfu:12.21109226822217 
Step 2316 | loss:2.041935920715332 lr:0.000114423995636924 tokens_per_second_per_gpu:889.8725780439495 mfu:13.076423989122832 
Step 2317 | loss:2.034275531768799 lr:0.00011436171834153996 tokens_per_second_per_gpu:869.1689917287149 mfu:12.772190687149976 
Step 2318 | loss:2.0790603160858154 lr:0.00011429943535819005 tokens_per_second_per_gpu:883.4968460535366 mfu:12.982734424116892 
Step 2319 | loss:2.033116579055786 lr:0.00011423714671154146 tokens_per_second_per_gpu:884.908204139121 mfu:13.003473929056065 
Step 2320 | loss:2.079313278198242 lr:0.00011417485242626364 tokens_per_second_per_gpu:880.9211605297505 mfu:12.9448854592171 
Step 2321 | loss:2.0493361949920654 lr:0.00011411255252702829 tokens_per_second_per_gpu:878.6733842065458 mfu:12.911855026590953 
Step 2322 | loss:2.090423583984375 lr:0.00011405024703850929 tokens_per_second_per_gpu:858.7166111765396 mfu:12.618595933060188 
Step 2323 | loss:2.02148175239563 lr:0.00011398793598538275 tokens_per_second_per_gpu:874.4135432406017 mfu:12.8492578773234 
Step 2324 | loss:2.0779545307159424 lr:0.00011392561939232706 tokens_per_second_per_gpu:883.8851942459968 mfu:12.98844109015573 
Step 2325 | loss:2.012808322906494 lr:0.00011386329728402268 tokens_per_second_per_gpu:873.0735871685273 mfu:12.829567604628673 
Step 2326 | loss:2.006453037261963 lr:0.00011380096968515233 tokens_per_second_per_gpu:854.1901898097886 mfu:12.552081460757686 
Step 2327 | loss:2.0625362396240234 lr:0.00011373863662040087 tokens_per_second_per_gpu:880.3720631218596 mfu:12.936816629258665 
Step 2328 | loss:2.0275304317474365 lr:0.00011367629811445539 tokens_per_second_per_gpu:883.9126633449227 mfu:12.988844740737868 
Step 2329 | loss:2.048534393310547 lr:0.00011361395419200504 tokens_per_second_per_gpu:885.6117325099691 mfu:13.01381207801421 
Step 2330 | loss:2.0526251792907715 lr:0.0001135516048777412 tokens_per_second_per_gpu:850.6639050945167 mfu:12.500263711586657 
Step 2331 | loss:1.993671178817749 lr:0.00011348925019635728 tokens_per_second_per_gpu:901.7628574432566 mfu:13.251148257080658 
Step 2332 | loss:1.9875870943069458 lr:0.00011342689017254899 tokens_per_second_per_gpu:833.9301706384435 mfu:12.254366251581772 
Step 2333 | loss:2.0635488033294678 lr:0.00011336452483101394 tokens_per_second_per_gpu:848.5286609199901 mfu:12.468886906822329 
Step 2334 | loss:2.010338306427002 lr:0.00011330215419645203 tokens_per_second_per_gpu:881.9253511192526 mfu:12.95964175381276 
Step 2335 | loss:2.0875165462493896 lr:0.00011323977829356514 tokens_per_second_per_gpu:892.3724860483271 mfu:13.113159424965682 
Step 2336 | loss:2.0057592391967773 lr:0.00011317739714705731 tokens_per_second_per_gpu:876.0837801365683 mfu:12.873801532620593 
Step 2337 | loss:2.0402796268463135 lr:0.0001131150107816346 tokens_per_second_per_gpu:857.7089402598051 mfu:12.603788496047473 
Step 2338 | loss:2.0803632736206055 lr:0.00011305261922200519 tokens_per_second_per_gpu:840.3331174533206 mfu:12.348455730679081 
Step 2339 | loss:2.0902905464172363 lr:0.00011299022249287922 tokens_per_second_per_gpu:883.284689673408 mfu:12.97961684655915 
Step 2340 | loss:1.991560697555542 lr:0.00011292782061896904 tokens_per_second_per_gpu:898.7879949047167 mfu:13.207433499683804 
Step 2341 | loss:2.046769142150879 lr:0.00011286541362498889 tokens_per_second_per_gpu:862.3513122778099 mfu:12.672006830133135 
Step 2342 | loss:1.9836018085479736 lr:0.0001128030015356551 tokens_per_second_per_gpu:849.5354586242752 mfu:12.483681512226898 
Step 2343 | loss:1.9967392683029175 lr:0.00011274058437568602 tokens_per_second_per_gpu:868.9268929034284 mfu:12.768633113891934 
Step 2344 | loss:2.0606813430786133 lr:0.00011267816216980201 tokens_per_second_per_gpu:863.4310742135365 mfu:12.687873624129542 
Step 2345 | loss:2.011715888977051 lr:0.00011261573494272538 tokens_per_second_per_gpu:859.5848342815984 mfu:12.63135422421223 
Step 2346 | loss:1.987174391746521 lr:0.00011255330271918047 tokens_per_second_per_gpu:850.9750828504729 mfu:12.504836380048708 
Step 2347 | loss:2.0356855392456055 lr:0.00011249086552389358 tokens_per_second_per_gpu:854.2483466404682 mfu:12.552936058814298 
Step 2348 | loss:2.04866361618042 lr:0.00011242842338159309 tokens_per_second_per_gpu:870.128310389708 mfu:12.786287601541245 
Step 2349 | loss:2.0580320358276367 lr:0.00011236597631700912 tokens_per_second_per_gpu:877.2790163579781 mfu:12.891365188343826 
Step 2350 | loss:1.9878672361373901 lr:0.00011230352435487392 tokens_per_second_per_gpu:895.8094970058571 mfu:13.163665321702846 
Step 2351 | loss:2.0077481269836426 lr:0.00011224106751992163 tokens_per_second_per_gpu:902.8988362982356 mfu:13.267841142687983 
Step 2352 | loss:2.0076870918273926 lr:0.00011217860583688829 tokens_per_second_per_gpu:832.2941935691936 mfu:12.230326034676763 
Step 2353 | loss:2.0638339519500732 lr:0.0001121161393305119 tokens_per_second_per_gpu:858.6937737243952 mfu:12.618260343207844 
Step 2354 | loss:2.0396924018859863 lr:0.0001120536680255323 tokens_per_second_per_gpu:893.6756163371599 mfu:13.132308553268187 
Step 2355 | loss:2.0075016021728516 lr:0.00011199119194669136 tokens_per_second_per_gpu:848.389083860278 mfu:12.466835861698584 
Step 2356 | loss:2.049177408218384 lr:0.00011192871111873271 tokens_per_second_per_gpu:884.5909469896657 mfu:12.998811925638702 
Step 2357 | loss:2.0353243350982666 lr:0.00011186622556640194 tokens_per_second_per_gpu:825.1176578766069 mfu:12.124868887434832 
Step 2358 | loss:2.0449132919311523 lr:0.00011180373531444648 tokens_per_second_per_gpu:862.1821919396667 mfu:12.669521654950406 
Step 2359 | loss:1.9846328496932983 lr:0.0001117412403876156 tokens_per_second_per_gpu:864.1005459776895 mfu:12.697711320955817 
Step 2360 | loss:2.037872791290283 lr:0.00011167874081066045 tokens_per_second_per_gpu:898.2994558470111 mfu:13.20025455742687 
Step 2361 | loss:2.033698558807373 lr:0.00011161623660833409 tokens_per_second_per_gpu:898.6196354954737 mfu:13.204959506134458 
Step 2362 | loss:1.997497320175171 lr:0.00011155372780539124 tokens_per_second_per_gpu:878.6778041641791 mfu:12.911919976609026 
Step 2363 | loss:2.0346431732177734 lr:0.00011149121442658861 tokens_per_second_per_gpu:846.463517047633 mfu:12.438540206025186 
Step 2364 | loss:2.0328259468078613 lr:0.00011142869649668466 tokens_per_second_per_gpu:879.3079683836532 mfu:12.92118006026587 
Step 2365 | loss:2.077672243118286 lr:0.00011136617404043959 tokens_per_second_per_gpu:896.9749132157249 mfu:13.180790780852881 
Step 2366 | loss:2.062649726867676 lr:0.00011130364708261552 tokens_per_second_per_gpu:860.2355154120025 mfu:12.640915798029447 
Step 2367 | loss:2.0799050331115723 lr:0.00011124111564797621 tokens_per_second_per_gpu:864.2964814988334 mfu:12.700590537612474 
Step 2368 | loss:2.000216007232666 lr:0.00011117857976128732 tokens_per_second_per_gpu:890.1094190534565 mfu:13.079904300276068 
Step 2369 | loss:2.0040271282196045 lr:0.00011111603944731623 tokens_per_second_per_gpu:883.7496689344126 mfu:12.986449584316292 
Step 2370 | loss:2.030457019805908 lr:0.000111053494730832 tokens_per_second_per_gpu:882.9486263768788 mfu:12.974678492168842 
Step 2371 | loss:2.0527091026306152 lr:0.00011099094563660557 tokens_per_second_per_gpu:876.4891155756558 mfu:12.879757821408562 
Step 2372 | loss:2.0442721843719482 lr:0.0001109283921894095 tokens_per_second_per_gpu:817.6332371356825 mfu:12.014887457131135 
Step 2373 | loss:1.987008810043335 lr:0.0001108658344140181 tokens_per_second_per_gpu:853.8160330915599 mfu:12.546583334389199 
Step 2374 | loss:2.003143548965454 lr:0.00011080327233520745 tokens_per_second_per_gpu:898.1044262385971 mfu:13.197388652899662 
Step 2375 | loss:2.0089097023010254 lr:0.00011074070597775527 tokens_per_second_per_gpu:884.5309037748383 mfu:12.997929607704512 
Step 2376 | loss:2.028687000274658 lr:0.00011067813536644098 tokens_per_second_per_gpu:865.6783506563858 mfu:12.720896711156293 
Step 2377 | loss:2.018913984298706 lr:0.00011061556052604578 tokens_per_second_per_gpu:895.6430054254739 mfu:13.16121877536641 
Step 2378 | loss:2.0336904525756836 lr:0.00011055298148135236 tokens_per_second_per_gpu:889.1607070963328 mfu:13.065963248376066 
Step 2379 | loss:2.046396017074585 lr:0.00011049039825714525 tokens_per_second_per_gpu:864.9741278244195 mfu:12.710548357289886 
Step 2380 | loss:2.030252695083618 lr:0.00011042781087821054 tokens_per_second_per_gpu:880.2111825757283 mfu:12.934452535471847 
Step 2381 | loss:2.0562973022460938 lr:0.00011036521936933604 tokens_per_second_per_gpu:866.528371772294 mfu:12.733387529263934 
Step 2382 | loss:2.0315723419189453 lr:0.00011030262375531109 tokens_per_second_per_gpu:881.1315592393247 mfu:12.947977208306845 
Step 2383 | loss:2.0293729305267334 lr:0.00011024002406092676 tokens_per_second_per_gpu:886.2502775574004 mfu:13.023195315549994 
Step 2384 | loss:2.077329158782959 lr:0.00011017742031097563 tokens_per_second_per_gpu:891.2191878537207 mfu:13.096212036597208 
Step 2385 | loss:1.9680285453796387 lr:0.00011011481253025202 tokens_per_second_per_gpu:867.3639715031262 mfu:12.745666429226867 
Step 2386 | loss:2.022320508956909 lr:0.00011005220074355171 tokens_per_second_per_gpu:879.0840451172071 mfu:12.917889571666349 
Step 2387 | loss:2.0410094261169434 lr:0.0001099895849756722 tokens_per_second_per_gpu:847.2315006241909 mfu:12.44982550586646 
Step 2388 | loss:2.045311450958252 lr:0.00010992696525141244 tokens_per_second_per_gpu:831.7926830657324 mfu:12.222956480720315 
Step 2389 | loss:2.024912118911743 lr:0.00010986434159557301 tokens_per_second_per_gpu:892.3134135602564 mfu:13.112291371584599 
Step 2390 | loss:2.049130916595459 lr:0.0001098017140329561 tokens_per_second_per_gpu:881.8158923527914 mfu:12.958033288426941 
Step 2391 | loss:2.0139193534851074 lr:0.00010973908258836527 tokens_per_second_per_gpu:884.3516335776964 mfu:12.995295283235727 
Step 2392 | loss:2.0423731803894043 lr:0.00010967644728660585 tokens_per_second_per_gpu:871.5036703151595 mfu:12.806498123773972 
Step 2393 | loss:2.037014961242676 lr:0.00010961380815248454 tokens_per_second_per_gpu:861.5608148283673 mfu:12.66039069534454 
Step 2394 | loss:2.037003517150879 lr:0.00010955116521080959 tokens_per_second_per_gpu:899.2493962659328 mfu:13.214213661222978 
Step 2395 | loss:2.0205891132354736 lr:0.00010948851848639076 tokens_per_second_per_gpu:859.0321485724837 mfu:12.623232665189702 
Step 2396 | loss:2.0369977951049805 lr:0.0001094258680040394 tokens_per_second_per_gpu:871.9451885218547 mfu:12.812986108022633 
Step 2397 | loss:2.035808801651001 lr:0.00010936321378856814 tokens_per_second_per_gpu:854.9494809340212 mfu:12.56323902748872 
Step 2398 | loss:2.0903546810150146 lr:0.0001093005558647913 tokens_per_second_per_gpu:847.3439030350823 mfu:12.45147722726847 
Step 2399 | loss:1.976881980895996 lr:0.00010923789425752456 tokens_per_second_per_gpu:881.3384535234529 mfu:12.951017460863152 
Step 2400 | loss:1.9650205373764038 lr:0.00010917522899158508 tokens_per_second_per_gpu:885.7995140385895 mfu:13.016571474073995 
Step 2401 | loss:2.032923698425293 lr:0.00010911256009179148 tokens_per_second_per_gpu:853.6659631389663 mfu:12.544378099194228 
Step 2402 | loss:2.0364766120910645 lr:0.0001090498875829638 tokens_per_second_per_gpu:878.6107056102187 mfu:12.910933982476504 
Step 2403 | loss:2.085369825363159 lr:0.00010898721148992351 tokens_per_second_per_gpu:888.2045194051364 mfu:13.051912342693873 
Step 2404 | loss:1.9694693088531494 lr:0.00010892453183749354 tokens_per_second_per_gpu:862.2148198238472 mfu:12.670001112412002 
Step 2405 | loss:2.031064510345459 lr:0.00010886184865049813 tokens_per_second_per_gpu:894.312458144484 mfu:13.141666762175888 
Step 2406 | loss:2.021639823913574 lr:0.00010879916195376308 tokens_per_second_per_gpu:865.3662053131682 mfu:12.716309824275124 
Step 2407 | loss:2.0346391201019287 lr:0.00010873647177211543 tokens_per_second_per_gpu:865.7522472315782 mfu:12.721982600273908 
Step 2408 | loss:1.996962547302246 lr:0.00010867377813038366 tokens_per_second_per_gpu:862.6673011190328 mfu:12.676650196122392 
Step 2409 | loss:2.009744167327881 lr:0.00010861108105339766 tokens_per_second_per_gpu:850.9728306350344 mfu:12.504803284384549 
Step 2410 | loss:2.0110490322113037 lr:0.0001085483805659886 tokens_per_second_per_gpu:874.9687881999108 mfu:12.857417043798344 
Step 2411 | loss:1.9985487461090088 lr:0.00010848567669298901 tokens_per_second_per_gpu:859.9393122601615 mfu:12.636563177108256 
Step 2412 | loss:2.0816686153411865 lr:0.00010842296945923292 tokens_per_second_per_gpu:882.6700476812164 mfu:12.970584857609582 
Step 2413 | loss:2.0174059867858887 lr:0.00010836025888955538 tokens_per_second_per_gpu:857.951870795256 mfu:12.607358291049408 
Step 2414 | loss:2.0716636180877686 lr:0.00010829754500879308 tokens_per_second_per_gpu:881.5175949702449 mfu:12.953649893382227 
Step 2415 | loss:2.0353856086730957 lr:0.00010823482784178385 tokens_per_second_per_gpu:873.2858110783112 mfu:12.832686174515459 
Step 2416 | loss:2.0400309562683105 lr:0.00010817210741336684 tokens_per_second_per_gpu:889.586165598626 mfu:13.072215239844319 
Step 2417 | loss:2.0469770431518555 lr:0.00010810938374838251 tokens_per_second_per_gpu:865.5256631896383 mfu:12.718653012336624 
Step 2418 | loss:2.052426815032959 lr:0.00010804665687167262 tokens_per_second_per_gpu:871.6398851428797 mfu:12.808499761856574 
Step 2419 | loss:2.033792734146118 lr:0.00010798392680808011 tokens_per_second_per_gpu:894.6419354390889 mfu:13.146508337144422 
Step 2420 | loss:2.1012487411499023 lr:0.00010792119358244939 tokens_per_second_per_gpu:889.3450271840101 mfu:13.068671779547437 
Step 2421 | loss:2.0276150703430176 lr:0.00010785845721962584 tokens_per_second_per_gpu:885.6152486930039 mfu:13.013863747322064 
Step 2422 | loss:2.021730899810791 lr:0.00010779571774445634 tokens_per_second_per_gpu:891.1037922611433 mfu:13.094516331243153 
Step 2423 | loss:2.038378953933716 lr:0.00010773297518178881 tokens_per_second_per_gpu:885.4137827771877 mfu:13.010903263091434 
Step 2424 | loss:1.9851179122924805 lr:0.00010767022955647255 tokens_per_second_per_gpu:892.1722907280657 mfu:13.110217611774706 
Step 2425 | loss:2.004812002182007 lr:0.00010760748089335793 tokens_per_second_per_gpu:892.768181846955 mfu:13.118974061983653 
Step 2426 | loss:2.0162806510925293 lr:0.00010754472921729661 tokens_per_second_per_gpu:888.4595648133069 mfu:13.055660162298617 
Step 2427 | loss:2.0126888751983643 lr:0.00010748197455314142 tokens_per_second_per_gpu:862.4976412235768 mfu:12.674157092298683 
Step 2428 | loss:2.035048484802246 lr:0.00010741921692574643 tokens_per_second_per_gpu:881.4531357749742 mfu:12.952702683873635 
Step 2429 | loss:2.057490825653076 lr:0.00010735645635996676 tokens_per_second_per_gpu:885.0068026584598 mfu:13.004922806204757 
Step 2430 | loss:1.9988335371017456 lr:0.00010729369288065878 tokens_per_second_per_gpu:878.4169242968916 mfu:12.90808642128993 
Step 2431 | loss:2.0074052810668945 lr:0.00010723092651268003 tokens_per_second_per_gpu:865.7538976679426 mfu:12.722006852966036 
Step 2432 | loss:2.016679525375366 lr:0.00010716815728088912 tokens_per_second_per_gpu:872.7487877897436 mfu:12.824794770300283 
Step 2433 | loss:2.039315700531006 lr:0.0001071053852101459 tokens_per_second_per_gpu:857.2647138336391 mfu:12.597260715285323 
Step 2434 | loss:2.040379524230957 lr:0.0001070426103253112 tokens_per_second_per_gpu:881.982418450574 mfu:12.960480341986727 
Step 2435 | loss:1.98529052734375 lr:0.0001069798326512471 tokens_per_second_per_gpu:842.868106862846 mfu:12.385706677775076 
Step 2436 | loss:2.0395188331604004 lr:0.00010691705221281669 tokens_per_second_per_gpu:885.7122253739785 mfu:13.015288792018094 
Step 2437 | loss:2.062368631362915 lr:0.00010685426903488425 tokens_per_second_per_gpu:854.3543599679731 mfu:12.55449389445634 
Step 2438 | loss:2.033402919769287 lr:0.00010679148314231504 tokens_per_second_per_gpu:882.9434281351976 mfu:12.974602105488435 
Step 2439 | loss:1.996868371963501 lr:0.00010672869455997548 tokens_per_second_per_gpu:869.2687478482044 mfu:12.773656574903052 
Step 2440 | loss:2.0397865772247314 lr:0.00010666590331273296 tokens_per_second_per_gpu:881.6336018364677 mfu:12.95535458122834 
Step 2441 | loss:1.9845607280731201 lr:0.00010660310942545608 tokens_per_second_per_gpu:862.2062524004576 mfu:12.66987521656635 
Step 2442 | loss:2.019914150238037 lr:0.00010654031292301432 tokens_per_second_per_gpu:875.3383381707164 mfu:12.862847475326017 
Step 2443 | loss:1.999145746231079 lr:0.00010647751383027828 tokens_per_second_per_gpu:856.8978050527328 mfu:12.591869095290685 
Step 2444 | loss:1.964357852935791 lr:0.00010641471217211958 tokens_per_second_per_gpu:858.7011559559226 mfu:12.61836882299677 
Step 2445 | loss:2.0763165950775146 lr:0.00010635190797341085 tokens_per_second_per_gpu:845.4139528691842 mfu:12.423117159467935 
Step 2446 | loss:2.040987014770508 lr:0.00010628910125902574 tokens_per_second_per_gpu:893.9431198459141 mfu:13.136239441111407 
Step 2447 | loss:2.058706283569336 lr:0.00010622629205383885 tokens_per_second_per_gpu:868.4966679000954 mfu:12.762311080048987 
Step 2448 | loss:2.0253524780273438 lr:0.00010616348038272579 tokens_per_second_per_gpu:859.957143903133 mfu:12.636825208021078 
Step 2449 | loss:1.975833535194397 lr:0.00010610066627056321 tokens_per_second_per_gpu:898.5776486473438 mfu:13.204342521364211 
Step 2450 | loss:1.9470080137252808 lr:0.00010603784974222861 tokens_per_second_per_gpu:881.6356450341272 mfu:12.95538460543579 
Step 2451 | loss:2.0357325077056885 lr:0.00010597503082260056 tokens_per_second_per_gpu:883.7740970426479 mfu:12.986808548406676 
Step 2452 | loss:2.026700496673584 lr:0.0001059122095365585 tokens_per_second_per_gpu:860.2323869938151 mfu:12.64086982681554 
Step 2453 | loss:2.0832841396331787 lr:0.00010584938590898281 tokens_per_second_per_gpu:883.5768205921265 mfu:12.983909627174878 
Step 2454 | loss:2.0382142066955566 lr:0.00010578655996475486 tokens_per_second_per_gpu:870.4382079983575 mfu:12.790841458603369 
Step 2455 | loss:2.0120887756347656 lr:0.0001057237317287569 tokens_per_second_per_gpu:901.5097183053255 mfu:13.247428449573942 
Step 2456 | loss:2.0102365016937256 lr:0.000105660901225872 tokens_per_second_per_gpu:874.2646271544584 mfu:12.847069597867153 
Step 2457 | loss:1.9726378917694092 lr:0.00010559806848098435 tokens_per_second_per_gpu:842.0626289942645 mfu:12.3738704099955 
Step 2458 | loss:2.0041990280151367 lr:0.00010553523351897878 tokens_per_second_per_gpu:862.1885518526083 mfu:12.669615112058997 
Step 2459 | loss:2.0160348415374756 lr:0.00010547239636474115 tokens_per_second_per_gpu:829.9630702142039 mfu:12.196070841166028 
Step 2460 | loss:2.0548415184020996 lr:0.00010540955704315816 tokens_per_second_per_gpu:890.8861143114868 mfu:13.091317615794422 
Step 2461 | loss:2.0217790603637695 lr:0.00010534671557911733 tokens_per_second_per_gpu:890.9639375594174 mfu:13.092461206249121 
Step 2462 | loss:1.998161792755127 lr:0.00010528387199750707 tokens_per_second_per_gpu:871.7585490934175 mfu:12.810243494799629 
Step 2463 | loss:2.0121617317199707 lr:0.0001052210263232166 tokens_per_second_per_gpu:822.6612036824665 mfu:12.088771992952426 
Step 2464 | loss:2.0131566524505615 lr:0.00010515817858113597 tokens_per_second_per_gpu:885.7063014478592 mfu:13.015201741611634 
Step 2465 | loss:2.0160956382751465 lr:0.00010509532879615614 tokens_per_second_per_gpu:872.5286900573125 mfu:12.821560496833131 
Step 2466 | loss:2.029285192489624 lr:0.00010503247699316867 tokens_per_second_per_gpu:896.4073611438326 mfu:13.172450764865108 
Step 2467 | loss:2.054579019546509 lr:0.00010496962319706614 tokens_per_second_per_gpu:881.4498946926711 mfu:12.952655057092652 
Step 2468 | loss:2.013270378112793 lr:0.00010490676743274181 tokens_per_second_per_gpu:872.2305809069608 mfu:12.817179867806889 
Step 2469 | loss:2.081737995147705 lr:0.00010484390972508973 tokens_per_second_per_gpu:908.7258654981915 mfu:13.353467676526247 
Step 2470 | loss:2.0209741592407227 lr:0.00010478105009900472 tokens_per_second_per_gpu:858.3785038992376 mfu:12.6136275429548 
Step 2471 | loss:2.056550979614258 lr:0.00010471818857938238 tokens_per_second_per_gpu:879.2639788778172 mfu:12.920533647011235 
Step 2472 | loss:2.0437798500061035 lr:0.00010465532519111908 tokens_per_second_per_gpu:836.5678090095411 mfu:12.293125595921008 
Step 2473 | loss:2.030498504638672 lr:0.00010459245995911182 tokens_per_second_per_gpu:880.4109545768928 mfu:12.937388128109305 
Step 2474 | loss:2.0916967391967773 lr:0.00010452959290825846 tokens_per_second_per_gpu:891.6005566581636 mfu:13.101816142517725 
Step 2475 | loss:2.0498430728912354 lr:0.00010446672406345748 tokens_per_second_per_gpu:890.6641079826425 mfu:13.088055296046779 
Step 2476 | loss:2.008594274520874 lr:0.00010440385344960821 tokens_per_second_per_gpu:888.5489989762822 mfu:13.056974371841681 
Step 2477 | loss:2.018292188644409 lr:0.00010434098109161051 tokens_per_second_per_gpu:890.3226902511838 mfu:13.083038259760785 
Step 2478 | loss:2.0658669471740723 lr:0.00010427810701436503 tokens_per_second_per_gpu:874.4376854824847 mfu:12.849612640689188 
Step 2479 | loss:2.038997173309326 lr:0.00010421523124277306 tokens_per_second_per_gpu:904.9280368091139 mfu:13.297659666029286 
Step 2480 | loss:2.0609898567199707 lr:0.00010415235380173662 tokens_per_second_per_gpu:862.2789841832312 mfu:12.670943989391242 
Step 2481 | loss:1.9935557842254639 lr:0.00010408947471615835 tokens_per_second_per_gpu:820.1607213175748 mfu:12.052028117045472 
Step 2482 | loss:2.0651230812072754 lr:0.00010402659401094152 tokens_per_second_per_gpu:890.8698855478042 mfu:13.091079138736054 
Step 2483 | loss:1.9907902479171753 lr:0.00010396371171099006 tokens_per_second_per_gpu:860.2481797293764 mfu:12.641101896564901 
Step 2484 | loss:2.061901092529297 lr:0.0001039008278412086 tokens_per_second_per_gpu:855.7164301083359 mfu:12.574509127083756 
Step 2485 | loss:2.022019863128662 lr:0.00010383794242650222 tokens_per_second_per_gpu:891.5500988663282 mfu:13.101074679643293 
Step 2486 | loss:1.9613769054412842 lr:0.00010377505549177682 tokens_per_second_per_gpu:892.3416714413777 mfu:13.112706613096352 
Step 2487 | loss:2.028207302093506 lr:0.00010371216706193876 tokens_per_second_per_gpu:849.6612965630662 mfu:12.4855306648833 
Step 2488 | loss:2.0495989322662354 lr:0.00010364927716189503 tokens_per_second_per_gpu:849.0614633242734 mfu:12.476716286345571 
Step 2489 | loss:2.0029406547546387 lr:0.00010358638581655322 tokens_per_second_per_gpu:810.1722701063014 mfu:11.905250672436063 
Step 2490 | loss:2.0153415203094482 lr:0.00010352349305082148 tokens_per_second_per_gpu:851.0095389342005 mfu:12.505342702381752 
Step 2491 | loss:2.003258228302002 lr:0.00010346059888960851 tokens_per_second_per_gpu:849.3878667051298 mfu:12.4815126910274 
Step 2492 | loss:2.0261030197143555 lr:0.00010339770335782359 tokens_per_second_per_gpu:879.7770268582644 mfu:12.928072740904698 
Step 2493 | loss:2.044558048248291 lr:0.0001033348064803765 tokens_per_second_per_gpu:847.1004865364789 mfu:12.447900291176472 
Step 2494 | loss:2.0205509662628174 lr:0.00010327190828217763 tokens_per_second_per_gpu:876.2296301058739 mfu:12.875944756363516 
Step 2495 | loss:1.9964679479599 lr:0.0001032090087881378 tokens_per_second_per_gpu:887.8000757221188 mfu:13.045969158007267 
Step 2496 | loss:2.012577533721924 lr:0.00010314610802316839 tokens_per_second_per_gpu:867.5541546982347 mfu:12.748461117091406 
Step 2497 | loss:2.0225236415863037 lr:0.00010308320601218132 tokens_per_second_per_gpu:878.0182401721345 mfu:12.90222787167093 
Step 2498 | loss:2.0144312381744385 lr:0.0001030203027800889 tokens_per_second_per_gpu:876.5190387734979 mfu:12.880197534275041 
Step 2499 | loss:1.968900442123413 lr:0.00010295739835180403 tokens_per_second_per_gpu:882.7306150582275 mfu:12.971474877957716 
Step 2500 | loss:2.0062947273254395 lr:0.00010289449275224006 tokens_per_second_per_gpu:893.210430748396 mfu:13.12547278358341 
Step 2501 | loss:1.988368034362793 lr:0.00010283158600631072 tokens_per_second_per_gpu:877.2943721129928 mfu:12.891590836788561 
Step 2502 | loss:2.0275983810424805 lr:0.0001027686781389303 tokens_per_second_per_gpu:886.3841229031597 mfu:13.025162134770298 
Step 2503 | loss:2.0159661769866943 lr:0.00010270576917501352 tokens_per_second_per_gpu:861.7311482274447 mfu:12.662893696112066 
Step 2504 | loss:2.030179977416992 lr:0.00010264285913947545 tokens_per_second_per_gpu:880.0737608846933 mfu:12.932433162876698 
Step 2505 | loss:2.020559549331665 lr:0.00010257994805723167 tokens_per_second_per_gpu:881.2872123654287 mfu:12.950264486645773 
Step 2506 | loss:2.000640392303467 lr:0.00010251703595319815 tokens_per_second_per_gpu:872.0582801960402 mfu:12.81464795795236 
Step 2507 | loss:2.013597011566162 lr:0.00010245412285229124 tokens_per_second_per_gpu:889.4789705163892 mfu:13.0706400386532 
Step 2508 | loss:2.0436060428619385 lr:0.00010239120877942774 tokens_per_second_per_gpu:860.6677537496602 mfu:12.647267417246649 
Step 2509 | loss:2.0399386882781982 lr:0.00010232829375952478 tokens_per_second_per_gpu:879.2748300704586 mfu:12.920693102195344 
Step 2510 | loss:2.013664722442627 lr:0.00010226537781749987 tokens_per_second_per_gpu:866.6277845602436 mfu:12.734848371857856 
Step 2511 | loss:2.024193048477173 lr:0.00010220246097827093 tokens_per_second_per_gpu:863.7872894955534 mfu:12.693108106204827 
Step 2512 | loss:2.0297765731811523 lr:0.00010213954326675619 tokens_per_second_per_gpu:858.0120860362196 mfu:12.608243136858656 
Step 2513 | loss:1.9648487567901611 lr:0.00010207662470787427 tokens_per_second_per_gpu:848.8898022747524 mfu:12.474193776133053 
Step 2514 | loss:1.9956074953079224 lr:0.00010201370532654404 tokens_per_second_per_gpu:901.2238366897111 mfu:13.243227500686759 
Step 2515 | loss:2.0444841384887695 lr:0.0001019507851476848 tokens_per_second_per_gpu:845.4536812384193 mfu:12.423700956534317 
Step 2516 | loss:1.9959077835083008 lr:0.00010188786419621612 tokens_per_second_per_gpu:883.5469851144259 mfu:12.983471203330883 
Step 2517 | loss:2.0310158729553223 lr:0.00010182494249705785 tokens_per_second_per_gpu:878.5419193498581 mfu:12.909923187979297 
Step 2518 | loss:2.024324417114258 lr:0.00010176202007513016 tokens_per_second_per_gpu:884.3570900795868 mfu:12.995375464976323 
Step 2519 | loss:2.0484259128570557 lr:0.00010169909695535354 tokens_per_second_per_gpu:889.2367833111432 mfu:13.067081166676834 
Step 2520 | loss:2.0400290489196777 lr:0.00010163617316264869 tokens_per_second_per_gpu:869.9269080827813 mfu:12.783328052025121 
Step 2521 | loss:1.9996904134750366 lr:0.00010157324872193663 tokens_per_second_per_gpu:899.5051566655649 mfu:13.21797198742353 
Step 2522 | loss:2.0284721851348877 lr:0.00010151032365813859 tokens_per_second_per_gpu:859.8222239003262 mfu:12.634842597021654 
Step 2523 | loss:2.035623073577881 lr:0.00010144739799617613 tokens_per_second_per_gpu:849.7635244115743 mfu:12.487032873990051 
Step 2524 | loss:2.0496106147766113 lr:0.00010138447176097092 tokens_per_second_per_gpu:893.9774391629062 mfu:13.13674375369624 
Step 2525 | loss:2.018894672393799 lr:0.000101321544977445 tokens_per_second_per_gpu:888.6594224395154 mfu:13.0585970131717 
Step 2526 | loss:2.0526249408721924 lr:0.0001012586176705205 tokens_per_second_per_gpu:875.8110988038379 mfu:12.869794558129323 
Step 2527 | loss:2.0326809883117676 lr:0.0001011956898651198 tokens_per_second_per_gpu:848.8240383715225 mfu:12.473227394312746 
Step 2528 | loss:2.032337188720703 lr:0.00010113276158616553 tokens_per_second_per_gpu:871.0118580288616 mfu:12.799271082355496 
Step 2529 | loss:2.0160679817199707 lr:0.00010106983285858049 tokens_per_second_per_gpu:856.1601959147661 mfu:12.581030139170128 
Step 2530 | loss:2.0232813358306885 lr:0.00010100690370728755 tokens_per_second_per_gpu:865.5238790006102 mfu:12.718626794187212 
Step 2531 | loss:2.012298107147217 lr:0.00010094397415720991 tokens_per_second_per_gpu:882.1991283226339 mfu:12.963664831811005 
Step 2532 | loss:2.023819923400879 lr:0.00010088104423327083 tokens_per_second_per_gpu:877.1843141049471 mfu:12.889973565718394 
Step 2533 | loss:2.0474541187286377 lr:0.00010081811396039373 tokens_per_second_per_gpu:906.0543047995405 mfu:13.314209853248865 
Step 2534 | loss:1.9783614873886108 lr:0.00010075518336350218 tokens_per_second_per_gpu:862.2228241058941 mfu:12.670118733056077 
Step 2535 | loss:1.9526787996292114 lr:0.00010069225246751985 tokens_per_second_per_gpu:892.8679343428993 mfu:13.120439896489765 
Step 2536 | loss:2.0264976024627686 lr:0.00010062932129737057 tokens_per_second_per_gpu:874.7101200400073 mfu:12.85361598888909 
Step 2537 | loss:2.0561397075653076 lr:0.00010056638987797833 tokens_per_second_per_gpu:878.162799224044 mfu:12.904352125750533 
Step 2538 | loss:2.015793800354004 lr:0.00010050345823426703 tokens_per_second_per_gpu:879.7276992843595 mfu:12.927347886260728 
Step 2539 | loss:2.0654454231262207 lr:0.00010044052639116086 tokens_per_second_per_gpu:873.348391944233 mfu:12.833605782509446 
Step 2540 | loss:2.017390727996826 lr:0.00010037759437358398 tokens_per_second_per_gpu:878.6682082698582 mfu:12.91177896767607 
Step 2541 | loss:2.0412068367004395 lr:0.00010031466220646066 tokens_per_second_per_gpu:893.0138970837056 mfu:13.122584777377762 
Step 2542 | loss:2.0422160625457764 lr:0.00010025172991471523 tokens_per_second_per_gpu:893.0896617039871 mfu:13.12369811688571 
Step 2543 | loss:1.9444698095321655 lr:0.00010018879752327202 tokens_per_second_per_gpu:880.0381034964806 mfu:12.931909187716526 
Step 2544 | loss:2.0189208984375 lr:0.00010012586505705543 tokens_per_second_per_gpu:873.4445904983995 mfu:12.835019392853734 
Step 2545 | loss:2.0318429470062256 lr:0.00010006293254098998 tokens_per_second_per_gpu:865.3036594094284 mfu:12.71539073004044 
Step 2546 | loss:1.99387526512146 lr:0.0001 tokens_per_second_per_gpu:873.1977770521828 mfu:12.831392539584426 
Step 2547 | loss:2.0086560249328613 lr:9.993706745901007e-05 tokens_per_second_per_gpu:879.2743332275772 mfu:12.920685801230764 
Step 2548 | loss:2.0368900299072266 lr:9.987413494294457e-05 tokens_per_second_per_gpu:856.3352871232732 mfu:12.583603054591615 
Step 2549 | loss:1.9930758476257324 lr:9.981120247672801e-05 tokens_per_second_per_gpu:887.780857152434 mfu:13.045686746601564 
Step 2550 | loss:1.9930357933044434 lr:9.97482700852848e-05 tokens_per_second_per_gpu:856.9794025730542 mfu:12.593068147602791 
Step 2551 | loss:2.0059080123901367 lr:9.968533779353937e-05 tokens_per_second_per_gpu:868.3629568908405 mfu:12.760346234865336 
Step 2552 | loss:2.0345208644866943 lr:9.962240562641602e-05 tokens_per_second_per_gpu:877.6168331350076 mfu:12.896329309630481 
Step 2553 | loss:2.05073618888855 lr:9.955947360883917e-05 tokens_per_second_per_gpu:861.2713828339356 mfu:12.656137574652222 
Step 2554 | loss:2.0152652263641357 lr:9.9496541765733e-05 tokens_per_second_per_gpu:868.8675528641847 mfu:12.767761128922595 
Step 2555 | loss:2.0103776454925537 lr:9.943361012202172e-05 tokens_per_second_per_gpu:895.1802691643783 mfu:13.154418997853847 
Step 2556 | loss:2.015549421310425 lr:9.937067870262942e-05 tokens_per_second_per_gpu:821.5872157166058 mfu:12.07299004579806 
Step 2557 | loss:2.0017666816711426 lr:9.930774753248016e-05 tokens_per_second_per_gpu:872.7215237673687 mfu:12.824394133259634 
Step 2558 | loss:2.0634098052978516 lr:9.924481663649785e-05 tokens_per_second_per_gpu:858.7131403834998 mfu:12.618544930745376 
Step 2559 | loss:2.0213143825531006 lr:9.918188603960632e-05 tokens_per_second_per_gpu:871.8823999341523 mfu:12.812063447616264 
Step 2560 | loss:2.0010805130004883 lr:9.911895576672917e-05 tokens_per_second_per_gpu:858.2561116681342 mfu:12.611829023991108 
Step 2561 | loss:1.9531632661819458 lr:9.90560258427901e-05 tokens_per_second_per_gpu:844.016495302563 mfu:12.402581918694347 
Step 2562 | loss:1.9926846027374268 lr:9.899309629271246e-05 tokens_per_second_per_gpu:859.5131538335075 mfu:12.630300900450948 
Step 2563 | loss:2.0013461112976074 lr:9.893016714141955e-05 tokens_per_second_per_gpu:871.914920034709 mfu:12.812541321228217 
Step 2564 | loss:2.013976573944092 lr:9.886723841383448e-05 tokens_per_second_per_gpu:874.8675417454039 mfu:12.855929255996816 
Step 2565 | loss:2.0473737716674805 lr:9.880431013488022e-05 tokens_per_second_per_gpu:905.3443845250763 mfu:13.303777777088282 
Step 2566 | loss:2.04793119430542 lr:9.874138232947954e-05 tokens_per_second_per_gpu:894.3698111015176 mfu:13.142509547538316 
Step 2567 | loss:2.0197103023529053 lr:9.867845502255506e-05 tokens_per_second_per_gpu:870.3702299939623 mfu:12.789842541197284 
Step 2568 | loss:1.981623649597168 lr:9.861552823902907e-05 tokens_per_second_per_gpu:848.070344461705 mfu:12.462152077052762 
Step 2569 | loss:2.0268921852111816 lr:9.855260200382391e-05 tokens_per_second_per_gpu:878.0744002750203 mfu:12.90305312838153 
Step 2570 | loss:2.094653606414795 lr:9.848967634186142e-05 tokens_per_second_per_gpu:892.1065060573321 mfu:13.109250924781847 
Step 2571 | loss:2.0142319202423096 lr:9.84267512780634e-05 tokens_per_second_per_gpu:833.8395718908544 mfu:12.253034928799622 
Step 2572 | loss:2.0138049125671387 lr:9.836382683735132e-05 tokens_per_second_per_gpu:879.5185105345573 mfu:12.924273917185088 
Step 2573 | loss:1.9954652786254883 lr:9.830090304464647e-05 tokens_per_second_per_gpu:868.8184940129003 mfu:12.767040223080969 
Step 2574 | loss:1.9973580837249756 lr:9.823797992486985e-05 tokens_per_second_per_gpu:882.3457229251794 mfu:12.965818997727226 
Step 2575 | loss:1.9873038530349731 lr:9.81750575029422e-05 tokens_per_second_per_gpu:858.4502111559632 mfu:12.614681260661332 
Step 2576 | loss:2.033630132675171 lr:9.81121358037839e-05 tokens_per_second_per_gpu:861.7918822559412 mfu:12.663786165356296 
Step 2577 | loss:1.9407689571380615 lr:9.804921485231522e-05 tokens_per_second_per_gpu:894.5500407066787 mfu:13.145157970234584 
Step 2578 | loss:2.016756534576416 lr:9.798629467345599e-05 tokens_per_second_per_gpu:880.2195161216496 mfu:12.934574994554739 
Step 2579 | loss:2.038347005844116 lr:9.792337529212578e-05 tokens_per_second_per_gpu:903.4192381005564 mfu:13.275488298898606 
Step 2580 | loss:2.0099713802337646 lr:9.786045673324382e-05 tokens_per_second_per_gpu:873.5265884723559 mfu:12.83622432971791 
Step 2581 | loss:2.004154920578003 lr:9.779753902172909e-05 tokens_per_second_per_gpu:873.9619810177311 mfu:12.842622299118812 
Step 2582 | loss:1.9843225479125977 lr:9.773462218250015e-05 tokens_per_second_per_gpu:867.531531250654 mfu:12.748128671975149 
Step 2583 | loss:1.9707014560699463 lr:9.767170624047527e-05 tokens_per_second_per_gpu:903.4697728834163 mfu:13.276230893134207 
Step 2584 | loss:2.0190610885620117 lr:9.760879122057227e-05 tokens_per_second_per_gpu:880.9507960059151 mfu:12.945320944095506 
Step 2585 | loss:2.0609326362609863 lr:9.754587714770878e-05 tokens_per_second_per_gpu:876.9636009914537 mfu:12.886730249401868 
Step 2586 | loss:2.0250067710876465 lr:9.74829640468019e-05 tokens_per_second_per_gpu:858.5316672587948 mfu:12.615878234883718 
Step 2587 | loss:2.0329554080963135 lr:9.742005194276835e-05 tokens_per_second_per_gpu:827.088402358285 mfu:12.15382841608251 
Step 2588 | loss:2.0155460834503174 lr:9.735714086052458e-05 tokens_per_second_per_gpu:825.5236759553941 mfu:12.130835207418691 
Step 2589 | loss:2.0667948722839355 lr:9.729423082498652e-05 tokens_per_second_per_gpu:885.6592163326902 mfu:13.01450983925986 
Step 2590 | loss:1.9870834350585938 lr:9.723132186106973e-05 tokens_per_second_per_gpu:837.9613537203751 mfu:12.313603338393667 
Step 2591 | loss:2.006042957305908 lr:9.71684139936893e-05 tokens_per_second_per_gpu:891.5727611675293 mfu:13.101407695702429 
Step 2592 | loss:1.9925861358642578 lr:9.710550724775998e-05 tokens_per_second_per_gpu:903.6331476151504 mfu:13.278631638267806 
Step 2593 | loss:1.960245132446289 lr:9.704260164819601e-05 tokens_per_second_per_gpu:909.1825690245115 mfu:13.360178804720146 
Step 2594 | loss:2.020284652709961 lr:9.697969721991114e-05 tokens_per_second_per_gpu:873.3988805495293 mfu:12.834347698178906 
Step 2595 | loss:2.014997959136963 lr:9.691679398781871e-05 tokens_per_second_per_gpu:896.5267060361566 mfu:13.174204504053694 
Step 2596 | loss:2.0457143783569336 lr:9.685389197683162e-05 tokens_per_second_per_gpu:872.8650534646752 mfu:12.82650326126663 
Step 2597 | loss:1.9872920513153076 lr:9.679099121186222e-05 tokens_per_second_per_gpu:843.9336142524421 mfu:12.401364005277545 
Step 2598 | loss:2.0454275608062744 lr:9.67280917178224e-05 tokens_per_second_per_gpu:870.5572512735748 mfu:12.792590765614511 
Step 2599 | loss:1.9652156829833984 lr:9.66651935196235e-05 tokens_per_second_per_gpu:870.0478745112684 mfu:12.785105619225615 
Step 2600 | loss:1.991829514503479 lr:9.660229664217642e-05 tokens_per_second_per_gpu:887.9560752274921 mfu:13.04826152629087 
Step 2601 | loss:1.9922410249710083 lr:9.653940111039153e-05 tokens_per_second_per_gpu:870.3398191076199 mfu:12.789395661887244 
Step 2602 | loss:2.032850503921509 lr:9.647650694917856e-05 tokens_per_second_per_gpu:859.4146943798685 mfu:12.62885406683309 
Step 2603 | loss:1.9664092063903809 lr:9.64136141834468e-05 tokens_per_second_per_gpu:886.2388570866199 mfu:13.02302749498583 
Step 2604 | loss:2.042034387588501 lr:9.635072283810499e-05 tokens_per_second_per_gpu:898.9919860763539 mfu:13.210431091829218 
Step 2605 | loss:2.0163142681121826 lr:9.628783293806126e-05 tokens_per_second_per_gpu:878.5657064197075 mfu:12.91027273219325 
Step 2606 | loss:2.043304443359375 lr:9.62249445082232e-05 tokens_per_second_per_gpu:876.343681407457 mfu:12.87762070774443 
Step 2607 | loss:2.028721570968628 lr:9.616205757349777e-05 tokens_per_second_per_gpu:890.6131964293837 mfu:13.087307165277519 
Step 2608 | loss:2.0068581104278564 lr:9.609917215879143e-05 tokens_per_second_per_gpu:867.3551956529418 mfu:12.74553747060885 
Step 2609 | loss:1.9846510887145996 lr:9.603628828900996e-05 tokens_per_second_per_gpu:861.6030802436819 mfu:12.661011773580197 
Step 2610 | loss:1.9814302921295166 lr:9.597340598905852e-05 tokens_per_second_per_gpu:879.0828466763505 mfu:12.917871960919426 
Step 2611 | loss:2.0094528198242188 lr:9.591052528384167e-05 tokens_per_second_per_gpu:842.6676675867752 mfu:12.382761279722988 
Step 2612 | loss:1.9591991901397705 lr:9.584764619826339e-05 tokens_per_second_per_gpu:857.67793947647 mfu:12.603332948369202 
Step 2613 | loss:2.0576820373535156 lr:9.578476875722695e-05 tokens_per_second_per_gpu:883.1765826363004 mfu:12.978028244451043 
Step 2614 | loss:2.0642054080963135 lr:9.572189298563501e-05 tokens_per_second_per_gpu:889.0679485904809 mfu:13.064600188561611 
Step 2615 | loss:1.997131109237671 lr:9.56590189083895e-05 tokens_per_second_per_gpu:891.7797774398209 mfu:13.104449740840042 
Step 2616 | loss:2.0657124519348145 lr:9.55961465503918e-05 tokens_per_second_per_gpu:858.0173216949371 mfu:12.60832007337175 
Step 2617 | loss:2.0165648460388184 lr:9.553327593654253e-05 tokens_per_second_per_gpu:875.9761630909675 mfu:12.872220130798068 
Step 2618 | loss:2.0103352069854736 lr:9.547040709174159e-05 tokens_per_second_per_gpu:882.4255458687551 mfu:12.966991973139672 
Step 2619 | loss:2.0017194747924805 lr:9.540754004088819e-05 tokens_per_second_per_gpu:859.7126179655534 mfu:12.633231969039427 
Step 2620 | loss:2.0267574787139893 lr:9.534467480888096e-05 tokens_per_second_per_gpu:880.2668037786854 mfu:12.935269873201536 
Step 2621 | loss:2.023455858230591 lr:9.528181142061763e-05 tokens_per_second_per_gpu:877.1477367923244 mfu:12.889436072531124 
Step 2622 | loss:2.0366861820220947 lr:9.52189499009953e-05 tokens_per_second_per_gpu:858.8028302739451 mfu:12.619862898130751 
Step 2623 | loss:2.0232760906219482 lr:9.515609027491028e-05 tokens_per_second_per_gpu:882.7474545242713 mfu:12.971722329113279 
Step 2624 | loss:1.9818854331970215 lr:9.509323256725821e-05 tokens_per_second_per_gpu:878.4746039952403 mfu:12.908934008022886 
Step 2625 | loss:2.023759603500366 lr:9.50303768029339e-05 tokens_per_second_per_gpu:890.6196614344943 mfu:13.087402166685589 
Step 2626 | loss:1.9703457355499268 lr:9.496752300683133e-05 tokens_per_second_per_gpu:887.8386669131258 mfu:13.046536244563596 
Step 2627 | loss:2.0390918254852295 lr:9.490467120384389e-05 tokens_per_second_per_gpu:876.49043144321 mfu:12.87977715770735 
Step 2628 | loss:2.014333963394165 lr:9.484182141886403e-05 tokens_per_second_per_gpu:896.1356617820861 mfu:13.16845822015766 
Step 2629 | loss:2.0126538276672363 lr:9.477897367678344e-05 tokens_per_second_per_gpu:878.6928344727804 mfu:12.912140842711441 
Step 2630 | loss:1.9572030305862427 lr:9.471612800249296e-05 tokens_per_second_per_gpu:869.9776208022517 mfu:12.784073260988515 
Step 2631 | loss:2.0323266983032227 lr:9.46532844208827e-05 tokens_per_second_per_gpu:888.7376883357315 mfu:13.059747108216836 
Step 2632 | loss:2.0105037689208984 lr:9.459044295684186e-05 tokens_per_second_per_gpu:874.1867033051537 mfu:12.845924529103923 
Step 2633 | loss:2.038410186767578 lr:9.452760363525887e-05 tokens_per_second_per_gpu:877.8447486184291 mfu:12.89967846272098 
Step 2634 | loss:2.010542869567871 lr:9.446476648102123e-05 tokens_per_second_per_gpu:850.4921455993529 mfu:12.497739754743467 
Step 2635 | loss:2.0159928798675537 lr:9.440193151901567e-05 tokens_per_second_per_gpu:860.1754655350987 mfu:12.640033382197942 
Step 2636 | loss:1.9881260395050049 lr:9.433909877412802e-05 tokens_per_second_per_gpu:897.422269582714 mfu:13.187364555203633 
Step 2637 | loss:2.035766363143921 lr:9.427626827124317e-05 tokens_per_second_per_gpu:901.7719122379402 mfu:13.251281314708613 
Step 2638 | loss:1.9986193180084229 lr:9.421344003524515e-05 tokens_per_second_per_gpu:871.7298458111892 mfu:12.809821708245511 
Step 2639 | loss:2.029460906982422 lr:9.415061409101721e-05 tokens_per_second_per_gpu:883.3572921235431 mfu:12.98068371887777 
Step 2640 | loss:2.034374475479126 lr:9.408779046344154e-05 tokens_per_second_per_gpu:858.8967963232177 mfu:12.621243702451716 
Step 2641 | loss:1.9821679592132568 lr:9.402496917739947e-05 tokens_per_second_per_gpu:880.2444592469147 mfu:12.93494152667364 
Step 2642 | loss:2.035480499267578 lr:9.396215025777139e-05 tokens_per_second_per_gpu:844.3999657892091 mfu:12.408216908236021 
Step 2643 | loss:1.9838600158691406 lr:9.38993337294368e-05 tokens_per_second_per_gpu:886.4409125375512 mfu:13.025996642267003 
Step 2644 | loss:2.034285545349121 lr:9.383651961727423e-05 tokens_per_second_per_gpu:827.869790795496 mfu:12.16531069653173 
Step 2645 | loss:1.9944672584533691 lr:9.37737079461612e-05 tokens_per_second_per_gpu:853.0051043365289 mfu:12.534666967386332 
Step 2646 | loss:2.0709595680236816 lr:9.371089874097428e-05 tokens_per_second_per_gpu:888.136878016239 mfu:13.05091837175662 
Step 2647 | loss:2.001782178878784 lr:9.364809202658916e-05 tokens_per_second_per_gpu:899.9881989376075 mfu:13.225070155981308 
Step 2648 | loss:1.9888241291046143 lr:9.358528782788045e-05 tokens_per_second_per_gpu:900.7215077441633 mfu:13.235845919957043 
Step 2649 | loss:2.0101771354675293 lr:9.352248616972174e-05 tokens_per_second_per_gpu:883.6610308322876 mfu:12.985147072660604 
Step 2650 | loss:1.9909418821334839 lr:9.345968707698569e-05 tokens_per_second_per_gpu:872.7208186182933 mfu:12.824383771294885 
Step 2651 | loss:2.025108814239502 lr:9.339689057454393e-05 tokens_per_second_per_gpu:841.0377127615393 mfu:12.35880955797789 
Step 2652 | loss:2.0118720531463623 lr:9.333409668726705e-05 tokens_per_second_per_gpu:903.3896777220323 mfu:13.275053917558626 
Step 2653 | loss:2.0566492080688477 lr:9.327130544002457e-05 tokens_per_second_per_gpu:872.2477382528076 mfu:12.817431990115585 
Step 2654 | loss:2.047255516052246 lr:9.320851685768497e-05 tokens_per_second_per_gpu:876.7585552064031 mfu:12.883717160012825 
Step 2655 | loss:2.046027183532715 lr:9.314573096511578e-05 tokens_per_second_per_gpu:857.4534809107273 mfu:12.60003459369904 
Step 2656 | loss:1.9833712577819824 lr:9.308294778718332e-05 tokens_per_second_per_gpu:857.2675361380471 mfu:12.59730218824446 
Step 2657 | loss:2.0447216033935547 lr:9.302016734875292e-05 tokens_per_second_per_gpu:867.7826785818899 mfu:12.75181921044999 
Step 2658 | loss:2.002504348754883 lr:9.295738967468881e-05 tokens_per_second_per_gpu:896.6009105031396 mfu:13.175294917553444 
Step 2659 | loss:2.0173044204711914 lr:9.289461478985413e-05 tokens_per_second_per_gpu:858.5454944015025 mfu:12.616081420806136 
Step 2660 | loss:2.0596938133239746 lr:9.283184271911089e-05 tokens_per_second_per_gpu:848.1457194206844 mfu:12.463259690598901 
Step 2661 | loss:1.960008144378662 lr:9.276907348732001e-05 tokens_per_second_per_gpu:864.0023909362985 mfu:12.696268960589213 
Step 2662 | loss:2.0256717205047607 lr:9.270630711934123e-05 tokens_per_second_per_gpu:851.5920797641412 mfu:12.513902973898405 
Step 2663 | loss:2.0148472785949707 lr:9.264354364003327e-05 tokens_per_second_per_gpu:877.6534151568072 mfu:12.896866872017764 
Step 2664 | loss:2.0079236030578613 lr:9.25807830742536e-05 tokens_per_second_per_gpu:882.468795538492 mfu:12.967627514713627 
Step 2665 | loss:2.0628299713134766 lr:9.251802544685857e-05 tokens_per_second_per_gpu:884.7247761114749 mfu:13.000778506452683 
Step 2666 | loss:1.988375186920166 lr:9.245527078270341e-05 tokens_per_second_per_gpu:888.9382446761906 mfu:13.062694226496752 
Step 2667 | loss:2.0248756408691406 lr:9.239251910664209e-05 tokens_per_second_per_gpu:857.4103898002072 mfu:12.599401382107597 
Step 2668 | loss:2.025256633758545 lr:9.232977044352751e-05 tokens_per_second_per_gpu:899.2976993991464 mfu:13.214923462002874 
Step 2669 | loss:2.015669584274292 lr:9.226702481821118e-05 tokens_per_second_per_gpu:891.3669666900305 mfu:13.09838360449118 
Step 2670 | loss:2.0052642822265625 lr:9.22042822555437e-05 tokens_per_second_per_gpu:900.2693385126616 mfu:13.229201421933574 
Step 2671 | loss:2.015718460083008 lr:9.214154278037418e-05 tokens_per_second_per_gpu:824.1867415451009 mfu:12.111189337182898 
Step 2672 | loss:1.9730442762374878 lr:9.207880641755065e-05 tokens_per_second_per_gpu:862.8353609236283 mfu:12.679119787066805 
Step 2673 | loss:2.0299344062805176 lr:9.201607319191989e-05 tokens_per_second_per_gpu:852.3858128857935 mfu:12.525566655968202 
Step 2674 | loss:2.0325400829315186 lr:9.195334312832742e-05 tokens_per_second_per_gpu:858.9489467937514 mfu:12.622010038757336 
Step 2675 | loss:1.9939838647842407 lr:9.189061625161751e-05 tokens_per_second_per_gpu:899.8038164461929 mfu:13.222360707804794 
Step 2676 | loss:2.061368465423584 lr:9.182789258663321e-05 tokens_per_second_per_gpu:884.8597154103765 mfu:13.002761401002722 
Step 2677 | loss:1.9965829849243164 lr:9.176517215821615e-05 tokens_per_second_per_gpu:896.3774424068918 mfu:13.1720111175503 
Step 2678 | loss:2.0186893939971924 lr:9.170245499120693e-05 tokens_per_second_per_gpu:871.0782382896796 mfu:12.800246521374946 
Step 2679 | loss:2.021446704864502 lr:9.163974111044463e-05 tokens_per_second_per_gpu:893.8315302614269 mfu:13.134599663961815 
Step 2680 | loss:2.060753345489502 lr:9.157703054076713e-05 tokens_per_second_per_gpu:874.4714003451946 mfu:12.850108070990567 
Step 2681 | loss:2.025651693344116 lr:9.151432330701097e-05 tokens_per_second_per_gpu:858.6448054696307 mfu:12.617540768656264 
Step 2682 | loss:2.0455591678619385 lr:9.145161943401142e-05 tokens_per_second_per_gpu:861.6483516005003 mfu:12.661677023269789 
Step 2683 | loss:1.948193907737732 lr:9.138891894660237e-05 tokens_per_second_per_gpu:856.653927063425 mfu:12.588285377724274 
Step 2684 | loss:2.012686014175415 lr:9.132622186961637e-05 tokens_per_second_per_gpu:853.7248225060436 mfu:12.545243020823035 
Step 2685 | loss:2.0117268562316895 lr:9.126352822788458e-05 tokens_per_second_per_gpu:878.0271698600545 mfu:12.902359090890643 
Step 2686 | loss:2.0342090129852295 lr:9.120083804623695e-05 tokens_per_second_per_gpu:886.5118639196263 mfu:13.027039252610912 
Step 2687 | loss:1.9802016019821167 lr:9.11381513495019e-05 tokens_per_second_per_gpu:901.9036047395315 mfu:13.253216498497265 
Step 2688 | loss:1.9933686256408691 lr:9.107546816250651e-05 tokens_per_second_per_gpu:867.8545965208706 mfu:12.752876024072231 
Step 2689 | loss:1.999240756034851 lr:9.10127885100765e-05 tokens_per_second_per_gpu:888.4460257409377 mfu:13.055461209487746 
Step 2690 | loss:2.020855665206909 lr:9.095011241703623e-05 tokens_per_second_per_gpu:891.3198352821565 mfu:13.0976910218813 
Step 2691 | loss:2.058182716369629 lr:9.088743990820853e-05 tokens_per_second_per_gpu:855.8362792446934 mfu:12.576270275994744 
Step 2692 | loss:1.9864654541015625 lr:9.082477100841496e-05 tokens_per_second_per_gpu:876.7985510615183 mfu:12.884304887708002 
Step 2693 | loss:2.017728328704834 lr:9.076210574247543e-05 tokens_per_second_per_gpu:881.1968545609442 mfu:12.9489367044539 
Step 2694 | loss:1.9998321533203125 lr:9.069944413520872e-05 tokens_per_second_per_gpu:891.6520819789184 mfu:13.102573292425465 
Step 2695 | loss:2.047870635986328 lr:9.063678621143189e-05 tokens_per_second_per_gpu:874.0878083394048 mfu:12.8444712957597 
Step 2696 | loss:2.0365540981292725 lr:9.057413199596065e-05 tokens_per_second_per_gpu:865.1727325960684 mfu:12.713466797822184 
Step 2697 | loss:2.055920124053955 lr:9.051148151360923e-05 tokens_per_second_per_gpu:859.7635248552142 mfu:12.633980031278444 
Step 2698 | loss:1.9810442924499512 lr:9.044883478919042e-05 tokens_per_second_per_gpu:874.2178624296334 mfu:12.846382403560199 
Step 2699 | loss:1.9936774969100952 lr:9.038619184751549e-05 tokens_per_second_per_gpu:903.4612708128448 mfu:13.276105957629593 
Step 2700 | loss:1.9978216886520386 lr:9.03235527133942e-05 tokens_per_second_per_gpu:894.3921218081513 mfu:13.142837397015462 
Step 2701 | loss:1.9915145635604858 lr:9.026091741163473e-05 tokens_per_second_per_gpu:885.9494133725315 mfu:13.018774202076493 
Step 2702 | loss:2.0428619384765625 lr:9.019828596704394e-05 tokens_per_second_per_gpu:871.1111584909044 mfu:12.800730274352219 
Step 2703 | loss:2.020444393157959 lr:9.013565840442701e-05 tokens_per_second_per_gpu:883.6942059085391 mfu:12.985634570953776 
Step 2704 | loss:1.9873981475830078 lr:9.007303474858756e-05 tokens_per_second_per_gpu:864.6443185350256 mfu:12.705701903752521 
Step 2705 | loss:2.0603253841400146 lr:9.001041502432783e-05 tokens_per_second_per_gpu:863.5508053790487 mfu:12.689633039492572 
Step 2706 | loss:2.074781656265259 lr:8.994779925644831e-05 tokens_per_second_per_gpu:884.4683443677139 mfu:12.997010315041438 
Step 2707 | loss:1.9934184551239014 lr:8.988518746974803e-05 tokens_per_second_per_gpu:879.4513387633352 mfu:12.923286847145766 
Step 2708 | loss:2.0040531158447266 lr:8.982257968902438e-05 tokens_per_second_per_gpu:894.7789580685061 mfu:13.148521845642797 
Step 2709 | loss:2.008322238922119 lr:8.975997593907328e-05 tokens_per_second_per_gpu:889.0426416083469 mfu:13.064228309669696 
Step 2710 | loss:2.051732301712036 lr:8.969737624468893e-05 tokens_per_second_per_gpu:862.7566763009295 mfu:12.67796353895531 
Step 2711 | loss:2.070323944091797 lr:8.963478063066402e-05 tokens_per_second_per_gpu:892.5842764623319 mfu:13.116271624755505 
Step 2712 | loss:1.9772658348083496 lr:8.957218912178945e-05 tokens_per_second_per_gpu:908.42226942901 mfu:13.34900641879115 
Step 2713 | loss:2.0644423961639404 lr:8.950960174285478e-05 tokens_per_second_per_gpu:885.7533468494739 mfu:13.01589306038404 
Step 2714 | loss:1.99376380443573 lr:8.944701851864767e-05 tokens_per_second_per_gpu:881.7605561886468 mfu:12.957220139261386 
Step 2715 | loss:2.017296314239502 lr:8.938443947395427e-05 tokens_per_second_per_gpu:842.1056085754717 mfu:12.374501982695469 
Step 2716 | loss:2.003901958465576 lr:8.932186463355901e-05 tokens_per_second_per_gpu:864.6409747459726 mfu:12.705652767725109 
Step 2717 | loss:1.996810793876648 lr:8.925929402224475e-05 tokens_per_second_per_gpu:862.6551692886825 mfu:12.676471922332032 
Step 2718 | loss:1.9757702350616455 lr:8.919672766479256e-05 tokens_per_second_per_gpu:862.398923214086 mfu:12.672706459276256 
Step 2719 | loss:2.035421848297119 lr:8.913416558598194e-05 tokens_per_second_per_gpu:889.4384142500766 mfu:13.070044075875154 
Step 2720 | loss:2.038548707962036 lr:8.907160781059052e-05 tokens_per_second_per_gpu:881.2095323228833 mfu:12.949123000553406 
Step 2721 | loss:2.015601396560669 lr:8.900905436339446e-05 tokens_per_second_per_gpu:897.6039057876301 mfu:13.19003364748253 
Step 2722 | loss:2.0003395080566406 lr:8.894650526916803e-05 tokens_per_second_per_gpu:894.1151234911262 mfu:13.13876698566999 
Step 2723 | loss:2.0270605087280273 lr:8.88839605526838e-05 tokens_per_second_per_gpu:870.7751009883248 mfu:12.795792005102351 
Step 2724 | loss:1.999025821685791 lr:8.882142023871268e-05 tokens_per_second_per_gpu:875.3245127363904 mfu:12.862644314507783 
Step 2725 | loss:2.028036117553711 lr:8.875888435202381e-05 tokens_per_second_per_gpu:837.5913634497122 mfu:12.308166436785042 
Step 2726 | loss:2.066065788269043 lr:8.869635291738452e-05 tokens_per_second_per_gpu:837.4544564406973 mfu:12.306154627295536 
Step 2727 | loss:1.9851888418197632 lr:8.863382595956045e-05 tokens_per_second_per_gpu:892.2369963490014 mfu:13.111168442438231 
Step 2728 | loss:2.027454137802124 lr:8.857130350331535e-05 tokens_per_second_per_gpu:900.8327745934388 mfu:13.237480954604653 
Step 2729 | loss:2.0195212364196777 lr:8.85087855734114e-05 tokens_per_second_per_gpu:846.8411469958517 mfu:12.444089370518773 
Step 2730 | loss:2.0422792434692383 lr:8.844627219460878e-05 tokens_per_second_per_gpu:900.6924418383625 mfu:13.235418804752847 
Step 2731 | loss:2.009551525115967 lr:8.838376339166596e-05 tokens_per_second_per_gpu:879.5944494888305 mfu:12.925389818481372 
Step 2732 | loss:2.0318169593811035 lr:8.832125918933954e-05 tokens_per_second_per_gpu:868.9381675112681 mfu:12.768798791041743 
Step 2733 | loss:2.0292084217071533 lr:8.825875961238442e-05 tokens_per_second_per_gpu:865.0210391338309 mfu:12.711237705615572 
Step 2734 | loss:2.0491299629211426 lr:8.819626468555355e-05 tokens_per_second_per_gpu:880.6245632426012 mfu:12.940527046589851 
Step 2735 | loss:2.0035743713378906 lr:8.81337744335981e-05 tokens_per_second_per_gpu:873.5058508065131 mfu:12.835919595626986 
Step 2736 | loss:2.0309805870056152 lr:8.807128888126727e-05 tokens_per_second_per_gpu:884.9707474590127 mfu:13.00439298532184 
Step 2737 | loss:2.0150082111358643 lr:8.800880805330866e-05 tokens_per_second_per_gpu:890.9999776352614 mfu:13.092990804895 
Step 2738 | loss:1.9983868598937988 lr:8.79463319744677e-05 tokens_per_second_per_gpu:862.6464472905282 mfu:12.676343755054253 
Step 2739 | loss:2.0355498790740967 lr:8.788386066948815e-05 tokens_per_second_per_gpu:890.4203042435726 mfu:13.084472669566459 
Step 2740 | loss:2.0276668071746826 lr:8.782139416311172e-05 tokens_per_second_per_gpu:883.3105982573313 mfu:12.97999756581795 
Step 2741 | loss:1.9785761833190918 lr:8.775893248007839e-05 tokens_per_second_per_gpu:880.4515383434833 mfu:12.937984494996101 
Step 2742 | loss:2.0474514961242676 lr:8.769647564512609e-05 tokens_per_second_per_gpu:880.1783577157005 mfu:12.933970183506297 
Step 2743 | loss:2.0449979305267334 lr:8.763402368299088e-05 tokens_per_second_per_gpu:870.7256589261227 mfu:12.795065468085475 
Step 2744 | loss:2.0325005054473877 lr:8.757157661840693e-05 tokens_per_second_per_gpu:872.7175279483356 mfu:12.824335415837444 
Step 2745 | loss:2.0310275554656982 lr:8.750913447610643e-05 tokens_per_second_per_gpu:907.1232705936594 mfu:13.329918001020419 
Step 2746 | loss:2.038130283355713 lr:8.744669728081958e-05 tokens_per_second_per_gpu:868.1428459388221 mfu:12.757111767140117 
Step 2747 | loss:2.042673110961914 lr:8.738426505727466e-05 tokens_per_second_per_gpu:878.8841287179885 mfu:12.914951857140627 
Step 2748 | loss:1.9413034915924072 lr:8.732183783019803e-05 tokens_per_second_per_gpu:885.6657675828666 mfu:13.014606108014599 
Step 2749 | loss:2.004781723022461 lr:8.725941562431399e-05 tokens_per_second_per_gpu:867.9306860882626 mfu:12.753994138585384 
Step 2750 | loss:2.0039191246032715 lr:8.719699846434492e-05 tokens_per_second_per_gpu:813.9418489317769 mfu:11.960643559236427 
Step 2751 | loss:1.9918079376220703 lr:8.713458637501111e-05 tokens_per_second_per_gpu:858.2541772427345 mfu:12.61180059816102 
Step 2752 | loss:1.9924787282943726 lr:8.707217938103097e-05 tokens_per_second_per_gpu:898.747873015203 mfu:13.206843919949051 
Step 2753 | loss:2.022202968597412 lr:8.70097775071208e-05 tokens_per_second_per_gpu:886.9782560858544 mfu:13.033892752607741 
Step 2754 | loss:2.0458133220672607 lr:8.694738077799488e-05 tokens_per_second_per_gpu:844.2801012332322 mfu:12.40645553273812 
Step 2755 | loss:1.9867326021194458 lr:8.688498921836541e-05 tokens_per_second_per_gpu:864.136344226597 mfu:12.698237366023765 
Step 2756 | loss:1.9928444623947144 lr:8.682260285294271e-05 tokens_per_second_per_gpu:879.9391195489857 mfu:12.930454646810897 
Step 2757 | loss:2.0140786170959473 lr:8.676022170643488e-05 tokens_per_second_per_gpu:864.8032868676644 mfu:12.7080378981069 
Step 2758 | loss:1.9982705116271973 lr:8.669784580354801e-05 tokens_per_second_per_gpu:833.138626982073 mfu:12.24273474308046 
Step 2759 | loss:1.978100061416626 lr:8.663547516898607e-05 tokens_per_second_per_gpu:893.8691036463864 mfu:13.135151794148271 
Step 2760 | loss:2.0457756519317627 lr:8.657310982745103e-05 tokens_per_second_per_gpu:868.9600900655619 mfu:12.769120936730847 
Step 2761 | loss:1.9890578985214233 lr:8.651074980364274e-05 tokens_per_second_per_gpu:881.6925847460244 mfu:12.956221318278683 
Step 2762 | loss:2.0388548374176025 lr:8.644839512225886e-05 tokens_per_second_per_gpu:875.1092293027757 mfu:12.859480785790032 
Step 2763 | loss:2.0032958984375 lr:8.638604580799498e-05 tokens_per_second_per_gpu:886.3595645664412 mfu:13.024801257009457 
Step 2764 | loss:2.02132511138916 lr:8.632370188554463e-05 tokens_per_second_per_gpu:864.8174019609717 mfu:12.708245315381335 
Step 2765 | loss:1.9353896379470825 lr:8.626136337959914e-05 tokens_per_second_per_gpu:851.6992090899562 mfu:12.51547720881764 
Step 2766 | loss:1.9938170909881592 lr:8.619903031484771e-05 tokens_per_second_per_gpu:863.2663000862676 mfu:12.68545231527728 
Step 2767 | loss:2.0545613765716553 lr:8.613670271597733e-05 tokens_per_second_per_gpu:892.4561705314284 mfu:13.114389144601214 
Step 2768 | loss:2.0288400650024414 lr:8.607438060767296e-05 tokens_per_second_per_gpu:847.4111049725843 mfu:12.45246474059268 
Step 2769 | loss:1.9874680042266846 lr:8.601206401461727e-05 tokens_per_second_per_gpu:889.3780427437002 mfu:13.06915693379019 
Step 2770 | loss:2.050659418106079 lr:8.594975296149076e-05 tokens_per_second_per_gpu:878.2695506453382 mfu:12.905920807470507 
Step 2771 | loss:1.9846798181533813 lr:8.588744747297173e-05 tokens_per_second_per_gpu:869.9453098550554 mfu:12.7835984608256 
Step 2772 | loss:2.0048699378967285 lr:8.582514757373639e-05 tokens_per_second_per_gpu:860.9313564595598 mfu:12.651140983962128 
Step 2773 | loss:2.009687900543213 lr:8.576285328845856e-05 tokens_per_second_per_gpu:890.3327449334632 mfu:13.08318601045207 
Step 2774 | loss:2.0501649379730225 lr:8.570056464180998e-05 tokens_per_second_per_gpu:833.2577308592896 mfu:12.244484940620715 
Step 2775 | loss:1.9759159088134766 lr:8.563828165846005e-05 tokens_per_second_per_gpu:874.5470372945217 mfu:12.851219534410216 
Step 2776 | loss:1.9872187376022339 lr:8.557600436307602e-05 tokens_per_second_per_gpu:873.7445057390073 mfu:12.839426561861693 
Step 2777 | loss:2.0194098949432373 lr:8.551373278032284e-05 tokens_per_second_per_gpu:839.3480756181101 mfu:12.333980821571814 
Step 2778 | loss:2.031827688217163 lr:8.545146693486319e-05 tokens_per_second_per_gpu:869.2268837533858 mfu:12.77304139395774 
Step 2779 | loss:1.993014931678772 lr:8.538920685135745e-05 tokens_per_second_per_gpu:877.2644012555118 mfu:12.891150423577264 
Step 2780 | loss:2.0006983280181885 lr:8.532695255446383e-05 tokens_per_second_per_gpu:840.7056915478962 mfu:12.353930600843912 
Step 2781 | loss:1.9871103763580322 lr:8.526470406883816e-05 tokens_per_second_per_gpu:886.9561800974129 mfu:13.033568352247553 
Step 2782 | loss:1.9841235876083374 lr:8.520246141913393e-05 tokens_per_second_per_gpu:895.0480916636186 mfu:13.152476687140604 
Step 2783 | loss:2.0297305583953857 lr:8.514022463000244e-05 tokens_per_second_per_gpu:860.884985372222 mfu:12.650459574045893 
Step 2784 | loss:1.9939371347427368 lr:8.507799372609258e-05 tokens_per_second_per_gpu:896.7708186049293 mfu:13.177791668698505 
Step 2785 | loss:2.064920425415039 lr:8.501576873205095e-05 tokens_per_second_per_gpu:885.4414261222041 mfu:13.011309474170224 
Step 2786 | loss:2.0168564319610596 lr:8.495354967252169e-05 tokens_per_second_per_gpu:856.6778447453223 mfu:12.588636841245055 
Step 2787 | loss:1.9803524017333984 lr:8.489133657214682e-05 tokens_per_second_per_gpu:887.5468208998627 mfu:13.042247650552358 
Step 2788 | loss:1.9915781021118164 lr:8.482912945556583e-05 tokens_per_second_per_gpu:871.0163323629301 mfu:12.799336831419792 
Step 2789 | loss:2.0478549003601074 lr:8.476692834741585e-05 tokens_per_second_per_gpu:879.5183230353363 mfu:12.924271161937456 
Step 2790 | loss:2.032698154449463 lr:8.470473327233166e-05 tokens_per_second_per_gpu:911.0983496146696 mfu:13.388330654642418 
Step 2791 | loss:1.9930875301361084 lr:8.464254425494568e-05 tokens_per_second_per_gpu:869.3042964496286 mfu:12.774178951472365 
Step 2792 | loss:2.0013444423675537 lr:8.458036131988792e-05 tokens_per_second_per_gpu:839.5680605914822 mfu:12.337213438076722 
Step 2793 | loss:2.038243055343628 lr:8.451818449178591e-05 tokens_per_second_per_gpu:882.3788363896273 mfu:12.966305590652496 
Step 2794 | loss:1.970747470855713 lr:8.445601379526482e-05 tokens_per_second_per_gpu:865.2225459760299 mfu:12.714198791247737 
Step 2795 | loss:2.0245513916015625 lr:8.439384925494743e-05 tokens_per_second_per_gpu:864.681692352152 mfu:12.706251101346531 
Step 2796 | loss:2.0744309425354004 lr:8.433169089545404e-05 tokens_per_second_per_gpu:881.7061614609228 mfu:12.956420824235796 
Step 2797 | loss:2.005263090133667 lr:8.426953874140244e-05 tokens_per_second_per_gpu:873.4943440261685 mfu:12.835750506768372 
Step 2798 | loss:2.0480852127075195 lr:8.420739281740805e-05 tokens_per_second_per_gpu:856.3276182185533 mfu:12.583490362221804 
Step 2799 | loss:1.989311695098877 lr:8.414525314808381e-05 tokens_per_second_per_gpu:878.4481155227918 mfu:12.908544767467433 
Step 2800 | loss:2.0234532356262207 lr:8.408311975804017e-05 tokens_per_second_per_gpu:847.7851665719397 mfu:12.457961469216425 
Step 2801 | loss:2.0265917778015137 lr:8.402099267188508e-05 tokens_per_second_per_gpu:863.5193290409254 mfu:12.689170503672186 
Step 2802 | loss:2.003325939178467 lr:8.395887191422397e-05 tokens_per_second_per_gpu:855.8950880423987 mfu:12.57713445452104 
Step 2803 | loss:2.02333927154541 lr:8.389675750965987e-05 tokens_per_second_per_gpu:893.5549532149826 mfu:13.1305354430675 
Step 2804 | loss:2.0465972423553467 lr:8.383464948279319e-05 tokens_per_second_per_gpu:870.4747001890753 mfu:12.7913777009485 
Step 2805 | loss:2.0015461444854736 lr:8.377254785822181e-05 tokens_per_second_per_gpu:877.6723082880446 mfu:12.897144501198209 
Step 2806 | loss:2.0008926391601562 lr:8.371045266054114e-05 tokens_per_second_per_gpu:858.7776815544962 mfu:12.619493344863901 
Step 2807 | loss:2.0400824546813965 lr:8.364836391434402e-05 tokens_per_second_per_gpu:869.1251603177955 mfu:12.771546597055094 
Step 2808 | loss:2.045226573944092 lr:8.358628164422072e-05 tokens_per_second_per_gpu:859.9981764756349 mfu:12.637428169982865 
Step 2809 | loss:2.014374017715454 lr:8.352420587475898e-05 tokens_per_second_per_gpu:864.6231530101799 mfu:12.705390882395458 
Step 2810 | loss:2.0304508209228516 lr:8.346213663054387e-05 tokens_per_second_per_gpu:873.1319787910185 mfu:12.83042565288406 
Step 2811 | loss:2.015376091003418 lr:8.340007393615803e-05 tokens_per_second_per_gpu:892.2480009858067 mfu:13.11133015244061 
Step 2812 | loss:2.0101377964019775 lr:8.33380178161814e-05 tokens_per_second_per_gpu:862.3066899579655 mfu:12.671351117856949 
Step 2813 | loss:2.0358099937438965 lr:8.327596829519132e-05 tokens_per_second_per_gpu:852.1021036108626 mfu:12.521397629008414 
Step 2814 | loss:2.0367112159729004 lr:8.32139253977625e-05 tokens_per_second_per_gpu:891.0718220014699 mfu:13.094046537386316 
Step 2815 | loss:1.9575910568237305 lr:8.315188914846714e-05 tokens_per_second_per_gpu:833.3643647271606 mfu:12.246051894926628 
Step 2816 | loss:2.0136821269989014 lr:8.308985957187466e-05 tokens_per_second_per_gpu:906.336101470798 mfu:13.318350775042619 
Step 2817 | loss:1.9596929550170898 lr:8.302783669255196e-05 tokens_per_second_per_gpu:858.429124090417 mfu:12.61437139224132 
Step 2818 | loss:2.0139176845550537 lr:8.296582053506317e-05 tokens_per_second_per_gpu:882.2101668418866 mfu:12.963827039706294 
Step 2819 | loss:2.058897018432617 lr:8.290381112396987e-05 tokens_per_second_per_gpu:878.4188259094386 mfu:12.908114364944495 
Step 2820 | loss:2.0583925247192383 lr:8.284180848383095e-05 tokens_per_second_per_gpu:867.0852383935658 mfu:12.741570525599371 
Step 2821 | loss:2.0311508178710938 lr:8.277981263920247e-05 tokens_per_second_per_gpu:824.7486782666571 mfu:12.119446837197426 
Step 2822 | loss:1.9744951725006104 lr:8.271782361463805e-05 tokens_per_second_per_gpu:854.1735750780562 mfu:12.551837312008798 
Step 2823 | loss:1.9687120914459229 lr:8.26558414346884e-05 tokens_per_second_per_gpu:887.9380179948143 mfu:13.047996180401594 
Step 2824 | loss:2.0509285926818848 lr:8.25938661239016e-05 tokens_per_second_per_gpu:863.1962390515583 mfu:12.684422788334231 
Step 2825 | loss:2.0232913494110107 lr:8.253189770682301e-05 tokens_per_second_per_gpu:855.3125054366318 mfu:12.568573569120524 
Step 2826 | loss:2.012451648712158 lr:8.246993620799526e-05 tokens_per_second_per_gpu:864.0367586949432 mfu:12.696773985010328 
Step 2827 | loss:2.0348668098449707 lr:8.240798165195822e-05 tokens_per_second_per_gpu:878.2446169465132 mfu:12.90555441387046 
Step 2828 | loss:2.004626512527466 lr:8.234603406324908e-05 tokens_per_second_per_gpu:877.0429966953817 mfu:12.887896946649422 
Step 2829 | loss:2.0055105686187744 lr:8.228409346640209e-05 tokens_per_second_per_gpu:883.7264963162203 mfu:12.986109069294368 
Step 2830 | loss:1.9810582399368286 lr:8.222215988594898e-05 tokens_per_second_per_gpu:867.51760932802 mfu:12.747924093288718 
Step 2831 | loss:2.0781617164611816 lr:8.216023334641851e-05 tokens_per_second_per_gpu:896.2452077422369 mfu:13.170067966829905 
Step 2832 | loss:2.031656503677368 lr:8.209831387233676e-05 tokens_per_second_per_gpu:860.3161579475423 mfu:12.642100817112283 
Step 2833 | loss:2.0118584632873535 lr:8.20364014882269e-05 tokens_per_second_per_gpu:891.2822610510326 mfu:13.097138879260699 
Step 2834 | loss:1.987271785736084 lr:8.197449621860943e-05 tokens_per_second_per_gpu:814.7359924728611 mfu:11.972313272302838 
Step 2835 | loss:2.0479109287261963 lr:8.191259808800195e-05 tokens_per_second_per_gpu:880.8298666506586 mfu:12.943543921675575 
Step 2836 | loss:2.011500835418701 lr:8.185070712091924e-05 tokens_per_second_per_gpu:877.5503570929487 mfu:12.895352463132983 
Step 2837 | loss:1.969508409500122 lr:8.178882334187319e-05 tokens_per_second_per_gpu:856.7322893938557 mfu:12.589436889842716 
Step 2838 | loss:1.9834015369415283 lr:8.172694677537302e-05 tokens_per_second_per_gpu:868.6421337992756 mfu:12.764448659990848 
Step 2839 | loss:2.0084660053253174 lr:8.16650774459249e-05 tokens_per_second_per_gpu:882.8217184778763 mfu:12.972813616751989 
Step 2840 | loss:1.99197518825531 lr:8.16032153780322e-05 tokens_per_second_per_gpu:878.2691874311255 mfu:12.905915470141139 
Step 2841 | loss:2.0062806606292725 lr:8.154136059619545e-05 tokens_per_second_per_gpu:861.815621311007 mfu:12.664135004006685 
Step 2842 | loss:2.0300493240356445 lr:8.147951312491227e-05 tokens_per_second_per_gpu:888.4964009038835 mfu:13.056201458154188 
Step 2843 | loss:2.0076539516448975 lr:8.141767298867738e-05 tokens_per_second_per_gpu:859.5833938601401 mfu:12.631333057629307 
Step 2844 | loss:2.0056159496307373 lr:8.135584021198261e-05 tokens_per_second_per_gpu:880.6151015607173 mfu:12.94038800987042 
Step 2845 | loss:1.9959585666656494 lr:8.12940148193168e-05 tokens_per_second_per_gpu:844.9184253554366 mfu:12.41583552384064 
Step 2846 | loss:1.9850549697875977 lr:8.123219683516603e-05 tokens_per_second_per_gpu:825.1588222061661 mfu:12.125473785529037 
Step 2847 | loss:2.0257458686828613 lr:8.117038628401325e-05 tokens_per_second_per_gpu:904.0879794201201 mfu:13.285315262049759 
Step 2848 | loss:2.0562639236450195 lr:8.110858319033863e-05 tokens_per_second_per_gpu:883.9741693443838 mfu:12.989748553875469 
Step 2849 | loss:2.027226448059082 lr:8.104678757861925e-05 tokens_per_second_per_gpu:874.0025552052874 mfu:12.843218525244431 
Step 2850 | loss:2.034374237060547 lr:8.098499947332934e-05 tokens_per_second_per_gpu:856.0343305025568 mfu:12.579180582799674 
Step 2851 | loss:2.0474894046783447 lr:8.092321889894012e-05 tokens_per_second_per_gpu:870.6782762423578 mfu:12.794369193047972 
Step 2852 | loss:2.0231573581695557 lr:8.08614458799198e-05 tokens_per_second_per_gpu:862.368542987411 mfu:12.672260030501297 
Step 2853 | loss:2.0006232261657715 lr:8.079968044073357e-05 tokens_per_second_per_gpu:870.099627157473 mfu:12.785866109616068 
Step 2854 | loss:2.0678470134735107 lr:8.073792260584377e-05 tokens_per_second_per_gpu:881.8410927670374 mfu:12.958403601334107 
Step 2855 | loss:1.9770047664642334 lr:8.067617239970952e-05 tokens_per_second_per_gpu:877.5720566641559 mfu:12.895671332149163 
Step 2856 | loss:2.0022287368774414 lr:8.061442984678708e-05 tokens_per_second_per_gpu:869.2300000047734 mfu:12.773087186383991 
Step 2857 | loss:2.0056679248809814 lr:8.055269497152957e-05 tokens_per_second_per_gpu:859.4200991205398 mfu:12.628933487957323 
Step 2858 | loss:2.0474209785461426 lr:8.049096779838719e-05 tokens_per_second_per_gpu:899.7681299708917 mfu:13.221836305218144 
Step 2859 | loss:1.9497956037521362 lr:8.042924835180696e-05 tokens_per_second_per_gpu:874.9549512324865 mfu:12.857213713504514 
Step 2860 | loss:1.9963605403900146 lr:8.036753665623289e-05 tokens_per_second_per_gpu:872.6678600010727 mfu:12.82360555950396 
Step 2861 | loss:2.0168843269348145 lr:8.0305832736106e-05 tokens_per_second_per_gpu:865.6932590572442 mfu:12.72111578585916 
Step 2862 | loss:2.0222041606903076 lr:8.024413661586409e-05 tokens_per_second_per_gpu:888.759051045876 mfu:13.060061027155681 
Step 2863 | loss:2.021635055541992 lr:8.018244831994199e-05 tokens_per_second_per_gpu:861.9644871237882 mfu:12.666322544710198 
Step 2864 | loss:1.993349552154541 lr:8.01207678727713e-05 tokens_per_second_per_gpu:836.4416335973834 mfu:12.291271484189638 
Step 2865 | loss:2.0737311840057373 lr:8.00590952987807e-05 tokens_per_second_per_gpu:890.4825300956095 mfu:13.085387060732561 
Step 2866 | loss:2.034119129180908 lr:7.999743062239557e-05 tokens_per_second_per_gpu:871.2514234621062 mfu:12.802791428139304 
Step 2867 | loss:1.9667420387268066 lr:7.993577386803827e-05 tokens_per_second_per_gpu:889.2642557313909 mfu:13.067484866064849 
Step 2868 | loss:2.0243396759033203 lr:7.987412506012794e-05 tokens_per_second_per_gpu:856.9628770983849 mfu:12.592825310461015 
Step 2869 | loss:2.0082712173461914 lr:7.98124842230807e-05 tokens_per_second_per_gpu:872.8512094610993 mfu:12.82629982757856 
Step 2870 | loss:2.078204870223999 lr:7.975085138130938e-05 tokens_per_second_per_gpu:889.2825849065148 mfu:13.06775420807089 
Step 2871 | loss:2.0305676460266113 lr:7.968922655922374e-05 tokens_per_second_per_gpu:865.1734917558405 mfu:12.713477953458732 
Step 2872 | loss:2.0247116088867188 lr:7.962760978123023e-05 tokens_per_second_per_gpu:870.0425817367276 mfu:12.785027843411768 
Step 2873 | loss:2.035393238067627 lr:7.956600107173233e-05 tokens_per_second_per_gpu:898.6492834747411 mfu:13.205395174742398 
Step 2874 | loss:1.9914052486419678 lr:7.950440045513013e-05 tokens_per_second_per_gpu:862.4946759758998 mfu:12.674113518828939 
Step 2875 | loss:2.0035910606384277 lr:7.944280795582059e-05 tokens_per_second_per_gpu:891.2306092303198 mfu:13.09637987047212 
Step 2876 | loss:2.0288543701171875 lr:7.938122359819746e-05 tokens_per_second_per_gpu:880.9283969952571 mfu:12.944991797015883 
Step 2877 | loss:2.002708673477173 lr:7.931964740665126e-05 tokens_per_second_per_gpu:894.5585226069717 mfu:13.1452826093427 
Step 2878 | loss:1.947066307067871 lr:7.925807940556926e-05 tokens_per_second_per_gpu:878.3422296689027 mfu:12.906988805013857 
Step 2879 | loss:1.9759044647216797 lr:7.919651961933553e-05 tokens_per_second_per_gpu:898.3054754599762 mfu:13.200343013924265 
Step 2880 | loss:2.065365791320801 lr:7.913496807233077e-05 tokens_per_second_per_gpu:892.2576703221854 mfu:13.111472240583678 
Step 2881 | loss:2.0293729305267334 lr:7.907342478893263e-05 tokens_per_second_per_gpu:897.701590260608 mfu:13.191469092980379 
Step 2882 | loss:2.0064289569854736 lr:7.901188979351526e-05 tokens_per_second_per_gpu:884.9027839762706 mfu:13.003394281307308 
Step 2883 | loss:2.107375144958496 lr:7.895036311044966e-05 tokens_per_second_per_gpu:885.8485937681245 mfu:13.017292686715566 
Step 2884 | loss:2.0054407119750977 lr:7.888884476410348e-05 tokens_per_second_per_gpu:852.9072355761689 mfu:12.533228813837912 
Step 2885 | loss:2.0084140300750732 lr:7.882733477884115e-05 tokens_per_second_per_gpu:888.5013131026323 mfu:13.056273641515203 
Step 2886 | loss:2.007133722305298 lr:7.876583317902367e-05 tokens_per_second_per_gpu:883.0439120144443 mfu:12.97607868746379 
Step 2887 | loss:2.0160293579101562 lr:7.870433998900884e-05 tokens_per_second_per_gpu:886.1442878792768 mfu:13.021637827428872 
Step 2888 | loss:2.0171024799346924 lr:7.864285523315096e-05 tokens_per_second_per_gpu:882.0571722333243 mfu:12.961578827525166 
Step 2889 | loss:2.0296454429626465 lr:7.858137893580126e-05 tokens_per_second_per_gpu:880.9792015710591 mfu:12.945738355781895 
Step 2890 | loss:2.0091872215270996 lr:7.851991112130735e-05 tokens_per_second_per_gpu:872.5362830414168 mfu:12.82167207357113 
Step 2891 | loss:2.0076398849487305 lr:7.845845181401358e-05 tokens_per_second_per_gpu:887.5344418805175 mfu:13.042065744390149 
Step 2892 | loss:2.0101518630981445 lr:7.839700103826098e-05 tokens_per_second_per_gpu:846.0961603060202 mfu:12.4331420033756 
Step 2893 | loss:1.9923579692840576 lr:7.833555881838715e-05 tokens_per_second_per_gpu:889.1755531111053 mfu:13.066181406333175 
Step 2894 | loss:2.0211822986602783 lr:7.827412517872634e-05 tokens_per_second_per_gpu:885.832709417936 mfu:13.017059270715365 
Step 2895 | loss:2.013821840286255 lr:7.821270014360935e-05 tokens_per_second_per_gpu:900.2080659432607 mfu:13.228301038984197 
Step 2896 | loss:2.0061330795288086 lr:7.815128373736355e-05 tokens_per_second_per_gpu:874.3960847162751 mfu:12.849001329282757 
Step 2897 | loss:1.9799299240112305 lr:7.808987598431303e-05 tokens_per_second_per_gpu:839.9006566781582 mfu:12.342100842806124 
Step 2898 | loss:1.9649187326431274 lr:7.802847690877832e-05 tokens_per_second_per_gpu:844.890799564938 mfu:12.415429570720487 
Step 2899 | loss:2.0049264430999756 lr:7.796708653507652e-05 tokens_per_second_per_gpu:887.7210667112007 mfu:13.044808143103317 
Step 2900 | loss:2.0365216732025146 lr:7.790570488752135e-05 tokens_per_second_per_gpu:876.1195209935299 mfu:12.874326734330248 
Step 2901 | loss:2.034010887145996 lr:7.784433199042308e-05 tokens_per_second_per_gpu:876.3119105519469 mfu:12.877153844074959 
Step 2902 | loss:2.1162526607513428 lr:7.778296786808843e-05 tokens_per_second_per_gpu:876.8436021342102 mfu:12.884966900385118 
Step 2903 | loss:1.981446623802185 lr:7.772161254482068e-05 tokens_per_second_per_gpu:888.1217907728147 mfu:13.050696669013204 
Step 2904 | loss:2.035661220550537 lr:7.766026604491967e-05 tokens_per_second_per_gpu:853.8292687942652 mfu:12.546777829269296 
Step 2905 | loss:2.0425291061401367 lr:7.759892839268174e-05 tokens_per_second_per_gpu:842.4645448427004 mfu:12.379776448873168 
Step 2906 | loss:1.985321283340454 lr:7.753759961239964e-05 tokens_per_second_per_gpu:887.6337744324968 mfu:13.043525407939347 
Step 2907 | loss:1.9962685108184814 lr:7.747627972836265e-05 tokens_per_second_per_gpu:868.2296664237929 mfu:12.758387569429603 
Step 2908 | loss:2.001901626586914 lr:7.741496876485661e-05 tokens_per_second_per_gpu:882.3908010983998 mfu:12.966481408638888 
Step 2909 | loss:2.0225536823272705 lr:7.735366674616372e-05 tokens_per_second_per_gpu:847.2432191216706 mfu:12.449997705848055 
Step 2910 | loss:2.029665470123291 lr:7.729237369656269e-05 tokens_per_second_per_gpu:868.7410606425708 mfu:12.76590236176653 
Step 2911 | loss:2.044516086578369 lr:7.723108964032864e-05 tokens_per_second_per_gpu:837.5822823972555 mfu:12.308032993306593 
Step 2912 | loss:2.013892889022827 lr:7.716981460173319e-05 tokens_per_second_per_gpu:874.2092498026777 mfu:12.846255843461021 
Step 2913 | loss:2.0270397663116455 lr:7.710854860504434e-05 tokens_per_second_per_gpu:885.8778639566684 mfu:13.017722803796467 
Step 2914 | loss:2.0164380073547363 lr:7.704729167452647e-05 tokens_per_second_per_gpu:864.3507862629899 mfu:12.701388530649075 
Step 2915 | loss:2.0453295707702637 lr:7.698604383444044e-05 tokens_per_second_per_gpu:864.4785489149449 mfu:12.703265966417025 
Step 2916 | loss:2.070051908493042 lr:7.692480510904354e-05 tokens_per_second_per_gpu:860.107796605918 mfu:12.63903900656407 
Step 2917 | loss:1.977585792541504 lr:7.686357552258936e-05 tokens_per_second_per_gpu:854.1769938340589 mfu:12.551887549654175 
Step 2918 | loss:2.0036213397979736 lr:7.68023550993279e-05 tokens_per_second_per_gpu:853.0848388518258 mfu:12.535838643370418 
Step 2919 | loss:2.0178165435791016 lr:7.674114386350554e-05 tokens_per_second_per_gpu:854.6450027083299 mfu:12.55876480671506 
Step 2920 | loss:2.0326385498046875 lr:7.667994183936506e-05 tokens_per_second_per_gpu:872.8704360376076 mfu:12.826582356642254 
Step 2921 | loss:2.0084424018859863 lr:7.661874905114554e-05 tokens_per_second_per_gpu:886.1882430502797 mfu:13.022283736142917 
Step 2922 | loss:1.989353895187378 lr:7.655756552308238e-05 tokens_per_second_per_gpu:892.9557226218797 mfu:13.121729920236476 
Step 2923 | loss:1.9760425090789795 lr:7.649639127940735e-05 tokens_per_second_per_gpu:863.7961764628902 mfu:12.69323869765774 
Step 2924 | loss:2.017369508743286 lr:7.643522634434856e-05 tokens_per_second_per_gpu:881.8239901036364 mfu:12.958152282568374 
Step 2925 | loss:2.0784873962402344 lr:7.637407074213043e-05 tokens_per_second_per_gpu:875.4818964678892 mfu:12.864957023599901 
Step 2926 | loss:2.074777126312256 lr:7.631292449697364e-05 tokens_per_second_per_gpu:879.4139275094174 mfu:12.922737099428772 
Step 2927 | loss:2.0051169395446777 lr:7.625178763309519e-05 tokens_per_second_per_gpu:856.0494540094095 mfu:12.579402818423839 
Step 2928 | loss:1.9909930229187012 lr:7.61906601747084e-05 tokens_per_second_per_gpu:883.3120179420297 mfu:12.980018427680092 
Step 2929 | loss:2.028275728225708 lr:7.612954214602282e-05 tokens_per_second_per_gpu:894.9352153957634 mfu:13.150818002545526 
Step 2930 | loss:2.0041282176971436 lr:7.606843357124426e-05 tokens_per_second_per_gpu:890.4224811086456 mfu:13.084504657978467 
Step 2931 | loss:1.9740276336669922 lr:7.600733447457475e-05 tokens_per_second_per_gpu:881.522151037848 mfu:12.953716843497526 
Step 2932 | loss:2.006721019744873 lr:7.594624488021274e-05 tokens_per_second_per_gpu:882.0549807805935 mfu:12.961546624751684 
Step 2933 | loss:1.9966516494750977 lr:7.588516481235271e-05 tokens_per_second_per_gpu:870.789409994292 mfu:12.796002271868074 
Step 2934 | loss:2.0339608192443848 lr:7.582409429518548e-05 tokens_per_second_per_gpu:882.0805357400417 mfu:12.961922147599575 
Step 2935 | loss:1.9394454956054688 lr:7.576303335289803e-05 tokens_per_second_per_gpu:882.0178431804594 mfu:12.961000898299071 
Step 2936 | loss:2.0016636848449707 lr:7.570198200967362e-05 tokens_per_second_per_gpu:871.8738013696592 mfu:12.811937094160966 
Step 2937 | loss:2.0145208835601807 lr:7.564094028969166e-05 tokens_per_second_per_gpu:892.2160915802953 mfu:13.110861252818346 
Step 2938 | loss:1.9594217538833618 lr:7.557990821712769e-05 tokens_per_second_per_gpu:865.0974010407277 mfu:12.71235982208015 
Step 2939 | loss:2.0500755310058594 lr:7.551888581615357e-05 tokens_per_second_per_gpu:871.1433070797748 mfu:12.801202688705796 
Step 2940 | loss:2.0042104721069336 lr:7.545787311093726e-05 tokens_per_second_per_gpu:873.9713372136276 mfu:12.842759785751717 
Step 2941 | loss:2.0091328620910645 lr:7.539687012564281e-05 tokens_per_second_per_gpu:895.2800824685019 mfu:13.15588572591883 
Step 2942 | loss:2.0778136253356934 lr:7.533587688443049e-05 tokens_per_second_per_gpu:873.7359980698577 mfu:12.83930154408757 
Step 2943 | loss:2.0501811504364014 lr:7.527489341145676e-05 tokens_per_second_per_gpu:872.1508989467712 mfu:12.816008964105135 
Step 2944 | loss:1.9998719692230225 lr:7.521391973087412e-05 tokens_per_second_per_gpu:872.6511823822998 mfu:12.823360486647932 
Step 2945 | loss:2.0257866382598877 lr:7.515295586683122e-05 tokens_per_second_per_gpu:875.4526529700257 mfu:12.864527298730945 
Step 2946 | loss:2.0098652839660645 lr:7.509200184347282e-05 tokens_per_second_per_gpu:840.0863925569251 mfu:12.344830178624166 
Step 2947 | loss:2.063682794570923 lr:7.503105768493984e-05 tokens_per_second_per_gpu:867.1116585040724 mfu:12.741958761595566 
Step 2948 | loss:2.008841037750244 lr:7.497012341536924e-05 tokens_per_second_per_gpu:849.3144999127245 mfu:12.480434586916896 
Step 2949 | loss:2.017965793609619 lr:7.490919905889403e-05 tokens_per_second_per_gpu:862.4044834542336 mfu:12.672788165420986 
Step 2950 | loss:2.028985023498535 lr:7.48482846396433e-05 tokens_per_second_per_gpu:876.1657531049847 mfu:12.875006102035481 
Step 2951 | loss:1.9901938438415527 lr:7.478738018174234e-05 tokens_per_second_per_gpu:899.479220248281 mfu:13.217590859161428 
Step 2952 | loss:1.9980047941207886 lr:7.47264857093123e-05 tokens_per_second_per_gpu:865.282309723804 mfu:12.715077002493206 
Step 2953 | loss:1.9754996299743652 lr:7.466560124647054e-05 tokens_per_second_per_gpu:866.4403248415482 mfu:12.732093704703228 
Step 2954 | loss:1.9915568828582764 lr:7.460472681733031e-05 tokens_per_second_per_gpu:859.3098952662443 mfu:12.62731407371807 
Step 2955 | loss:2.0030269622802734 lr:7.454386244600102e-05 tokens_per_second_per_gpu:904.8346599923607 mfu:13.29628752031231 
Step 2956 | loss:2.047067642211914 lr:7.448300815658802e-05 tokens_per_second_per_gpu:878.6014924291708 mfu:12.910798597406053 
Step 2957 | loss:1.9904429912567139 lr:7.442216397319266e-05 tokens_per_second_per_gpu:876.4401702069748 mfu:12.87903858316146 
Step 2958 | loss:1.9610142707824707 lr:7.436132991991229e-05 tokens_per_second_per_gpu:889.8715396626802 mfu:13.076408730405939 
Step 2959 | loss:2.032456398010254 lr:7.430050602084033e-05 tokens_per_second_per_gpu:893.978951696487 mfu:13.136765979946254 
Step 2960 | loss:2.004751205444336 lr:7.423969230006609e-05 tokens_per_second_per_gpu:907.6275204976041 mfu:13.337327809686451 
Step 2961 | loss:1.950480580329895 lr:7.417888878167486e-05 tokens_per_second_per_gpu:869.3815744566656 mfu:12.775314529767487 
Step 2962 | loss:2.036355495452881 lr:7.411809548974792e-05 tokens_per_second_per_gpu:895.8469132694056 mfu:13.164215143034934 
Step 2963 | loss:2.0099687576293945 lr:7.40573124483625e-05 tokens_per_second_per_gpu:845.1619369590762 mfu:12.419413857474048 
Step 2964 | loss:2.055565118789673 lr:7.399653968159172e-05 tokens_per_second_per_gpu:881.233432898274 mfu:12.949474212698949 
Step 2965 | loss:2.0049893856048584 lr:7.393577721350468e-05 tokens_per_second_per_gpu:832.7521049056857 mfu:12.237054911297006 
Step 2966 | loss:1.9596055746078491 lr:7.387502506816638e-05 tokens_per_second_per_gpu:880.526974651978 mfu:12.939093010055885 
Step 2967 | loss:2.053952217102051 lr:7.381428326963775e-05 tokens_per_second_per_gpu:859.5964698961795 mfu:12.631525206253244 
Step 2968 | loss:2.0107080936431885 lr:7.375355184197561e-05 tokens_per_second_per_gpu:873.0909391403289 mfu:12.829822586910321 
Step 2969 | loss:2.0155022144317627 lr:7.369283080923269e-05 tokens_per_second_per_gpu:881.732698104303 mfu:12.956810772649366 
Step 2970 | loss:2.049746513366699 lr:7.363212019545751e-05 tokens_per_second_per_gpu:874.2212863653147 mfu:12.846432717319477 
Step 2971 | loss:1.9916378259658813 lr:7.357142002469462e-05 tokens_per_second_per_gpu:892.8679050373213 mfu:13.120439465852648 
Step 2972 | loss:1.968660831451416 lr:7.351073032098437e-05 tokens_per_second_per_gpu:860.8763136435581 mfu:12.650332145463953 
Step 2973 | loss:2.0599136352539062 lr:7.345005110836287e-05 tokens_per_second_per_gpu:894.4922865340561 mfu:13.144309289123392 
Step 2974 | loss:1.994435429573059 lr:7.338938241086217e-05 tokens_per_second_per_gpu:884.3921801709596 mfu:12.99589110387107 
Step 2975 | loss:2.0329885482788086 lr:7.332872425251018e-05 tokens_per_second_per_gpu:869.2540366641877 mfu:12.773440398245484 
Step 2976 | loss:2.020571231842041 lr:7.326807665733057e-05 tokens_per_second_per_gpu:854.9542653249783 mfu:12.563309332750652 
Step 2977 | loss:1.991748571395874 lr:7.320743964934283e-05 tokens_per_second_per_gpu:826.1805876780893 mfu:12.140488338014386 
Step 2978 | loss:1.9815888404846191 lr:7.314681325256232e-05 tokens_per_second_per_gpu:884.4736717572929 mfu:12.997088599513404 
Step 2979 | loss:1.9929883480072021 lr:7.308619749100014e-05 tokens_per_second_per_gpu:847.2301909175184 mfu:12.449806260100074 
Step 2980 | loss:2.0373666286468506 lr:7.302559238866323e-05 tokens_per_second_per_gpu:879.9552834405773 mfu:12.930692170592371 
Step 2981 | loss:2.011396646499634 lr:7.296499796955414e-05 tokens_per_second_per_gpu:842.607898360418 mfu:12.381882987971302 
Step 2982 | loss:2.008580207824707 lr:7.290441425767149e-05 tokens_per_second_per_gpu:879.441186761852 mfu:12.92313766637651 
Step 2983 | loss:2.0658822059631348 lr:7.28438412770094e-05 tokens_per_second_per_gpu:867.9151799668103 mfu:12.753766280548694 
Step 2984 | loss:1.9973266124725342 lr:7.278327905155783e-05 tokens_per_second_per_gpu:874.1770638074104 mfu:12.8457828794311 
Step 2985 | loss:1.9511468410491943 lr:7.272272760530248e-05 tokens_per_second_per_gpu:877.9474997889737 mfu:12.901188361895953 
Step 2986 | loss:2.0525710582733154 lr:7.26621869622248e-05 tokens_per_second_per_gpu:862.9298549303697 mfu:12.680508349572348 
Step 2987 | loss:2.0364816188812256 lr:7.260165714630195e-05 tokens_per_second_per_gpu:855.21803265285 mfu:12.567185318480327 
Step 2988 | loss:1.9991252422332764 lr:7.25411381815068e-05 tokens_per_second_per_gpu:872.5217166693863 mfu:12.821458024884436 
Step 2989 | loss:1.9583089351654053 lr:7.248063009180783e-05 tokens_per_second_per_gpu:868.2463990739698 mfu:12.758633450956435 
Step 2990 | loss:2.005800724029541 lr:7.242013290116944e-05 tokens_per_second_per_gpu:843.1332061022289 mfu:12.389602235564915 
Step 2991 | loss:1.9785346984863281 lr:7.235964663355148e-05 tokens_per_second_per_gpu:832.1474335931848 mfu:12.228169438644619 
Step 2992 | loss:2.031949996948242 lr:7.229917131290957e-05 tokens_per_second_per_gpu:889.511583757521 mfu:13.071119280939367 
Step 2993 | loss:1.9898849725723267 lr:7.2238706963195e-05 tokens_per_second_per_gpu:888.5278378946375 mfu:13.056663415776194 
Step 2994 | loss:2.0293636322021484 lr:7.217825360835473e-05 tokens_per_second_per_gpu:874.6838310672159 mfu:12.853229679924254 
Step 2995 | loss:2.0125863552093506 lr:7.211781127233135e-05 tokens_per_second_per_gpu:844.5053061222892 mfu:12.409764854416743 
Step 2996 | loss:1.984526515007019 lr:7.205737997906307e-05 tokens_per_second_per_gpu:851.5056937746514 mfu:12.512633556396215 
Step 2997 | loss:1.9828323125839233 lr:7.199695975248366e-05 tokens_per_second_per_gpu:874.4044923578308 mfu:12.849124877179886 
Step 2998 | loss:1.9946954250335693 lr:7.19365506165227e-05 tokens_per_second_per_gpu:855.1816219206823 mfu:12.566650273145381 
Step 2999 | loss:2.0202510356903076 lr:7.187615259510516e-05 tokens_per_second_per_gpu:852.6827813547521 mfu:12.52993052300638 
Step 3000 | loss:1.9914615154266357 lr:7.181576571215178e-05 tokens_per_second_per_gpu:874.9302364433215 mfu:12.85685053671955 
Step 3001 | loss:2.00010347366333 lr:7.175538999157876e-05 tokens_per_second_per_gpu:888.5520367068939 mfu:13.057019010427501 
Step 3002 | loss:2.0231378078460693 lr:7.169502545729797e-05 tokens_per_second_per_gpu:897.3845798109348 mfu:13.186810714746024 
Step 3003 | loss:1.9970273971557617 lr:7.163467213321681e-05 tokens_per_second_per_gpu:880.1644721705142 mfu:12.933766139376097 
Step 3004 | loss:2.0067427158355713 lr:7.157433004323825e-05 tokens_per_second_per_gpu:839.0903368947468 mfu:12.330193424467698 
Step 3005 | loss:2.008730411529541 lr:7.151399921126075e-05 tokens_per_second_per_gpu:846.2295514901103 mfu:12.435102148819578 
Step 3006 | loss:1.9841787815093994 lr:7.145367966117846e-05 tokens_per_second_per_gpu:851.386949025152 mfu:12.51088863613544 
Step 3007 | loss:1.9965567588806152 lr:7.139337141688092e-05 tokens_per_second_per_gpu:881.3342971623235 mfu:12.9509563843206 
Step 3008 | loss:2.0043601989746094 lr:7.133307450225322e-05 tokens_per_second_per_gpu:874.8132128608095 mfu:12.855130908517253 
Step 3009 | loss:2.01835560798645 lr:7.1272788941176e-05 tokens_per_second_per_gpu:858.1621056983329 mfu:12.610447633049347 
Step 3010 | loss:2.0084705352783203 lr:7.121251475752539e-05 tokens_per_second_per_gpu:882.172852586252 mfu:12.963278717351436 
Step 3011 | loss:1.9772512912750244 lr:7.115225197517304e-05 tokens_per_second_per_gpu:878.5190820112297 mfu:12.909587599795039 
Step 3012 | loss:2.0247304439544678 lr:7.109200061798604e-05 tokens_per_second_per_gpu:865.3670669983687 mfu:12.716322486493631 
Step 3013 | loss:2.003174066543579 lr:7.10317607098269e-05 tokens_per_second_per_gpu:828.3100971756763 mfu:12.171780873335031 
Step 3014 | loss:2.0008013248443604 lr:7.097153227455379e-05 tokens_per_second_per_gpu:887.7079582590421 mfu:13.044615518133748 
Step 3015 | loss:1.9958029985427856 lr:7.091131533602011e-05 tokens_per_second_per_gpu:885.180119527855 mfu:13.007469648218544 
Step 3016 | loss:2.0022525787353516 lr:7.085110991807484e-05 tokens_per_second_per_gpu:859.6579463151022 mfu:12.632428584713262 
Step 3017 | loss:2.021305799484253 lr:7.079091604456241e-05 tokens_per_second_per_gpu:882.0874361681788 mfu:12.962023547424959 
Step 3018 | loss:2.0284862518310547 lr:7.073073373932259e-05 tokens_per_second_per_gpu:875.7640863278008 mfu:12.869103723188898 
Step 3019 | loss:2.0256357192993164 lr:7.067056302619061e-05 tokens_per_second_per_gpu:884.2243358942059 mfu:12.993424680046882 
Step 3020 | loss:2.0123701095581055 lr:7.061040392899712e-05 tokens_per_second_per_gpu:866.3180092664849 mfu:12.7302963121782 
Step 3021 | loss:2.01131534576416 lr:7.055025647156819e-05 tokens_per_second_per_gpu:883.3753355389151 mfu:12.980948861725677 
Step 3022 | loss:2.0183589458465576 lr:7.04901206777252e-05 tokens_per_second_per_gpu:887.2409402066411 mfu:13.037752820917934 
Step 3023 | loss:1.9827909469604492 lr:7.042999657128503e-05 tokens_per_second_per_gpu:857.560127542808 mfu:12.601601735571379 
Step 3024 | loss:2.0015554428100586 lr:7.036988417605975e-05 tokens_per_second_per_gpu:901.0633827191858 mfu:13.240869675306929 
Step 3025 | loss:2.0105643272399902 lr:7.030978351585705e-05 tokens_per_second_per_gpu:866.811231475213 mfu:12.737544072005072 
Step 3026 | loss:2.0111782550811768 lr:7.024969461447972e-05 tokens_per_second_per_gpu:868.4431580554408 mfu:12.761524768127975 
Step 3027 | loss:2.0239615440368652 lr:7.018961749572604e-05 tokens_per_second_per_gpu:885.337107810031 mfu:13.009776546295534 
Step 3028 | loss:1.9782381057739258 lr:7.012955218338954e-05 tokens_per_second_per_gpu:868.9869928053503 mfu:12.769516264826825 
Step 3029 | loss:1.9895803928375244 lr:7.006949870125919e-05 tokens_per_second_per_gpu:887.3590895158322 mfu:13.039488991353034 
Step 3030 | loss:1.9972515106201172 lr:7.000945707311917e-05 tokens_per_second_per_gpu:815.5492813728524 mfu:11.984264320963437 
Step 3031 | loss:2.0077414512634277 lr:6.994942732274901e-05 tokens_per_second_per_gpu:834.0829911817439 mfu:12.256611905923469 
Step 3032 | loss:1.947704792022705 lr:6.988940947392344e-05 tokens_per_second_per_gpu:877.4023959521983 mfu:12.893178216327199 
Step 3033 | loss:2.0228395462036133 lr:6.98294035504127e-05 tokens_per_second_per_gpu:860.7548926975888 mfu:12.648547899258563 
Step 3034 | loss:1.9920262098312378 lr:6.976940957598206e-05 tokens_per_second_per_gpu:873.8006636282639 mfu:12.84025178604364 
Step 3035 | loss:1.9526112079620361 lr:6.97094275743922e-05 tokens_per_second_per_gpu:893.7753014173417 mfu:13.133773397118878 
Step 3036 | loss:2.0098023414611816 lr:6.964945756939901e-05 tokens_per_second_per_gpu:865.7310412217347 mfu:12.721670984001339 
Step 3037 | loss:2.0579144954681396 lr:6.958949958475367e-05 tokens_per_second_per_gpu:856.6439402865512 mfu:12.588138624883577 
Step 3038 | loss:1.9972931146621704 lr:6.952955364420255e-05 tokens_per_second_per_gpu:881.6974152784142 mfu:12.95629230157582 
Step 3039 | loss:1.9981937408447266 lr:6.946961977148729e-05 tokens_per_second_per_gpu:887.8889001799342 mfu:13.047274408106729 
Step 3040 | loss:1.9919795989990234 lr:6.940969799034465e-05 tokens_per_second_per_gpu:884.852581255219 mfu:13.002656566625369 
Step 3041 | loss:2.047262668609619 lr:6.93497883245068e-05 tokens_per_second_per_gpu:853.7855908206911 mfu:12.546135993892488 
Step 3042 | loss:1.986279010772705 lr:6.928989079770094e-05 tokens_per_second_per_gpu:876.541867382128 mfu:12.880532994174464 
Step 3043 | loss:2.0202598571777344 lr:6.92300054336495e-05 tokens_per_second_per_gpu:854.9631445680399 mfu:12.56343981069754 
Step 3044 | loss:2.007925510406494 lr:6.91701322560701e-05 tokens_per_second_per_gpu:874.0579161544757 mfu:12.84403203861914 
Step 3045 | loss:1.9554443359375 lr:6.91102712886756e-05 tokens_per_second_per_gpu:872.7283179648583 mfu:12.82449397205592 
Step 3046 | loss:2.0083937644958496 lr:6.905042255517393e-05 tokens_per_second_per_gpu:859.2492023684578 mfu:12.626422208877903 
Step 3047 | loss:1.99448823928833 lr:6.899058607926822e-05 tokens_per_second_per_gpu:880.8640394043927 mfu:12.944046080555092 
Step 3048 | loss:1.9816362857818604 lr:6.893076188465667e-05 tokens_per_second_per_gpu:879.3655182879118 mfu:12.922025739711652 
Step 3049 | loss:1.9651025533676147 lr:6.887094999503283e-05 tokens_per_second_per_gpu:869.5486037049859 mfu:12.777768976981065 
Step 3050 | loss:2.0265650749206543 lr:6.881115043408511e-05 tokens_per_second_per_gpu:875.3466912383687 mfu:12.862970221275186 
Step 3051 | loss:1.9850316047668457 lr:6.87513632254972e-05 tokens_per_second_per_gpu:877.1982159795945 mfu:12.890177849805372 
Step 3052 | loss:1.9353736639022827 lr:6.869158839294782e-05 tokens_per_second_per_gpu:831.6751110518263 mfu:12.221228793474948 
Step 3053 | loss:1.9954760074615479 lr:6.863182596011087e-05 tokens_per_second_per_gpu:887.4204653933444 mfu:13.040390892385672 
Step 3054 | loss:1.9968513250350952 lr:6.857207595065526e-05 tokens_per_second_per_gpu:888.1512097718008 mfu:13.051128972821152 
Step 3055 | loss:2.0284345149993896 lr:6.851233838824501e-05 tokens_per_second_per_gpu:880.4938503446895 mfu:12.93860625779816 
Step 3056 | loss:1.9998247623443604 lr:6.845261329653922e-05 tokens_per_second_per_gpu:885.2090996170804 mfu:13.007895502372612 
Step 3057 | loss:1.960375428199768 lr:6.83929006991921e-05 tokens_per_second_per_gpu:894.3154010458378 mfu:13.141710007272781 
Step 3058 | loss:1.9484798908233643 lr:6.833320061985277e-05 tokens_per_second_per_gpu:865.9797529709791 mfu:12.725325732292768 
Step 3059 | loss:2.050811767578125 lr:6.82735130821655e-05 tokens_per_second_per_gpu:875.2433879561459 mfu:12.86145220897641 
Step 3060 | loss:2.040919303894043 lr:6.821383810976958e-05 tokens_per_second_per_gpu:821.4595782567471 mfu:12.071114449692296 
Step 3061 | loss:2.0261292457580566 lr:6.815417572629931e-05 tokens_per_second_per_gpu:878.0349222767128 mfu:12.902473010444593 
Step 3062 | loss:1.9954066276550293 lr:6.809452595538402e-05 tokens_per_second_per_gpu:887.9505730938517 mfu:13.04818067400471 
Step 3063 | loss:1.9565353393554688 lr:6.8034888820648e-05 tokens_per_second_per_gpu:897.9364262602246 mfu:13.19491994108455 
Step 3064 | loss:2.0214924812316895 lr:6.79752643457106e-05 tokens_per_second_per_gpu:863.2814764971381 mfu:12.68567532831091 
Step 3065 | loss:1.9318983554840088 lr:6.791565255418615e-05 tokens_per_second_per_gpu:892.8688564418304 mfu:13.120453446470831 
Step 3066 | loss:2.0497019290924072 lr:6.785605346968386e-05 tokens_per_second_per_gpu:883.9003612250103 mfu:12.988663964590913 
Step 3067 | loss:2.0171093940734863 lr:6.7796467115808e-05 tokens_per_second_per_gpu:861.6204376509071 mfu:12.661266835733844 
Step 3068 | loss:2.0028910636901855 lr:6.77368935161578e-05 tokens_per_second_per_gpu:869.2309464267126 mfu:12.77310109378473 
Step 3069 | loss:1.9657796621322632 lr:6.76773326943274e-05 tokens_per_second_per_gpu:829.5702874843546 mfu:12.190299010863756 
Step 3070 | loss:2.0707311630249023 lr:6.761778467390592e-05 tokens_per_second_per_gpu:881.672656598616 mfu:12.955928479830504 
Step 3071 | loss:1.982521414756775 lr:6.755824947847731e-05 tokens_per_second_per_gpu:869.5787794372803 mfu:12.77821240076937 
Step 3072 | loss:2.0097415447235107 lr:6.749872713162059e-05 tokens_per_second_per_gpu:906.8581717321364 mfu:13.326022448783121 
Step 3073 | loss:1.9959641695022583 lr:6.743921765690962e-05 tokens_per_second_per_gpu:865.0873298520142 mfu:12.71221182883152 
Step 3074 | loss:1.9970033168792725 lr:6.73797210779131e-05 tokens_per_second_per_gpu:857.9365850642615 mfu:12.607133671587702 
Step 3075 | loss:2.0016350746154785 lr:6.732023741819468e-05 tokens_per_second_per_gpu:871.4023577804915 mfu:12.805009364943304 
Step 3076 | loss:2.009948968887329 lr:6.726076670131296e-05 tokens_per_second_per_gpu:857.341269277415 mfu:12.598385675719197 
Step 3077 | loss:2.033648729324341 lr:6.720130895082129e-05 tokens_per_second_per_gpu:866.1368638701765 mfu:12.727634432191953 
Step 3078 | loss:2.0373759269714355 lr:6.714186419026798e-05 tokens_per_second_per_gpu:861.1341501147313 mfu:12.654120978944283 
Step 3079 | loss:2.007847785949707 lr:6.708243244319611e-05 tokens_per_second_per_gpu:866.3652115425964 mfu:12.730989936176643 
Step 3080 | loss:2.0392098426818848 lr:6.70230137331437e-05 tokens_per_second_per_gpu:875.8312546065644 mfu:12.870090741907536 
Step 3081 | loss:2.023799180984497 lr:6.696360808364357e-05 tokens_per_second_per_gpu:862.937983426367 mfu:12.680627795505032 
Step 3082 | loss:2.005002021789551 lr:6.690421551822333e-05 tokens_per_second_per_gpu:897.5779609919275 mfu:13.18965239610195 
Step 3083 | loss:1.9910858869552612 lr:6.68448360604054e-05 tokens_per_second_per_gpu:822.1753014614295 mfu:12.081631798259044 
Step 3084 | loss:1.9651134014129639 lr:6.67854697337071e-05 tokens_per_second_per_gpu:876.2649686654843 mfu:12.87646404642822 
Step 3085 | loss:2.0268330574035645 lr:6.672611656164048e-05 tokens_per_second_per_gpu:889.2641119783779 mfu:13.06748275365528 
Step 3086 | loss:1.9921422004699707 lr:6.666677656771239e-05 tokens_per_second_per_gpu:881.6441492325804 mfu:12.955509572209017 
Step 3087 | loss:1.9794882535934448 lr:6.660744977542443e-05 tokens_per_second_per_gpu:880.1184511571151 mfu:12.933089873696646 
Step 3088 | loss:1.9694271087646484 lr:6.65481362082731e-05 tokens_per_second_per_gpu:863.3976157151532 mfu:12.687381961028898 
Step 3089 | loss:2.0136094093322754 lr:6.64888358897495e-05 tokens_per_second_per_gpu:878.2163125367699 mfu:12.905138488633861 
Step 3090 | loss:1.9922490119934082 lr:6.642954884333955e-05 tokens_per_second_per_gpu:878.6943742746353 mfu:12.912163469660971 
Step 3091 | loss:1.998967170715332 lr:6.637027509252389e-05 tokens_per_second_per_gpu:887.5960624017702 mfu:13.042971240392848 
Step 3092 | loss:1.995466709136963 lr:6.6311014660778e-05 tokens_per_second_per_gpu:862.7237644235439 mfu:12.677479908294483 
Step 3093 | loss:2.0225367546081543 lr:6.625176757157196e-05 tokens_per_second_per_gpu:875.4568580224637 mfu:12.864589090778404 
Step 3094 | loss:2.0029404163360596 lr:6.619253384837059e-05 tokens_per_second_per_gpu:883.7745506089906 mfu:12.98681521343485 
Step 3095 | loss:2.028679370880127 lr:6.613331351463348e-05 tokens_per_second_per_gpu:887.1805047959912 mfu:13.036864739777878 
Step 3096 | loss:2.0292088985443115 lr:6.607410659381483e-05 tokens_per_second_per_gpu:871.7522216446794 mfu:12.810150514743258 
Step 3097 | loss:2.008301019668579 lr:6.601491310936363e-05 tokens_per_second_per_gpu:881.4803548968697 mfu:12.953102661114535 
Step 3098 | loss:1.9991025924682617 lr:6.595573308472338e-05 tokens_per_second_per_gpu:871.839208601362 mfu:12.811428763287116 
Step 3099 | loss:2.0374369621276855 lr:6.589656654333248e-05 tokens_per_second_per_gpu:892.1110055180692 mfu:13.109317043075379 
Step 3100 | loss:2.0143320560455322 lr:6.583741350862384e-05 tokens_per_second_per_gpu:907.5104061176814 mfu:13.335606847242078 
Step 3101 | loss:2.016859769821167 lr:6.5778274004025e-05 tokens_per_second_per_gpu:841.8995586472738 mfu:12.37147413770898 
Step 3102 | loss:1.999752163887024 lr:6.57191480529582e-05 tokens_per_second_per_gpu:870.8968027263546 mfu:12.797580377467066 
Step 3103 | loss:2.0111258029937744 lr:6.566003567884035e-05 tokens_per_second_per_gpu:882.4215059618963 mfu:12.966932607859444 
Step 3104 | loss:2.017711639404297 lr:6.56009369050829e-05 tokens_per_second_per_gpu:839.2026759007098 mfu:12.331844214152351 
Step 3105 | loss:1.9822895526885986 lr:6.554185175509197e-05 tokens_per_second_per_gpu:880.0434065078693 mfu:12.931987113957932 
Step 3106 | loss:1.9731906652450562 lr:6.548278025226821e-05 tokens_per_second_per_gpu:860.0048318528244 mfu:12.637525968854394 
Step 3107 | loss:1.9908802509307861 lr:6.542372242000701e-05 tokens_per_second_per_gpu:864.3127999477782 mfu:12.700830332570217 
Step 3108 | loss:1.9917800426483154 lr:6.536467828169822e-05 tokens_per_second_per_gpu:857.7595588849238 mfu:12.604532322321177 
Step 3109 | loss:1.9856204986572266 lr:6.530564786072625e-05 tokens_per_second_per_gpu:900.438630833456 mfu:13.231689124352359 
Step 3110 | loss:2.009042739868164 lr:6.524663118047016e-05 tokens_per_second_per_gpu:856.1799537153436 mfu:12.581320474420162 
Step 3111 | loss:1.9893736839294434 lr:6.518762826430355e-05 tokens_per_second_per_gpu:884.4143660080281 mfu:12.996217118425536 
Step 3112 | loss:1.9812703132629395 lr:6.512863913559455e-05 tokens_per_second_per_gpu:827.0827013611671 mfu:12.153744641554209 
Step 3113 | loss:1.9976966381072998 lr:6.506966381770582e-05 tokens_per_second_per_gpu:868.7708573337433 mfu:12.766340215653544 
Step 3114 | loss:1.9827697277069092 lr:6.501070233399458e-05 tokens_per_second_per_gpu:829.3689767028086 mfu:12.187340806287025 
Step 3115 | loss:1.9859364032745361 lr:6.495175470781256e-05 tokens_per_second_per_gpu:872.0720787345514 mfu:12.81485072354426 
Step 3116 | loss:2.0566296577453613 lr:6.489282096250601e-05 tokens_per_second_per_gpu:862.2461293669426 mfu:12.670461197226977 
Step 3117 | loss:2.018219470977783 lr:6.483390112141563e-05 tokens_per_second_per_gpu:853.3685983150966 mfu:12.540008407833565 
Step 3118 | loss:2.0077853202819824 lr:6.477499520787665e-05 tokens_per_second_per_gpu:884.4611285011408 mfu:12.996904279938112 
Step 3119 | loss:1.9540431499481201 lr:6.471610324521883e-05 tokens_per_second_per_gpu:851.2544463215826 mfu:12.508941546659566 
Step 3120 | loss:2.020970582962036 lr:6.465722525676635e-05 tokens_per_second_per_gpu:876.4325757482184 mfu:12.878926984753871 
Step 3121 | loss:1.9654207229614258 lr:6.459836126583785e-05 tokens_per_second_per_gpu:877.4742572163323 mfu:12.894234197128716 
Step 3122 | loss:2.0378787517547607 lr:6.453951129574644e-05 tokens_per_second_per_gpu:856.733743510942 mfu:12.589458257678988 
Step 3123 | loss:2.0254411697387695 lr:6.448067536979971e-05 tokens_per_second_per_gpu:882.3269327131369 mfu:12.965542880915025 
Step 3124 | loss:1.9954450130462646 lr:6.442185351129965e-05 tokens_per_second_per_gpu:887.7159501334252 mfu:13.044732956450737 
Step 3125 | loss:1.9500527381896973 lr:6.436304574354265e-05 tokens_per_second_per_gpu:881.823852728969 mfu:12.958150263886775 
Step 3126 | loss:2.043039560317993 lr:6.43042520898196e-05 tokens_per_second_per_gpu:875.8712564877354 mfu:12.870678558153884 
Step 3127 | loss:2.0299878120422363 lr:6.424547257341575e-05 tokens_per_second_per_gpu:871.6137949325179 mfu:12.80811637364901 
Step 3128 | loss:2.0427026748657227 lr:6.418670721761073e-05 tokens_per_second_per_gpu:880.3013579501937 mfu:12.93577763690657 
Step 3129 | loss:1.9572032690048218 lr:6.412795604567862e-05 tokens_per_second_per_gpu:878.9441727836868 mfu:12.915834187578124 
Step 3130 | loss:1.9969511032104492 lr:6.406921908088783e-05 tokens_per_second_per_gpu:881.2983076126111 mfu:12.950427528141828 
Step 3131 | loss:2.0054590702056885 lr:6.401049634650118e-05 tokens_per_second_per_gpu:856.6864290382143 mfu:12.58876298498324 
Step 3132 | loss:2.0142364501953125 lr:6.395178786577587e-05 tokens_per_second_per_gpu:865.7540173157173 mfu:12.722008611155994 
Step 3133 | loss:1.9671387672424316 lr:6.389309366196332e-05 tokens_per_second_per_gpu:881.0929417788459 mfu:12.947409735728113 
Step 3134 | loss:1.9462591409683228 lr:6.383441375830951e-05 tokens_per_second_per_gpu:893.2480931989215 mfu:13.126026222562983 
Step 3135 | loss:2.024779796600342 lr:6.37757481780546e-05 tokens_per_second_per_gpu:878.5043544997944 mfu:12.909371183210705 
Step 3136 | loss:1.9343047142028809 lr:6.371709694443313e-05 tokens_per_second_per_gpu:880.5937591272798 mfu:12.940074388892006 
Step 3137 | loss:2.0116565227508545 lr:6.365846008067394e-05 tokens_per_second_per_gpu:849.4171688831256 mfu:12.48194327818418 
Step 3138 | loss:2.0115175247192383 lr:6.359983761000018e-05 tokens_per_second_per_gpu:860.7623533112816 mfu:12.648657530851077 
Step 3139 | loss:1.9999362230300903 lr:6.354122955562935e-05 tokens_per_second_per_gpu:856.6410902322153 mfu:12.588096744147157 
Step 3140 | loss:1.977561116218567 lr:6.34826359407732e-05 tokens_per_second_per_gpu:881.350256472244 mfu:12.951190901832705 
Step 3141 | loss:2.0087733268737793 lr:6.342405678863766e-05 tokens_per_second_per_gpu:873.0575793473557 mfu:12.829332374257554 
Step 3142 | loss:2.0015430450439453 lr:6.336549212242318e-05 tokens_per_second_per_gpu:894.0765341159786 mfu:13.1381999257972 
Step 3143 | loss:1.992226481437683 lr:6.330694196532423e-05 tokens_per_second_per_gpu:892.1379379298794 mfu:13.109712807193263 
Step 3144 | loss:2.006088972091675 lr:6.324840634052967e-05 tokens_per_second_per_gpu:862.1644607463128 mfu:12.669261100116096 
Step 3145 | loss:1.9920250177383423 lr:6.318988527122252e-05 tokens_per_second_per_gpu:863.1207247308328 mfu:12.68331312690694 
Step 3146 | loss:1.9978562593460083 lr:6.313137878058013e-05 tokens_per_second_per_gpu:874.7276806798064 mfu:12.853874037487506 
Step 3147 | loss:2.0183353424072266 lr:6.307288689177399e-05 tokens_per_second_per_gpu:831.3797129732726 mfu:12.21688800287633 
Step 3148 | loss:1.9924266338348389 lr:6.30144096279699e-05 tokens_per_second_per_gpu:881.9048562969734 mfu:12.959340588238815 
Step 3149 | loss:2.0461761951446533 lr:6.29559470123277e-05 tokens_per_second_per_gpu:885.6640050427558 mfu:13.014580207989859 
Step 3150 | loss:1.994134783744812 lr:6.289749906800166e-05 tokens_per_second_per_gpu:878.8921710772419 mfu:12.915070037318403 
Step 3151 | loss:1.9743504524230957 lr:6.283906581814005e-05 tokens_per_second_per_gpu:859.7435336867987 mfu:12.633686266754523 
Step 3152 | loss:2.0152366161346436 lr:6.278064728588542e-05 tokens_per_second_per_gpu:850.690009259822 mfu:12.500647304858138 
Step 3153 | loss:2.0315136909484863 lr:6.272224349437439e-05 tokens_per_second_per_gpu:858.9167988495982 mfu:12.621537633877697 
Step 3154 | loss:2.0356357097625732 lr:6.26638544667379e-05 tokens_per_second_per_gpu:855.6264121050151 mfu:12.573186338173164 
Step 3155 | loss:1.9994436502456665 lr:6.260548022610094e-05 tokens_per_second_per_gpu:870.5805117994636 mfu:12.792932572414985 
Step 3156 | loss:2.000274658203125 lr:6.254712079558263e-05 tokens_per_second_per_gpu:897.8603126288818 mfu:13.193801472958496 
Step 3157 | loss:2.0004475116729736 lr:6.248877619829619e-05 tokens_per_second_per_gpu:885.6054061238742 mfu:13.013719113573078 
Step 3158 | loss:2.001255512237549 lr:6.243044645734917e-05 tokens_per_second_per_gpu:846.7835541067842 mfu:12.44324305942347 
Step 3159 | loss:1.9344496726989746 lr:6.2372131595843e-05 tokens_per_second_per_gpu:842.542302109104 mfu:12.380919069748128 
Step 3160 | loss:1.9793586730957031 lr:6.231383163687334e-05 tokens_per_second_per_gpu:844.0304258633838 mfu:12.402786624316471 
Step 3161 | loss:2.0278353691101074 lr:6.225554660352987e-05 tokens_per_second_per_gpu:874.2256119131061 mfu:12.846496280011824 
Step 3162 | loss:1.9939595460891724 lr:6.219727651889646e-05 tokens_per_second_per_gpu:879.6969181673044 mfu:12.926895566515855 
Step 3163 | loss:2.050945997238159 lr:6.213902140605101e-05 tokens_per_second_per_gpu:899.0492222401646 mfu:13.211272160948512 
Step 3164 | loss:1.9761143922805786 lr:6.20807812880655e-05 tokens_per_second_per_gpu:882.7949698530771 mfu:12.972420553331865 
Step 3165 | loss:2.0382602214813232 lr:6.202255618800586e-05 tokens_per_second_per_gpu:859.7379095824097 mfu:12.633603622142966 
Step 3166 | loss:1.9728443622589111 lr:6.196434612893228e-05 tokens_per_second_per_gpu:838.7329873918188 mfu:12.324942275339293 
Step 3167 | loss:1.995265007019043 lr:6.190615113389884e-05 tokens_per_second_per_gpu:876.4508842576531 mfu:12.879196023083498 
Step 3168 | loss:2.0245985984802246 lr:6.18479712259537e-05 tokens_per_second_per_gpu:863.4536670981885 mfu:12.688205620132269 
Step 3169 | loss:1.981870412826538 lr:6.1789806428139e-05 tokens_per_second_per_gpu:893.5736351267291 mfu:13.130809968437706 
Step 3170 | loss:2.0031228065490723 lr:6.173165676349103e-05 tokens_per_second_per_gpu:882.9335256045753 mfu:12.974456590622399 
Step 3171 | loss:1.9703072309494019 lr:6.167352225503995e-05 tokens_per_second_per_gpu:861.278733471575 mfu:12.656245590177967 
Step 3172 | loss:2.022736072540283 lr:6.16154029258099e-05 tokens_per_second_per_gpu:864.5509558654832 mfu:12.704329965924773 
Step 3173 | loss:2.0652916431427 lr:6.155729879881918e-05 tokens_per_second_per_gpu:812.0349920191715 mfu:11.932622840213229 
Step 3174 | loss:1.9803931713104248 lr:6.149920989707989e-05 tokens_per_second_per_gpu:867.9241219744682 mfu:12.753897680803442 
Step 3175 | loss:1.9910401105880737 lr:6.14411362435982e-05 tokens_per_second_per_gpu:855.3048053430998 mfu:12.568460418440006 
Step 3176 | loss:1.983137845993042 lr:6.138307786137415e-05 tokens_per_second_per_gpu:841.366437521088 mfu:12.36364007465819 
Step 3177 | loss:1.9487189054489136 lr:6.132503477340189e-05 tokens_per_second_per_gpu:864.2307657716752 mfu:12.699624863725813 
Step 3178 | loss:2.014840602874756 lr:6.126700700266934e-05 tokens_per_second_per_gpu:838.3698648217553 mfu:12.31960629263421 
Step 3179 | loss:1.9488893747329712 lr:6.120899457215845e-05 tokens_per_second_per_gpu:864.1324882341223 mfu:12.698180703313012 
Step 3180 | loss:1.9846032857894897 lr:6.115099750484505e-05 tokens_per_second_per_gpu:880.8257972784886 mfu:12.943484123410997 
Step 3181 | loss:1.9660215377807617 lr:6.109301582369895e-05 tokens_per_second_per_gpu:855.9102588813839 mfu:12.577357385677407 
Step 3182 | loss:2.038353681564331 lr:6.103504955168382e-05 tokens_per_second_per_gpu:869.8622553852022 mfu:12.782377999055242 
Step 3183 | loss:2.009101629257202 lr:6.097709871175723e-05 tokens_per_second_per_gpu:871.4946245332504 mfu:12.806365198586171 
Step 3184 | loss:1.9892349243164062 lr:6.091916332687055e-05 tokens_per_second_per_gpu:870.1475447948411 mfu:12.786570245644349 
Step 3185 | loss:1.9937351942062378 lr:6.086124341996928e-05 tokens_per_second_per_gpu:861.4167356102479 mfu:12.658273492285769 
Step 3186 | loss:1.9594104290008545 lr:6.080333901399251e-05 tokens_per_second_per_gpu:898.206978499266 mfu:13.198895629150686 
Step 3187 | loss:1.987455129623413 lr:6.074545013187334e-05 tokens_per_second_per_gpu:891.4466166575792 mfu:13.099554038070195 
Step 3188 | loss:2.019150972366333 lr:6.068757679653868e-05 tokens_per_second_per_gpu:866.864363162375 mfu:12.738324827009473 
Step 3189 | loss:2.0164060592651367 lr:6.062971903090933e-05 tokens_per_second_per_gpu:855.9427128404724 mfu:12.577834287359329 
Step 3190 | loss:1.9916070699691772 lr:6.057187685789987e-05 tokens_per_second_per_gpu:856.7808551121972 mfu:12.59015054923625 
Step 3191 | loss:2.035745859146118 lr:6.0514050300418734e-05 tokens_per_second_per_gpu:882.2081764937113 mfu:12.963797792106956 
Step 3192 | loss:2.060793876647949 lr:6.0456239381368086e-05 tokens_per_second_per_gpu:871.4633286893928 mfu:12.805905315077592 
Step 3193 | loss:1.9879579544067383 lr:6.0398444123644084e-05 tokens_per_second_per_gpu:859.4316897281817 mfu:12.629103808634188 
Step 3194 | loss:1.975712776184082 lr:6.034066455013649e-05 tokens_per_second_per_gpu:845.0896023365943 mfu:12.41835092080648 
Step 3195 | loss:1.9987479448318481 lr:6.028290068372897e-05 tokens_per_second_per_gpu:885.7170446917055 mfu:13.015359610518955 
Step 3196 | loss:2.0035386085510254 lr:6.02251525472989e-05 tokens_per_second_per_gpu:875.0943401799391 mfu:12.859261994372204 
Step 3197 | loss:1.9974724054336548 lr:6.016742016371749e-05 tokens_per_second_per_gpu:860.1535624218882 mfu:12.639711522190016 
Step 3198 | loss:2.0153870582580566 lr:6.010970355584967e-05 tokens_per_second_per_gpu:878.2885208047875 mfu:12.906199568558579 
Step 3199 | loss:1.966606855392456 lr:6.005200274655416e-05 tokens_per_second_per_gpu:873.2713643458669 mfu:12.832473883898396 
Step 3200 | loss:1.991302251815796 lr:5.999431775868329e-05 tokens_per_second_per_gpu:900.4063646471619 mfu:13.231214981938148 
Step 3201 | loss:2.0176610946655273 lr:5.993664861508338e-05 tokens_per_second_per_gpu:854.5914953148983 mfu:12.557978530814074 
Step 3202 | loss:2.0433034896850586 lr:5.9878995338594224e-05 tokens_per_second_per_gpu:860.1696489138587 mfu:12.639947908606109 
Step 3203 | loss:1.9794886112213135 lr:5.982135795204946e-05 tokens_per_second_per_gpu:879.5293813584472 mfu:12.9244336608448 
Step 3204 | loss:1.9940581321716309 lr:5.976373647827638e-05 tokens_per_second_per_gpu:859.6994060729086 mfu:12.633037824041384 
Step 3205 | loss:2.0478286743164062 lr:5.9706130940096026e-05 tokens_per_second_per_gpu:861.9856080338753 mfu:12.666632910466094 
Step 3206 | loss:2.037201404571533 lr:5.9648541360323095e-05 tokens_per_second_per_gpu:878.4299414114075 mfu:12.908277704078865 
Step 3207 | loss:1.9995530843734741 lr:5.9590967761766005e-05 tokens_per_second_per_gpu:839.745299821262 mfu:12.339817918058788 
Step 3208 | loss:2.0085442066192627 lr:5.95334101672267e-05 tokens_per_second_per_gpu:898.1895713036912 mfu:13.198639835371427 
Step 3209 | loss:1.9943101406097412 lr:5.947586859950103e-05 tokens_per_second_per_gpu:853.3936161084856 mfu:12.540376037179268 
Step 3210 | loss:1.9768354892730713 lr:5.941834308137828e-05 tokens_per_second_per_gpu:890.486264284677 mfu:13.08544193357695 
Step 3211 | loss:1.9952473640441895 lr:5.936083363564147e-05 tokens_per_second_per_gpu:884.0101349100016 mfu:12.990277057614804 
Step 3212 | loss:2.013753652572632 lr:5.930334028506725e-05 tokens_per_second_per_gpu:877.4516613850188 mfu:12.89390215782564 
Step 3213 | loss:2.0126540660858154 lr:5.924586305242592e-05 tokens_per_second_per_gpu:839.1581710062826 mfu:12.331190227409214 
Step 3214 | loss:2.0071611404418945 lr:5.918840196048132e-05 tokens_per_second_per_gpu:851.9987237258293 mfu:12.519878491053163 
Step 3215 | loss:1.9635142087936401 lr:5.9130957031990967e-05 tokens_per_second_per_gpu:824.9255392292422 mfu:12.122045758650845 
Step 3216 | loss:2.02439022064209 lr:5.907352828970598e-05 tokens_per_second_per_gpu:881.1331029051521 mfu:12.947999892036352 
Step 3217 | loss:1.9695582389831543 lr:5.9016115756371026e-05 tokens_per_second_per_gpu:895.3592045833449 mfu:13.157048402852732 
Step 3218 | loss:1.9679768085479736 lr:5.8958719454724346e-05 tokens_per_second_per_gpu:867.3620258104921 mfu:12.745637837827982 
Step 3219 | loss:2.0473525524139404 lr:5.890133940749776e-05 tokens_per_second_per_gpu:823.3778309047083 mfu:12.099302625799636 
Step 3220 | loss:1.9706523418426514 lr:5.884397563741673e-05 tokens_per_second_per_gpu:888.0172358348599 mfu:13.049160263990071 
Step 3221 | loss:2.048102378845215 lr:5.878662816720015e-05 tokens_per_second_per_gpu:878.183685323027 mfu:12.904659041024155 
Step 3222 | loss:2.01058030128479 lr:5.872929701956054e-05 tokens_per_second_per_gpu:852.9957483609005 mfu:12.534529483990209 
Step 3223 | loss:2.0000674724578857 lr:5.8671982217203914e-05 tokens_per_second_per_gpu:875.0752162714386 mfu:12.85898097398563 
Step 3224 | loss:1.9970293045043945 lr:5.8614683782829835e-05 tokens_per_second_per_gpu:875.2748591268942 mfu:12.861914668863694 
Step 3225 | loss:2.029801607131958 lr:5.8557401739131425e-05 tokens_per_second_per_gpu:904.3718448970279 mfu:13.289486584353094 
Step 3226 | loss:2.0083158016204834 lr:5.85001361087952e-05 tokens_per_second_per_gpu:868.1283992616081 mfu:12.756899477334649 
Step 3227 | loss:2.029470682144165 lr:5.844288691450124e-05 tokens_per_second_per_gpu:875.4629846681247 mfu:12.86467912009077 
Step 3228 | loss:2.042092800140381 lr:5.838565417892317e-05 tokens_per_second_per_gpu:880.2340208004581 mfu:12.934788136677112 
Step 3229 | loss:2.0124526023864746 lr:5.8328437924728044e-05 tokens_per_second_per_gpu:869.5285407062302 mfu:12.777474156930761 
Step 3230 | loss:2.0481059551239014 lr:5.8271238174576305e-05 tokens_per_second_per_gpu:844.9533678034179 mfu:12.416348993157815 
Step 3231 | loss:2.0381343364715576 lr:5.8214054951122e-05 tokens_per_second_per_gpu:900.4441005164574 mfu:13.231769499785624 
Step 3232 | loss:2.0109028816223145 lr:5.8156888277012624e-05 tokens_per_second_per_gpu:877.3742052138354 mfu:12.892763961459147 
Step 3233 | loss:1.9953815937042236 lr:5.8099738174888986e-05 tokens_per_second_per_gpu:877.4303681787233 mfu:12.893589260226051 
Step 3234 | loss:2.0717146396636963 lr:5.804260466738547e-05 tokens_per_second_per_gpu:873.0372455294123 mfu:12.82903357459645 
Step 3235 | loss:1.9693431854248047 lr:5.7985487777129765e-05 tokens_per_second_per_gpu:849.2098715772119 mfu:12.478897103337566 
Step 3236 | loss:1.9813138246536255 lr:5.792838752674309e-05 tokens_per_second_per_gpu:875.9011082011269 mfu:12.87111722057673 
Step 3237 | loss:2.036818504333496 lr:5.787130393884006e-05 tokens_per_second_per_gpu:880.5371789173782 mfu:12.939242958828512 
Step 3238 | loss:2.0389468669891357 lr:5.781423703602863e-05 tokens_per_second_per_gpu:860.2798491492196 mfu:12.641567269666147 
Step 3239 | loss:1.9747841358184814 lr:5.775718684091012e-05 tokens_per_second_per_gpu:853.3603065390214 mfu:12.539886562546657 
Step 3240 | loss:2.026237726211548 lr:5.770015337607935e-05 tokens_per_second_per_gpu:876.5863359779171 mfu:12.881186447519458 
Step 3241 | loss:2.0060625076293945 lr:5.7643136664124465e-05 tokens_per_second_per_gpu:857.7529603795689 mfu:12.604435359165054 
Step 3242 | loss:1.972649097442627 lr:5.75861367276269e-05 tokens_per_second_per_gpu:852.1272846186985 mfu:12.52176765674391 
Step 3243 | loss:1.979533314704895 lr:5.7529153589161555e-05 tokens_per_second_per_gpu:875.3138647928232 mfu:12.862487846010907 
Step 3244 | loss:1.9990112781524658 lr:5.747218727129666e-05 tokens_per_second_per_gpu:894.0216924731503 mfu:13.137394043481489 
Step 3245 | loss:2.0268869400024414 lr:5.741523779659372e-05 tokens_per_second_per_gpu:852.4003651310081 mfu:12.52578049706536 
Step 3246 | loss:1.9912523031234741 lr:5.735830518760756e-05 tokens_per_second_per_gpu:877.8006316132146 mfu:12.899030175899304 
Step 3247 | loss:1.987899899482727 lr:5.7301389466886414e-05 tokens_per_second_per_gpu:832.6957933570021 mfu:12.236227429133562 
Step 3248 | loss:1.9790794849395752 lr:5.7244490656971815e-05 tokens_per_second_per_gpu:865.3760605165902 mfu:12.716454643681434 
Step 3249 | loss:2.006772041320801 lr:5.718760878039848e-05 tokens_per_second_per_gpu:879.8312965649619 mfu:12.928870218781924 
Step 3250 | loss:1.9846028089523315 lr:5.713074385969457e-05 tokens_per_second_per_gpu:882.1841790519736 mfu:12.963445156538043 
Step 3251 | loss:1.9693059921264648 lr:5.707389591738148e-05 tokens_per_second_per_gpu:883.2417098758641 mfu:12.978985270680178 
Step 3252 | loss:1.995603322982788 lr:5.701706497597381e-05 tokens_per_second_per_gpu:873.7366478831591 mfu:12.839311092908888 
Step 3253 | loss:1.99680495262146 lr:5.696025105797953e-05 tokens_per_second_per_gpu:899.2014201006373 mfu:13.213508665143475 
Step 3254 | loss:1.9921401739120483 lr:5.6903454185899774e-05 tokens_per_second_per_gpu:866.6513216621544 mfu:12.735194242864171 
Step 3255 | loss:2.0453176498413086 lr:5.684667438222899e-05 tokens_per_second_per_gpu:903.8700968415193 mfu:13.282113539636995 
Step 3256 | loss:2.034672737121582 lr:5.678991166945491e-05 tokens_per_second_per_gpu:862.9159168333916 mfu:12.68030353320854 
Step 3257 | loss:1.9695684909820557 lr:5.673316607005839e-05 tokens_per_second_per_gpu:881.6453342476175 mfu:12.955526985667351 
Step 3258 | loss:2.0180060863494873 lr:5.667643760651349e-05 tokens_per_second_per_gpu:869.2767966417263 mfu:12.77377484963057 
Step 3259 | loss:1.9701377153396606 lr:5.66197263012876e-05 tokens_per_second_per_gpu:849.514859231943 mfu:12.483378810025817 
Step 3260 | loss:1.977962851524353 lr:5.6563032176841324e-05 tokens_per_second_per_gpu:836.6848064334457 mfu:12.29484483973002 
Step 3261 | loss:2.02122163772583 lr:5.6506355255628284e-05 tokens_per_second_per_gpu:866.0359641258045 mfu:12.726151739197071 
Step 3262 | loss:1.982903242111206 lr:5.644969556009547e-05 tokens_per_second_per_gpu:889.9411940382762 mfu:13.077432281609182 
Step 3263 | loss:2.0020694732666016 lr:5.6393053112683014e-05 tokens_per_second_per_gpu:882.2342599927526 mfu:12.964181081693575 
Step 3264 | loss:1.982553482055664 lr:5.6336427935824144e-05 tokens_per_second_per_gpu:884.2312592421385 mfu:12.99352641667213 
Step 3265 | loss:2.016514301300049 lr:5.627982005194524e-05 tokens_per_second_per_gpu:889.6812288682888 mfu:13.073612167506296 
Step 3266 | loss:2.0334320068359375 lr:5.622322948346594e-05 tokens_per_second_per_gpu:893.4383759010801 mfu:13.12882237265527 
Step 3267 | loss:1.96938955783844 lr:5.616665625279901e-05 tokens_per_second_per_gpu:877.2796014083586 mfu:12.891373785492474 
Step 3268 | loss:1.9859585762023926 lr:5.6110100382350215e-05 tokens_per_second_per_gpu:879.4959297620231 mfu:12.923942099166482 
Step 3269 | loss:2.028935670852661 lr:5.6053561894518625e-05 tokens_per_second_per_gpu:853.5979771075132 mfu:12.543379063832814 
Step 3270 | loss:1.9832514524459839 lr:5.599704081169625e-05 tokens_per_second_per_gpu:864.9382991647292 mfu:12.71002186534415 
Step 3271 | loss:2.0010735988616943 lr:5.594053715626833e-05 tokens_per_second_per_gpu:885.6948046795259 mfu:13.015032799876668 
Step 3272 | loss:2.0200119018554688 lr:5.588405095061322e-05 tokens_per_second_per_gpu:887.5853232809563 mfu:13.042813432072313 
Step 3273 | loss:1.9838815927505493 lr:5.582758221710227e-05 tokens_per_second_per_gpu:851.2356896277433 mfu:12.508665922387813 
Step 3274 | loss:2.0156619548797607 lr:5.577113097809989e-05 tokens_per_second_per_gpu:859.5417226316129 mfu:12.630720710799196 
Step 3275 | loss:1.965041160583496 lr:5.5714697255963676e-05 tokens_per_second_per_gpu:887.8920468785099 mfu:13.04732064794573 
Step 3276 | loss:2.028214693069458 lr:5.565828107304428e-05 tokens_per_second_per_gpu:860.8790255244484 mfu:12.650371995780958 
Step 3277 | loss:2.042066812515259 lr:5.560188245168527e-05 tokens_per_second_per_gpu:837.1319799374467 mfu:12.301415926961264 
Step 3278 | loss:2.0094821453094482 lr:5.55455014142234e-05 tokens_per_second_per_gpu:859.1214451977424 mfu:12.624544853655209 
Step 3279 | loss:1.997446060180664 lr:5.5489137982988435e-05 tokens_per_second_per_gpu:882.1075696192424 mfu:12.962319402751854 
Step 3280 | loss:1.974898338317871 lr:5.5432792180303106e-05 tokens_per_second_per_gpu:872.1315718906582 mfu:12.815724958522278 
Step 3281 | loss:2.029214859008789 lr:5.537646402848315e-05 tokens_per_second_per_gpu:888.2460349986445 mfu:13.052522402511725 
Step 3282 | loss:1.946167230606079 lr:5.5320153549837415e-05 tokens_per_second_per_gpu:847.5497889496089 mfu:12.45450266212079 
Step 3283 | loss:1.947791576385498 lr:5.5263860766667744e-05 tokens_per_second_per_gpu:888.8419321795533 mfu:13.061278941800321 
Step 3284 | loss:1.9459874629974365 lr:5.5207585701268805e-05 tokens_per_second_per_gpu:896.947541562792 mfu:13.180388562211848 
Step 3285 | loss:1.992325782775879 lr:5.515132837592847e-05 tokens_per_second_per_gpu:890.6232939771052 mfu:13.08745554586426 
Step 3286 | loss:1.9930930137634277 lr:5.50950888129274e-05 tokens_per_second_per_gpu:883.7322238367194 mfu:12.9861932335762 
Step 3287 | loss:2.0130956172943115 lr:5.503886703453933e-05 tokens_per_second_per_gpu:884.7240028577046 mfu:13.000767143708847 
Step 3288 | loss:1.993127465248108 lr:5.498266306303099e-05 tokens_per_second_per_gpu:875.9096319512736 mfu:12.871242474656523 
Step 3289 | loss:2.016714572906494 lr:5.492647692066189e-05 tokens_per_second_per_gpu:848.3573397370412 mfu:12.466369390852254 
Step 3290 | loss:1.9862034320831299 lr:5.4870308629684677e-05 tokens_per_second_per_gpu:876.1122309877111 mfu:12.874219609771831 
Step 3291 | loss:2.0023162364959717 lr:5.481415821234472e-05 tokens_per_second_per_gpu:877.1152035475257 mfu:12.888958005768279 
Step 3292 | loss:2.003890037536621 lr:5.475802569088054e-05 tokens_per_second_per_gpu:891.9641713318148 mfu:13.107159356544818 
Step 3293 | loss:1.9851056337356567 lr:5.470191108752336e-05 tokens_per_second_per_gpu:874.1638691087464 mfu:12.845588987093707 
Step 3294 | loss:1.944966197013855 lr:5.464581442449741e-05 tokens_per_second_per_gpu:866.7137921812721 mfu:12.736112229343314 
Step 3295 | loss:1.97153639793396 lr:5.4589735724019876e-05 tokens_per_second_per_gpu:887.9856919352984 mfu:13.048696735373602 
Step 3296 | loss:1.9830944538116455 lr:5.453367500830069e-05 tokens_per_second_per_gpu:876.0540797713887 mfu:12.873365094216597 
Step 3297 | loss:2.012661933898926 lr:5.447763229954268e-05 tokens_per_second_per_gpu:866.27475701037 mfu:12.729660732598159 
Step 3298 | loss:1.924145221710205 lr:5.4421607619941706e-05 tokens_per_second_per_gpu:869.9411770762907 mfu:12.783537730819178 
Step 3299 | loss:2.033622980117798 lr:5.436560099168633e-05 tokens_per_second_per_gpu:868.191922598907 mfu:12.757832934676992 
Step 3300 | loss:2.015395164489746 lr:5.4309612436957937e-05 tokens_per_second_per_gpu:889.0815413322564 mfu:13.064799930029116 
Step 3301 | loss:1.9600450992584229 lr:5.425364197793088e-05 tokens_per_second_per_gpu:877.3059749497228 mfu:12.891761337168392 
Step 3302 | loss:2.020681858062744 lr:5.4197689636772334e-05 tokens_per_second_per_gpu:876.3124612197394 mfu:12.877161935981272 
Step 3303 | loss:2.012075901031494 lr:5.414175543564215e-05 tokens_per_second_per_gpu:887.9040641374238 mfu:13.047497238141476 
Step 3304 | loss:1.964104175567627 lr:5.4085839396693186e-05 tokens_per_second_per_gpu:891.9054384081682 mfu:13.106296292966196 
Step 3305 | loss:1.9781901836395264 lr:5.402994154207095e-05 tokens_per_second_per_gpu:855.6301448713499 mfu:12.573241190110902 
Step 3306 | loss:1.9918384552001953 lr:5.397406189391387e-05 tokens_per_second_per_gpu:884.0024523771212 mfu:12.990164164983058 
Step 3307 | loss:1.9899909496307373 lr:5.3918200474353055e-05 tokens_per_second_per_gpu:880.6289903616381 mfu:12.94059210184271 
Step 3308 | loss:2.0119423866271973 lr:5.386235730551252e-05 tokens_per_second_per_gpu:882.0722093572523 mfu:12.961799793776864 
Step 3309 | loss:2.0075156688690186 lr:5.38065324095089e-05 tokens_per_second_per_gpu:860.4006756417049 mfu:12.643342780546963 
Step 3310 | loss:2.028228521347046 lr:5.375072580845171e-05 tokens_per_second_per_gpu:886.8562084916903 mfu:13.032099297985676 
Step 3311 | loss:1.9873919486999512 lr:5.3694937524443235e-05 tokens_per_second_per_gpu:880.719970926735 mfu:12.941929035324346 
Step 3312 | loss:2.0259456634521484 lr:5.363916757957839e-05 tokens_per_second_per_gpu:859.1610864797352 mfu:12.625127370999376 
Step 3313 | loss:2.0128345489501953 lr:5.358341599594483e-05 tokens_per_second_per_gpu:867.810680430915 mfu:12.75223068964304 
Step 3314 | loss:1.9306670427322388 lr:5.3527682795623146e-05 tokens_per_second_per_gpu:847.782716587534 mfu:12.45792546739364 
Step 3315 | loss:2.0096545219421387 lr:5.3471968000686434e-05 tokens_per_second_per_gpu:876.2389801722026 mfu:12.876082152924166 
Step 3316 | loss:2.0160329341888428 lr:5.341627163320053e-05 tokens_per_second_per_gpu:845.1357912902596 mfu:12.419029654320292 
Step 3317 | loss:1.964956521987915 lr:5.3360593715224015e-05 tokens_per_second_per_gpu:879.4520710038821 mfu:12.923297607211971 
Step 3318 | loss:2.041187286376953 lr:5.330493426880825e-05 tokens_per_second_per_gpu:866.0562724170973 mfu:12.726450163751318 
Step 3319 | loss:1.9964642524719238 lr:5.3249293315997065e-05 tokens_per_second_per_gpu:839.1012763824725 mfu:12.330354177122917 
Step 3320 | loss:2.0190083980560303 lr:5.319367087882716e-05 tokens_per_second_per_gpu:884.9661789826772 mfu:13.004325852863753 
Step 3321 | loss:1.9588053226470947 lr:5.31380669793278e-05 tokens_per_second_per_gpu:875.3592449542181 mfu:12.863154694552748 
Step 3322 | loss:2.0330286026000977 lr:5.308248163952096e-05 tokens_per_second_per_gpu:888.7076220842484 mfu:13.059305293217863 
Step 3323 | loss:1.994697093963623 lr:5.302691488142122e-05 tokens_per_second_per_gpu:849.3551271187948 mfu:12.481031592134471 
Step 3324 | loss:1.9871935844421387 lr:5.2971366727035856e-05 tokens_per_second_per_gpu:880.2555875531966 mfu:12.93510505396374 
Step 3325 | loss:1.9988415241241455 lr:5.291583719836468e-05 tokens_per_second_per_gpu:899.9916970787104 mfu:13.225121560168114 
Step 3326 | loss:2.0005862712860107 lr:5.286032631740023e-05 tokens_per_second_per_gpu:862.2185290955389 mfu:12.670055619102653 
Step 3327 | loss:1.9430711269378662 lr:5.2804834106127664e-05 tokens_per_second_per_gpu:891.1030133808956 mfu:13.094504885819834 
Step 3328 | loss:1.9825878143310547 lr:5.274936058652462e-05 tokens_per_second_per_gpu:865.250029789848 mfu:12.71460265806102 
Step 3329 | loss:1.9972243309020996 lr:5.2693905780561434e-05 tokens_per_second_per_gpu:877.600795174114 mfu:12.896093636364734 
Step 3330 | loss:2.035654067993164 lr:5.263846971020108e-05 tokens_per_second_per_gpu:861.0241314175717 mfu:12.652504285536386 
Step 3331 | loss:1.971904993057251 lr:5.258305239739898e-05 tokens_per_second_per_gpu:857.0654906986986 mfu:12.594333188080642 
Step 3332 | loss:1.9655635356903076 lr:5.252765386410312e-05 tokens_per_second_per_gpu:878.7943753485034 mfu:12.91363295694885 
Step 3333 | loss:1.9498518705368042 lr:5.2472274132254286e-05 tokens_per_second_per_gpu:859.7836937803055 mfu:12.63427640788607 
Step 3334 | loss:1.977968692779541 lr:5.2416913223785534e-05 tokens_per_second_per_gpu:861.3794509483173 mfu:12.65772560480196 
Step 3335 | loss:1.9926190376281738 lr:5.236157116062257e-05 tokens_per_second_per_gpu:903.2979834677334 mfu:13.273706496617514 
Step 3336 | loss:2.0067389011383057 lr:5.230624796468369e-05 tokens_per_second_per_gpu:880.5575870000449 mfu:12.939542849788564 
Step 3337 | loss:2.0076379776000977 lr:5.225094365787969e-05 tokens_per_second_per_gpu:884.941085800975 mfu:13.003957115708264 
Step 3338 | loss:2.010221481323242 lr:5.2195658262113814e-05 tokens_per_second_per_gpu:875.619693392067 mfu:12.866981910139168 
Step 3339 | loss:1.9741935729980469 lr:5.214039179928194e-05 tokens_per_second_per_gpu:871.5359425701101 mfu:12.806972355365362 
Step 3340 | loss:2.0231223106384277 lr:5.208514429127229e-05 tokens_per_second_per_gpu:864.4951165402274 mfu:12.70350942295005 
Step 3341 | loss:2.0001718997955322 lr:5.202991575996576e-05 tokens_per_second_per_gpu:886.3523100690212 mfu:13.024694654236844 
Step 3342 | loss:1.9897003173828125 lr:5.197470622723555e-05 tokens_per_second_per_gpu:851.5236366926333 mfu:12.512897222463607 
Step 3343 | loss:1.9987062215805054 lr:5.191951571494751e-05 tokens_per_second_per_gpu:864.5948570375866 mfu:12.704975081140377 
Step 3344 | loss:1.9747593402862549 lr:5.186434424495979e-05 tokens_per_second_per_gpu:878.7066294666166 mfu:12.912343556215351 
Step 3345 | loss:1.959938645362854 lr:5.180919183912313e-05 tokens_per_second_per_gpu:875.253149410487 mfu:12.861595650766692 
Step 3346 | loss:2.007556200027466 lr:5.175405851928068e-05 tokens_per_second_per_gpu:822.30098215528 mfu:12.083478640245847 
Step 3347 | loss:2.015512466430664 lr:5.1698944307268006e-05 tokens_per_second_per_gpu:857.6279048617976 mfu:12.602597703962607 
Step 3348 | loss:2.0097744464874268 lr:5.164384922491302e-05 tokens_per_second_per_gpu:870.6344197359263 mfu:12.79372473418169 
Step 3349 | loss:2.01383638381958 lr:5.158877329403633e-05 tokens_per_second_per_gpu:886.7921287507268 mfu:13.031157664450014 
Step 3350 | loss:1.9722480773925781 lr:5.1533716536450693e-05 tokens_per_second_per_gpu:880.2489238188612 mfu:12.935007132286332 
Step 3351 | loss:1.9709458351135254 lr:5.147867897396136e-05 tokens_per_second_per_gpu:872.3003412741791 mfu:12.818204976526825 
Step 3352 | loss:1.9981887340545654 lr:5.142366062836599e-05 tokens_per_second_per_gpu:885.7180488088424 mfu:13.015374365734186 
Step 3353 | loss:2.0177760124206543 lr:5.136866152145467e-05 tokens_per_second_per_gpu:881.0009680828548 mfu:12.946058208470953 
Step 3354 | loss:2.0010671615600586 lr:5.131368167500976e-05 tokens_per_second_per_gpu:863.7608825247477 mfu:12.692720063292791 
Step 3355 | loss:1.9631139039993286 lr:5.125872111080614e-05 tokens_per_second_per_gpu:852.3905603964107 mfu:12.525636419284046 
Step 3356 | loss:1.9931843280792236 lr:5.1203779850610864e-05 tokens_per_second_per_gpu:877.115999458144 mfu:12.888969701448042 
Step 3357 | loss:2.0213534832000732 lr:5.1148857916183555e-05 tokens_per_second_per_gpu:888.6397990194896 mfu:13.058308652605586 
Step 3358 | loss:2.0241141319274902 lr:5.109395532927597e-05 tokens_per_second_per_gpu:865.8972170236409 mfu:12.72411289006303 
Step 3359 | loss:1.9383593797683716 lr:5.103907211163239e-05 tokens_per_second_per_gpu:864.3678656719931 mfu:12.701639507698058 
Step 3360 | loss:2.0266125202178955 lr:5.098420828498929e-05 tokens_per_second_per_gpu:868.5766538764868 mfu:12.763486451182208 
Step 3361 | loss:2.0350472927093506 lr:5.092936387107551e-05 tokens_per_second_per_gpu:893.0722314453493 mfu:13.123441984201309 
Step 3362 | loss:1.9941530227661133 lr:5.087453889161229e-05 tokens_per_second_per_gpu:876.2469859995228 mfu:12.876199796275593 
Step 3363 | loss:2.0837981700897217 lr:5.081973336831301e-05 tokens_per_second_per_gpu:860.1109405430617 mfu:12.639085205824617 
Step 3364 | loss:1.97196364402771 lr:5.07649473228834e-05 tokens_per_second_per_gpu:882.0714569418222 mfu:12.9617887372465 
Step 3365 | loss:1.9908554553985596 lr:5.071018077702161e-05 tokens_per_second_per_gpu:879.3257548413973 mfu:12.921441427194646 
Step 3366 | loss:1.9828076362609863 lr:5.06554337524179e-05 tokens_per_second_per_gpu:870.5603443795261 mfu:12.792636217925168 
Step 3367 | loss:2.02646541595459 lr:5.0600706270754815e-05 tokens_per_second_per_gpu:864.1058985966163 mfu:12.697789976165861 
Step 3368 | loss:1.995049238204956 lr:5.054599835370724e-05 tokens_per_second_per_gpu:892.2651968600503 mfu:13.111582840913119 
Step 3369 | loss:1.9154822826385498 lr:5.049131002294232e-05 tokens_per_second_per_gpu:865.5364474085878 mfu:12.718811483361414 
Step 3370 | loss:2.0208346843719482 lr:5.0436641300119314e-05 tokens_per_second_per_gpu:887.6633690103042 mfu:13.04396029182805 
Step 3371 | loss:2.018494129180908 lr:5.038199220688984e-05 tokens_per_second_per_gpu:855.2984960827505 mfu:12.568367705656827 
Step 3372 | loss:2.0084726810455322 lr:5.032736276489773e-05 tokens_per_second_per_gpu:877.0717020744446 mfu:12.888318764015926 
Step 3373 | loss:1.9815208911895752 lr:5.027275299577897e-05 tokens_per_second_per_gpu:878.3179326944444 mfu:12.90663176789696 
Step 3374 | loss:2.003200054168701 lr:5.021816292116175e-05 tokens_per_second_per_gpu:862.4439221770787 mfu:12.67336770621619 
Step 3375 | loss:2.022986650466919 lr:5.016359256266652e-05 tokens_per_second_per_gpu:873.13700529641 mfu:12.830499515948622 
Step 3376 | loss:2.0124964714050293 lr:5.010904194190595e-05 tokens_per_second_per_gpu:869.2167349251191 mfu:12.772892259817997 
Step 3377 | loss:1.962428331375122 lr:5.0054511080484776e-05 tokens_per_second_per_gpu:900.0136920026791 mfu:13.225444769308972 
Step 3378 | loss:1.9953231811523438 lr:5.000000000000002e-05 tokens_per_second_per_gpu:896.2738258437219 mfu:13.170488501677267 
Step 3379 | loss:2.026108503341675 lr:4.994550872204078e-05 tokens_per_second_per_gpu:837.2266947687759 mfu:12.302807734421206 
Step 3380 | loss:1.9940460920333862 lr:4.989103726818836e-05 tokens_per_second_per_gpu:889.204638249243 mfu:13.066608804151082 
Step 3381 | loss:2.0180509090423584 lr:4.9836585660016274e-05 tokens_per_second_per_gpu:883.7426545299196 mfu:12.986346509640832 
Step 3382 | loss:2.0079667568206787 lr:4.978215391909006e-05 tokens_per_second_per_gpu:858.1106006843283 mfu:12.609690781543518 
Step 3383 | loss:2.0349488258361816 lr:4.9727742066967383e-05 tokens_per_second_per_gpu:866.0205898330629 mfu:12.725925818345726 
Step 3384 | loss:1.996656894683838 lr:4.9673350125198145e-05 tokens_per_second_per_gpu:890.5237313354473 mfu:13.085992501212793 
Step 3385 | loss:1.94720458984375 lr:4.9618978115324336e-05 tokens_per_second_per_gpu:892.2666152115856 mfu:13.111603683184809 
Step 3386 | loss:1.9933245182037354 lr:4.956462605887994e-05 tokens_per_second_per_gpu:846.1335869858787 mfu:12.433691977772394 
Step 3387 | loss:1.991887092590332 lr:4.9510293977391155e-05 tokens_per_second_per_gpu:861.7051993709482 mfu:12.662512385059278 
Step 3388 | loss:1.9906584024429321 lr:4.945598189237626e-05 tokens_per_second_per_gpu:868.8037436508095 mfu:12.766823470712762 
Step 3389 | loss:2.0472490787506104 lr:4.940168982534555e-05 tokens_per_second_per_gpu:869.4191921635361 mfu:12.775867311251796 
Step 3390 | loss:2.0225698947906494 lr:4.93474177978014e-05 tokens_per_second_per_gpu:889.5841540544798 mfu:13.072185680776224 
Step 3391 | loss:2.007662773132324 lr:4.92931658312383e-05 tokens_per_second_per_gpu:882.7583203459035 mfu:12.97188199926624 
Step 3392 | loss:2.0089619159698486 lr:4.923893394714279e-05 tokens_per_second_per_gpu:833.5785723992016 mfu:12.249199615634563 
Step 3393 | loss:2.011744976043701 lr:4.91847221669934e-05 tokens_per_second_per_gpu:814.8177861342397 mfu:11.973515206851895 
Step 3394 | loss:1.9818183183670044 lr:4.913053051226079e-05 tokens_per_second_per_gpu:884.6014676954248 mfu:12.998966524412243 
Step 3395 | loss:1.9996949434280396 lr:4.90763590044075e-05 tokens_per_second_per_gpu:878.6472274754336 mfu:12.911470660879916 
Step 3396 | loss:2.004319906234741 lr:4.9022207664888255e-05 tokens_per_second_per_gpu:893.7866538691069 mfu:13.133940218162993 
Step 3397 | loss:2.014826774597168 lr:4.896807651514973e-05 tokens_per_second_per_gpu:878.3278986029362 mfu:12.906778214082731 
Step 3398 | loss:1.9788432121276855 lr:4.891396557663056e-05 tokens_per_second_per_gpu:874.1024994561806 mfu:12.844687177534883 
Step 3399 | loss:1.9873219728469849 lr:4.885987487076135e-05 tokens_per_second_per_gpu:883.144481609398 mfu:12.977556529007035 
Step 3400 | loss:2.0098633766174316 lr:4.880580441896488e-05 tokens_per_second_per_gpu:897.8519832288376 mfu:13.193679074798087 
Step 3401 | loss:1.9716639518737793 lr:4.875175424265573e-05 tokens_per_second_per_gpu:893.3748080530033 mfu:13.127888261239727 
Step 3402 | loss:1.938476800918579 lr:4.869772436324045e-05 tokens_per_second_per_gpu:859.44402351591 mfu:12.629285050130672 
Step 3403 | loss:1.991715908050537 lr:4.864371480211764e-05 tokens_per_second_per_gpu:871.0560072091548 mfu:12.799919841980783 
Step 3404 | loss:1.9938125610351562 lr:4.8589725580677835e-05 tokens_per_second_per_gpu:857.645808016602 mfu:12.602860785721436 
Step 3405 | loss:1.9548218250274658 lr:4.853575672030349e-05 tokens_per_second_per_gpu:869.1986967295877 mfu:12.772627193674161 
Step 3406 | loss:1.9956415891647339 lr:4.84818082423689e-05 tokens_per_second_per_gpu:900.9135016994819 mfu:13.23866721642694 
Step 3407 | loss:1.9826728105545044 lr:4.8427880168240547e-05 tokens_per_second_per_gpu:906.0242932108312 mfu:13.313768841503776 
Step 3408 | loss:1.9459024667739868 lr:4.837397251927659e-05 tokens_per_second_per_gpu:882.8089827695045 mfu:12.972626469146162 
Step 3409 | loss:1.974942922592163 lr:4.832008531682715e-05 tokens_per_second_per_gpu:866.3692852413453 mfu:12.731049798019066 
Step 3410 | loss:1.9714164733886719 lr:4.826621858223431e-05 tokens_per_second_per_gpu:880.3640201949084 mfu:12.936698440738734 
Step 3411 | loss:1.957694411277771 lr:4.8212372336832067e-05 tokens_per_second_per_gpu:878.1793631765968 mfu:12.904595528313843 
Step 3412 | loss:2.01088809967041 lr:4.8158546601946175e-05 tokens_per_second_per_gpu:880.0610771126765 mfu:12.93224677846081 
Step 3413 | loss:1.9512312412261963 lr:4.810474139889442e-05 tokens_per_second_per_gpu:860.6678501581885 mfu:12.647268833942503 
Step 3414 | loss:2.0493361949920654 lr:4.80509567489863e-05 tokens_per_second_per_gpu:884.3999356923348 mfu:12.996005069047952 
Step 3415 | loss:2.0635902881622314 lr:4.7997192673523296e-05 tokens_per_second_per_gpu:859.0414583921364 mfu:12.623369470336915 
Step 3416 | loss:1.9793171882629395 lr:4.794344919379872e-05 tokens_per_second_per_gpu:871.9706420371205 mfu:12.81336014017717 
Step 3417 | loss:2.013637065887451 lr:4.7889726331097686e-05 tokens_per_second_per_gpu:855.6026539528748 mfu:12.572837218896707 
Step 3418 | loss:1.9978125095367432 lr:4.783602410669712e-05 tokens_per_second_per_gpu:866.2602295309844 mfu:12.729447255427802 
Step 3419 | loss:1.9941506385803223 lr:4.778234254186584e-05 tokens_per_second_per_gpu:860.3321997531349 mfu:12.642336546874787 
Step 3420 | loss:1.9616605043411255 lr:4.7728681657864514e-05 tokens_per_second_per_gpu:894.2902964845695 mfu:13.141341102897812 
Step 3421 | loss:1.9638583660125732 lr:4.767504147594548e-05 tokens_per_second_per_gpu:876.330002033035 mfu:12.87741969323487 
Step 3422 | loss:1.9912993907928467 lr:4.762142201735299e-05 tokens_per_second_per_gpu:866.5826317253735 mfu:12.734184863814525 
Step 3423 | loss:2.0239109992980957 lr:4.75678233033231e-05 tokens_per_second_per_gpu:858.8787538144734 mfu:12.620978572926445 
Step 3424 | loss:1.9800314903259277 lr:4.7514245355083574e-05 tokens_per_second_per_gpu:870.2218534004076 mfu:12.787662189430911 
Step 3425 | loss:1.9787969589233398 lr:4.7460688193853944e-05 tokens_per_second_per_gpu:875.1818377786261 mfu:12.860547746654824 
Step 3426 | loss:1.9451311826705933 lr:4.740715184084559e-05 tokens_per_second_per_gpu:873.0003101641429 mfu:12.828490819927552 
Step 3427 | loss:1.9544073343276978 lr:4.735363631726165e-05 tokens_per_second_per_gpu:851.0857058163892 mfu:12.506461953013813 
Step 3428 | loss:2.0424795150756836 lr:4.730014164429689e-05 tokens_per_second_per_gpu:852.6598656332875 mfu:12.529593783008675 
Step 3429 | loss:1.9817724227905273 lr:4.724666784313799e-05 tokens_per_second_per_gpu:868.430806072479 mfu:12.761343259257718 
Step 3430 | loss:1.939615249633789 lr:4.7193214934963206e-05 tokens_per_second_per_gpu:882.0146942531412 mfu:12.960954625709332 
Step 3431 | loss:2.0255699157714844 lr:4.713978294094261e-05 tokens_per_second_per_gpu:865.6500748089874 mfu:12.720481205635217 
Step 3432 | loss:2.013115406036377 lr:4.7086371882238026e-05 tokens_per_second_per_gpu:862.3420229127552 mfu:12.671870325560409 
Step 3433 | loss:2.04870867729187 lr:4.703298178000287e-05 tokens_per_second_per_gpu:874.5801585319289 mfu:12.85170624155691 
Step 3434 | loss:2.0187623500823975 lr:4.697961265538231e-05 tokens_per_second_per_gpu:899.5145602324341 mfu:13.21811017015938 
Step 3435 | loss:2.0021612644195557 lr:4.692626452951323e-05 tokens_per_second_per_gpu:881.0165567163913 mfu:12.94628727899921 
Step 3436 | loss:2.015434503555298 lr:4.687293742352423e-05 tokens_per_second_per_gpu:874.5206631786906 mfu:12.850831974292673 
Step 3437 | loss:1.9985504150390625 lr:4.6819631358535467e-05 tokens_per_second_per_gpu:850.40555046551 mfu:12.496467263924599 
Step 3438 | loss:2.0009512901306152 lr:4.6766346355658854e-05 tokens_per_second_per_gpu:894.7736392065825 mfu:13.148443686482299 
Step 3439 | loss:2.031137466430664 lr:4.6713082435998e-05 tokens_per_second_per_gpu:891.5214253379853 mfu:13.100653330314044 
Step 3440 | loss:1.974364995956421 lr:4.6659839620648074e-05 tokens_per_second_per_gpu:890.6685992974093 mfu:13.088121294637599 
Step 3441 | loss:1.9997789859771729 lr:4.6606617930695864e-05 tokens_per_second_per_gpu:887.5090722934185 mfu:13.041692945536111 
Step 3442 | loss:1.9921668767929077 lr:4.6553417387219886e-05 tokens_per_second_per_gpu:868.5448161516713 mfu:12.763018604887346 
Step 3443 | loss:2.005244255065918 lr:4.6500238011290295e-05 tokens_per_second_per_gpu:861.624369952488 mfu:12.661324619785173 
Step 3444 | loss:2.007880210876465 lr:4.644707982396873e-05 tokens_per_second_per_gpu:867.8174691489256 mfu:12.752330447919944 
Step 3445 | loss:1.956621766090393 lr:4.6393942846308556e-05 tokens_per_second_per_gpu:883.670790120448 mfu:12.985290482619476 
Step 3446 | loss:1.9621533155441284 lr:4.634082709935473e-05 tokens_per_second_per_gpu:878.3461745441693 mfu:12.907046773831913 
Step 3447 | loss:1.9483603239059448 lr:4.6287732604143697e-05 tokens_per_second_per_gpu:883.7903993314621 mfu:12.987048105895903 
Step 3448 | loss:1.9902012348175049 lr:4.623465938170365e-05 tokens_per_second_per_gpu:891.553870518083 mfu:13.1011301029912 
Step 3449 | loss:1.9922122955322266 lr:4.6181607453054163e-05 tokens_per_second_per_gpu:884.2684881873403 mfu:12.994073485414484 
Step 3450 | loss:2.0058135986328125 lr:4.6128576839206585e-05 tokens_per_second_per_gpu:900.966344300556 mfu:13.239443723393647 
Step 3451 | loss:1.9581255912780762 lr:4.607556756116361e-05 tokens_per_second_per_gpu:875.7193426380811 mfu:12.868446227416976 
Step 3452 | loss:1.9868943691253662 lr:4.6022579639919695e-05 tokens_per_second_per_gpu:843.8813634914208 mfu:12.400596195231783 
Step 3453 | loss:2.035447120666504 lr:4.596961309646064e-05 tokens_per_second_per_gpu:855.4054180179216 mfu:12.569938893029642 
Step 3454 | loss:2.0235931873321533 lr:4.5916667951763926e-05 tokens_per_second_per_gpu:844.99498624594 mfu:12.416960564312623 
Step 3455 | loss:2.0279650688171387 lr:4.586374422679852e-05 tokens_per_second_per_gpu:858.5690049821271 mfu:12.616426902089708 
Step 3456 | loss:2.0096282958984375 lr:4.5810841942524864e-05 tokens_per_second_per_gpu:886.0099218476911 mfu:13.019663356878704 
Step 3457 | loss:1.9935526847839355 lr:4.575796111989486e-05 tokens_per_second_per_gpu:866.5398067821378 mfu:12.733555563475491 
Step 3458 | loss:1.917607069015503 lr:4.5705101779852135e-05 tokens_per_second_per_gpu:875.8775526885681 mfu:12.870771079031188 
Step 3459 | loss:1.9495043754577637 lr:4.565226394333158e-05 tokens_per_second_per_gpu:874.9590642468179 mfu:12.85727415307822 
Step 3460 | loss:1.9990034103393555 lr:4.5599447631259616e-05 tokens_per_second_per_gpu:863.9801966073765 mfu:12.69594282124938 
Step 3461 | loss:2.0365216732025146 lr:4.5546652864554194e-05 tokens_per_second_per_gpu:847.9794810261623 mfu:12.460816864756552 
Step 3462 | loss:2.0169122219085693 lr:4.549387966412477e-05 tokens_per_second_per_gpu:879.3281451612413 mfu:12.921476552263696 
Step 3463 | loss:1.9570856094360352 lr:4.544112805087209e-05 tokens_per_second_per_gpu:877.8756834110505 mfu:12.900133040684514 
Step 3464 | loss:1.9535878896713257 lr:4.5388398045688566e-05 tokens_per_second_per_gpu:880.2764764814025 mfu:12.935412010811987 
Step 3465 | loss:1.9831771850585938 lr:4.533568966945785e-05 tokens_per_second_per_gpu:879.300317469159 mfu:12.9210676322573 
Step 3466 | loss:1.9933298826217651 lr:4.528300294305519e-05 tokens_per_second_per_gpu:884.3240160334672 mfu:12.994889451292156 
Step 3467 | loss:2.0261781215667725 lr:4.5230337887347115e-05 tokens_per_second_per_gpu:868.070315562528 mfu:12.756045953926053 
Step 3468 | loss:1.9671564102172852 lr:4.517769452319175e-05 tokens_per_second_per_gpu:855.6985935388318 mfu:12.574247023776945 
Step 3469 | loss:1.9763706922531128 lr:4.512507287143842e-05 tokens_per_second_per_gpu:838.5892041500897 mfu:12.322829421569248 
Step 3470 | loss:1.9450403451919556 lr:4.507247295292801e-05 tokens_per_second_per_gpu:883.7069014741741 mfu:12.985821128673523 
Step 3471 | loss:2.015993595123291 lr:4.501989478849279e-05 tokens_per_second_per_gpu:886.672587478756 mfu:13.02940103951847 
Step 3472 | loss:1.972231388092041 lr:4.49673383989563e-05 tokens_per_second_per_gpu:855.1713141854591 mfu:12.566498803913188 
Step 3473 | loss:1.9293231964111328 lr:4.491480380513349e-05 tokens_per_second_per_gpu:884.8668218527158 mfu:13.002865828148108 
Step 3474 | loss:1.9568806886672974 lr:4.486229102783084e-05 tokens_per_second_per_gpu:889.5560897586282 mfu:13.071773283944852 
Step 3475 | loss:2.004441022872925 lr:4.480980008784599e-05 tokens_per_second_per_gpu:870.1102789998027 mfu:12.786022635404146 
Step 3476 | loss:2.0017895698547363 lr:4.475733100596795e-05 tokens_per_second_per_gpu:864.2568281174024 mfu:12.700007842470509 
Step 3477 | loss:1.9862325191497803 lr:4.4704883802977205e-05 tokens_per_second_per_gpu:896.9471603316391 mfu:13.180382960128679 
Step 3478 | loss:1.9540259838104248 lr:4.465245849964549e-05 tokens_per_second_per_gpu:898.9462568928961 mfu:13.209759114507605 
Step 3479 | loss:1.9700549840927124 lr:4.460005511673583e-05 tokens_per_second_per_gpu:876.6291514438087 mfu:12.88181560859162 
Step 3480 | loss:1.9849357604980469 lr:4.454767367500266e-05 tokens_per_second_per_gpu:843.5334592164526 mfu:12.395483841037084 
Step 3481 | loss:2.0235843658447266 lr:4.449531419519164e-05 tokens_per_second_per_gpu:880.4507046707075 mfu:12.937972244412194 
Step 3482 | loss:2.014288902282715 lr:4.444297669803981e-05 tokens_per_second_per_gpu:890.6644877197086 mfu:13.08806087617477 
Step 3483 | loss:1.9649330377578735 lr:4.439066120427539e-05 tokens_per_second_per_gpu:869.6952559714842 mfu:12.779923990252644 
Step 3484 | loss:2.0398173332214355 lr:4.433836773461801e-05 tokens_per_second_per_gpu:851.6930520670169 mfu:12.515386733119824 
Step 3485 | loss:1.9775609970092773 lr:4.428609630977855e-05 tokens_per_second_per_gpu:860.5523472899703 mfu:12.645571552203469 
Step 3486 | loss:1.9729926586151123 lr:4.423384695045907e-05 tokens_per_second_per_gpu:888.7407127411714 mfu:13.059791550993053 
Step 3487 | loss:2.0123162269592285 lr:4.4181619677353026e-05 tokens_per_second_per_gpu:889.3926197838822 mfu:13.069371139242326 
Step 3488 | loss:2.004753351211548 lr:4.412941451114498e-05 tokens_per_second_per_gpu:888.9970110203606 mfu:13.063557781180442 
Step 3489 | loss:1.9871779680252075 lr:4.407723147251085e-05 tokens_per_second_per_gpu:866.3907560198928 mfu:12.731365304992304 
Step 3490 | loss:2.0165891647338867 lr:4.40250705821178e-05 tokens_per_second_per_gpu:857.9295917562215 mfu:12.60703090691861 
Step 3491 | loss:1.9872546195983887 lr:4.397293186062413e-05 tokens_per_second_per_gpu:870.4772469332363 mfu:12.791415124628319 
Step 3492 | loss:1.9918417930603027 lr:4.3920815328679354e-05 tokens_per_second_per_gpu:833.1491437315474 mfu:12.24288928371752 
Step 3493 | loss:2.0045833587646484 lr:4.386872100692437e-05 tokens_per_second_per_gpu:841.0018648884021 mfu:12.358282783696028 
Step 3494 | loss:2.0007753372192383 lr:4.381664891599111e-05 tokens_per_second_per_gpu:879.2131725989132 mfu:12.919787063218621 
Step 3495 | loss:1.9540084600448608 lr:4.3764599076502696e-05 tokens_per_second_per_gpu:864.8652876264227 mfu:12.708948981591407 
Step 3496 | loss:1.9736249446868896 lr:4.371257150907354e-05 tokens_per_second_per_gpu:879.8359176812702 mfu:12.928938124769411 
Step 3497 | loss:1.9967703819274902 lr:4.366056623430923e-05 tokens_per_second_per_gpu:869.2002261236729 mfu:12.772649667684483 
Step 3498 | loss:1.9960095882415771 lr:4.36085832728064e-05 tokens_per_second_per_gpu:885.6867729471458 mfu:13.014914775857768 
Step 3499 | loss:2.0166797637939453 lr:4.3556622645153015e-05 tokens_per_second_per_gpu:877.2551618264608 mfu:12.891014652799887 
Step 3500 | loss:1.9594073295593262 lr:4.3504684371928006e-05 tokens_per_second_per_gpu:852.2887920235002 mfu:12.524140962040283 
Step 3501 | loss:1.9763238430023193 lr:4.3452768473701655e-05 tokens_per_second_per_gpu:857.668246287794 mfu:12.603190509723422 
Step 3502 | loss:1.9961166381835938 lr:4.340087497103519e-05 tokens_per_second_per_gpu:853.4855051195559 mfu:12.541726320015647 
Step 3503 | loss:1.9868108034133911 lr:4.334900388448113e-05 tokens_per_second_per_gpu:877.8824856472027 mfu:12.900232997606656 
Step 3504 | loss:1.9707475900650024 lr:4.3297155234582996e-05 tokens_per_second_per_gpu:851.9325051197599 mfu:12.518905427504182 
Step 3505 | loss:1.9771562814712524 lr:4.324532904187548e-05 tokens_per_second_per_gpu:867.5183660634832 mfu:12.747935213300739 
Step 3506 | loss:2.023263692855835 lr:4.3193525326884435e-05 tokens_per_second_per_gpu:874.2846405983233 mfu:12.847363689722455 
Step 3507 | loss:2.0510034561157227 lr:4.314174411012669e-05 tokens_per_second_per_gpu:850.1068826553883 mfu:12.492078425552211 
Step 3508 | loss:2.000509738922119 lr:4.308998541211015e-05 tokens_per_second_per_gpu:848.0893210127142 mfu:12.462430932062988 
Step 3509 | loss:1.9478251934051514 lr:4.3038249253334054e-05 tokens_per_second_per_gpu:876.1449375897445 mfu:12.874700223969846 
Step 3510 | loss:1.948729395866394 lr:4.2986535654288406e-05 tokens_per_second_per_gpu:893.1599946066219 mfu:13.124731638850461 
Step 3511 | loss:1.967550277709961 lr:4.293484463545442e-05 tokens_per_second_per_gpu:884.3812003296788 mfu:12.995729758231858 
Step 3512 | loss:2.008166551589966 lr:4.288317621730434e-05 tokens_per_second_per_gpu:837.7213369009614 mfu:12.310076359618714 
Step 3513 | loss:2.0172598361968994 lr:4.283153042030154e-05 tokens_per_second_per_gpu:880.1399354260117 mfu:12.933405578906717 
Step 3514 | loss:1.9509000778198242 lr:4.277990726490029e-05 tokens_per_second_per_gpu:863.5572439422446 mfu:12.68972765234424 
Step 3515 | loss:1.984072208404541 lr:4.272830677154601e-05 tokens_per_second_per_gpu:850.1048812400595 mfu:12.492049015324204 
Step 3516 | loss:2.0073585510253906 lr:4.267672896067506e-05 tokens_per_second_per_gpu:865.7039146355116 mfu:12.721272366545781 
Step 3517 | loss:1.998944640159607 lr:4.262517385271492e-05 tokens_per_second_per_gpu:850.7113255123622 mfu:12.500960541115724 
Step 3518 | loss:1.9165832996368408 lr:4.257364146808393e-05 tokens_per_second_per_gpu:906.1336007971468 mfu:13.31537508534043 
Step 3519 | loss:1.9675213098526 lr:4.252213182719162e-05 tokens_per_second_per_gpu:840.3097200512334 mfu:12.34811191252187 
Step 3520 | loss:2.0394763946533203 lr:4.247064495043832e-05 tokens_per_second_per_gpu:867.7506798430792 mfu:12.751348998100346 
Step 3521 | loss:1.957754135131836 lr:4.241918085821547e-05 tokens_per_second_per_gpu:851.3219362252107 mfu:12.50993329156395 
Step 3522 | loss:2.0230398178100586 lr:4.236773957090548e-05 tokens_per_second_per_gpu:867.7116600067937 mfu:12.750775612723784 
Step 3523 | loss:1.961567759513855 lr:4.231632110888164e-05 tokens_per_second_per_gpu:874.9627648113081 mfu:12.85732853181903 
Step 3524 | loss:2.009430170059204 lr:4.226492549250829e-05 tokens_per_second_per_gpu:883.0789313054471 mfu:12.976593285967272 
Step 3525 | loss:1.9559400081634521 lr:4.221355274214072e-05 tokens_per_second_per_gpu:858.8556551165435 mfu:12.620639144141718 
Step 3526 | loss:1.963435411453247 lr:4.216220287812509e-05 tokens_per_second_per_gpu:847.9787349049968 mfu:12.460805900718613 
Step 3527 | loss:1.9728991985321045 lr:4.2110875920798535e-05 tokens_per_second_per_gpu:885.0835401111302 mfu:13.006050441207476 
Step 3528 | loss:1.9984629154205322 lr:4.2059571890489126e-05 tokens_per_second_per_gpu:877.3727313714579 mfu:12.892742303765344 
Step 3529 | loss:1.9443178176879883 lr:4.200829080751591e-05 tokens_per_second_per_gpu:891.7035507714472 mfu:13.103329611667027 
Step 3530 | loss:1.9775325059890747 lr:4.195703269218868e-05 tokens_per_second_per_gpu:890.1643432741984 mfu:13.080711396050692 
Step 3531 | loss:1.9290494918823242 lr:4.1905797564808325e-05 tokens_per_second_per_gpu:881.2945222364059 mfu:12.950371903117034 
Step 3532 | loss:1.9757869243621826 lr:4.185458544566654e-05 tokens_per_second_per_gpu:837.8720726337929 mfu:12.312291378264584 
Step 3533 | loss:1.9225211143493652 lr:4.180339635504589e-05 tokens_per_second_per_gpu:824.2090518127773 mfu:12.11151718020969 
Step 3534 | loss:1.9855612516403198 lr:4.17522303132198e-05 tokens_per_second_per_gpu:865.6202911443679 mfu:12.720043543169686 
Step 3535 | loss:2.019353151321411 lr:4.170108734045264e-05 tokens_per_second_per_gpu:889.2158427752055 mfu:13.066773451467673 
Step 3536 | loss:2.056260824203491 lr:4.164996745699966e-05 tokens_per_second_per_gpu:861.9598601674184 mfu:12.66625455290467 
Step 3537 | loss:2.0118584632873535 lr:4.159887068310684e-05 tokens_per_second_per_gpu:855.069133605556 mfu:12.564997289405117 
Step 3538 | loss:1.9936230182647705 lr:4.154779703901114e-05 tokens_per_second_per_gpu:825.2844709645723 mfu:12.127320158233585 
Step 3539 | loss:2.0160422325134277 lr:4.1496746544940244e-05 tokens_per_second_per_gpu:852.2252926828124 mfu:12.523207857321307 
Step 3540 | loss:2.0337843894958496 lr:4.144571922111277e-05 tokens_per_second_per_gpu:867.6778698255425 mfu:12.750279075637899 
Step 3541 | loss:1.9523358345031738 lr:4.1394715087738125e-05 tokens_per_second_per_gpu:879.9975350124014 mfu:12.931313045401879 
Step 3542 | loss:1.9765310287475586 lr:4.1343734165016514e-05 tokens_per_second_per_gpu:887.903742972596 mfu:13.047492518715838 
Step 3543 | loss:1.9803388118743896 lr:4.12927764731389e-05 tokens_per_second_per_gpu:878.7684435985262 mfu:12.91325189727149 
Step 3544 | loss:2.031484842300415 lr:4.124184203228716e-05 tokens_per_second_per_gpu:878.2666302343872 mfu:12.905877892863675 
Step 3545 | loss:1.966300129890442 lr:4.1190930862633926e-05 tokens_per_second_per_gpu:852.1349635937623 mfu:12.521880497094557 
Step 3546 | loss:2.0227882862091064 lr:4.114004298434253e-05 tokens_per_second_per_gpu:866.7217925884518 mfu:12.736229793047317 
Step 3547 | loss:2.041670083999634 lr:4.1089178417567164e-05 tokens_per_second_per_gpu:844.8681855498285 mfu:12.415097264211708 
Step 3548 | loss:1.9767014980316162 lr:4.1038337182452826e-05 tokens_per_second_per_gpu:874.900948953231 mfu:12.85642016539735 
Step 3549 | loss:1.9957958459854126 lr:4.0987519299135146e-05 tokens_per_second_per_gpu:859.5538783336858 mfu:12.630899335377716 
Step 3550 | loss:2.0130667686462402 lr:4.093672478774056e-05 tokens_per_second_per_gpu:897.5482786970708 mfu:13.189216223236201 
Step 3551 | loss:1.969477653503418 lr:4.088595366838629e-05 tokens_per_second_per_gpu:890.9010924007786 mfu:13.09153771454896 
Step 3552 | loss:2.0207626819610596 lr:4.08352059611803e-05 tokens_per_second_per_gpu:877.570509548009 mfu:12.895648597718196 
Step 3553 | loss:1.980411410331726 lr:4.0784481686221164e-05 tokens_per_second_per_gpu:882.5915340125184 mfu:12.969431121618422 
Step 3554 | loss:1.9446806907653809 lr:4.0733780863598335e-05 tokens_per_second_per_gpu:886.2163297284445 mfu:13.022696461876006 
Step 3555 | loss:1.9540799856185913 lr:4.068310351339184e-05 tokens_per_second_per_gpu:867.8603042136251 mfu:12.752959896991005 
Step 3556 | loss:2.0175483226776123 lr:4.06324496556725e-05 tokens_per_second_per_gpu:851.3072119393714 mfu:12.50971692237883 
Step 3557 | loss:2.021261215209961 lr:4.0581819310501825e-05 tokens_per_second_per_gpu:874.2813347006702 mfu:12.847315110498368 
Step 3558 | loss:2.0609235763549805 lr:4.053121249793196e-05 tokens_per_second_per_gpu:883.1935543579825 mfu:12.978277639065528 
Step 3559 | loss:1.9498790502548218 lr:4.0480629238005687e-05 tokens_per_second_per_gpu:884.5992642755155 mfu:12.998934145784478 
Step 3560 | loss:2.027113199234009 lr:4.0430069550756665e-05 tokens_per_second_per_gpu:906.0669152476313 mfu:13.314395160190552 
Step 3561 | loss:2.021986961364746 lr:4.037953345620904e-05 tokens_per_second_per_gpu:873.5570388384159 mfu:12.836671789171147 
Step 3562 | loss:1.9576014280319214 lr:4.0329020974377596e-05 tokens_per_second_per_gpu:887.3535957011354 mfu:13.03940826131138 
Step 3563 | loss:2.022789716720581 lr:4.027853212526788e-05 tokens_per_second_per_gpu:861.3329963321623 mfu:12.657042967453554 
Step 3564 | loss:1.9867688417434692 lr:4.022806692887605e-05 tokens_per_second_per_gpu:870.5359196571159 mfu:12.792277303588518 
Step 3565 | loss:2.033984661102295 lr:4.0177625405188844e-05 tokens_per_second_per_gpu:869.5101095766278 mfu:12.777203316732708 
Step 3566 | loss:1.9764609336853027 lr:4.012720757418358e-05 tokens_per_second_per_gpu:876.2809952961724 mfu:12.876699553199824 
Step 3567 | loss:1.9493266344070435 lr:4.0076813455828413e-05 tokens_per_second_per_gpu:836.0095371908243 mfu:12.284921950609489 
Step 3568 | loss:1.9805908203125 lr:4.002644307008188e-05 tokens_per_second_per_gpu:864.6791339210816 mfu:12.706213505930908 
Step 3569 | loss:2.0354654788970947 lr:3.997609643689315e-05 tokens_per_second_per_gpu:864.3161825304234 mfu:12.70088003865841 
Step 3570 | loss:1.9858222007751465 lr:3.99257735762021e-05 tokens_per_second_per_gpu:879.918341114958 mfu:12.930149313643117 
Step 3571 | loss:1.9539873600006104 lr:3.9875474507939147e-05 tokens_per_second_per_gpu:891.4776793918611 mfu:13.100010496099978 
Step 3572 | loss:2.0249392986297607 lr:3.9825199252025184e-05 tokens_per_second_per_gpu:873.6666803524727 mfu:12.838282939980814 
Step 3573 | loss:1.9885425567626953 lr:3.977494782837182e-05 tokens_per_second_per_gpu:824.857884687769 mfu:12.121051594440235 
Step 3574 | loss:1.9621644020080566 lr:3.9724720256881095e-05 tokens_per_second_per_gpu:864.9426620746782 mfu:12.710085977062757 
Step 3575 | loss:1.9963760375976562 lr:3.967451655744571e-05 tokens_per_second_per_gpu:846.2408197990887 mfu:12.435267733409413 
Step 3576 | loss:2.0088322162628174 lr:3.962433674994889e-05 tokens_per_second_per_gpu:861.95438665314 mfu:12.66617412117188 
Step 3577 | loss:1.9848510026931763 lr:3.957418085426432e-05 tokens_per_second_per_gpu:907.5257756206526 mfu:13.335832697709112 
Step 3578 | loss:2.034637212753296 lr:3.952404889025626e-05 tokens_per_second_per_gpu:879.6705106659286 mfu:12.926507515807243 
Step 3579 | loss:1.968285322189331 lr:3.947394087777952e-05 tokens_per_second_per_gpu:874.3735034170581 mfu:12.848669503524695 
Step 3580 | loss:2.000277042388916 lr:3.942385683667946e-05 tokens_per_second_per_gpu:831.968693886058 mfu:12.225542909575458 
Step 3581 | loss:1.9842164516448975 lr:3.9373796786791796e-05 tokens_per_second_per_gpu:873.9566254818069 mfu:12.842543601044323 
Step 3582 | loss:1.998946189880371 lr:3.932376074794288e-05 tokens_per_second_per_gpu:881.6728165856631 mfu:12.955930830794578 
Step 3583 | loss:1.9675710201263428 lr:3.9273748739949546e-05 tokens_per_second_per_gpu:862.7682761705544 mfu:12.678133995734377 
Step 3584 | loss:2.047549247741699 lr:3.9223760782619045e-05 tokens_per_second_per_gpu:900.4627139181126 mfu:13.23204301841956 
Step 3585 | loss:2.0122628211975098 lr:3.917379689574908e-05 tokens_per_second_per_gpu:862.8678604848219 mfu:12.67959735885867 
Step 3586 | loss:2.013824224472046 lr:3.9123857099127936e-05 tokens_per_second_per_gpu:883.1855262866949 mfu:12.978159668845338 
Step 3587 | loss:1.9597983360290527 lr:3.907394141253431e-05 tokens_per_second_per_gpu:880.7256858612841 mfu:12.94201301465923 
Step 3588 | loss:2.015500068664551 lr:3.9024049855737266e-05 tokens_per_second_per_gpu:894.9365452404685 mfu:13.150837544234564 
Step 3589 | loss:2.0626916885375977 lr:3.8974182448496466e-05 tokens_per_second_per_gpu:889.8203184911432 mfu:13.075656049884296 
Step 3590 | loss:1.9844305515289307 lr:3.8924339210561836e-05 tokens_per_second_per_gpu:874.7867317728831 mfu:12.85474177647525 
Step 3591 | loss:1.9624359607696533 lr:3.887452016167385e-05 tokens_per_second_per_gpu:884.1335608343993 mfu:12.992090766406934 
Step 3592 | loss:2.071836471557617 lr:3.882472532156342e-05 tokens_per_second_per_gpu:851.4349222376457 mfu:12.51159358882436 
Step 3593 | loss:2.0270907878875732 lr:3.877495470995177e-05 tokens_per_second_per_gpu:891.6650928065479 mfu:13.102764482830395 
Step 3594 | loss:1.9776641130447388 lr:3.8725208346550535e-05 tokens_per_second_per_gpu:872.5113975129171 mfu:12.821306387820286 
Step 3595 | loss:1.9937529563903809 lr:3.867548625106184e-05 tokens_per_second_per_gpu:861.9023021675254 mfu:12.665408754495845 
Step 3596 | loss:1.967637300491333 lr:3.862578844317817e-05 tokens_per_second_per_gpu:879.6522438495452 mfu:12.926239090145128 
Step 3597 | loss:2.0153911113739014 lr:3.85761149425823e-05 tokens_per_second_per_gpu:869.1344300652769 mfu:12.77168281335317 
Step 3598 | loss:2.0166804790496826 lr:3.852646576894748e-05 tokens_per_second_per_gpu:870.7862140851414 mfu:12.795955308893694 
Step 3599 | loss:2.021376848220825 lr:3.847684094193733e-05 tokens_per_second_per_gpu:887.354487642339 mfu:13.039421368133231 
Step 3600 | loss:2.0250885486602783 lr:3.842724048120574e-05 tokens_per_second_per_gpu:866.8156764500922 mfu:12.737609389644446 
Step 3601 | loss:1.964881181716919 lr:3.837766440639694e-05 tokens_per_second_per_gpu:893.6362157789326 mfu:13.131729573291166 
Step 3602 | loss:1.9789977073669434 lr:3.832811273714569e-05 tokens_per_second_per_gpu:868.2034725345944 mfu:12.758002657691076 
Step 3603 | loss:2.0259017944335938 lr:3.82785854930769e-05 tokens_per_second_per_gpu:869.431426130279 mfu:12.776047085907344 
Step 3604 | loss:1.9730069637298584 lr:3.8229082693805806e-05 tokens_per_second_per_gpu:895.6976964259677 mfu:13.162022444035937 
Step 3605 | loss:1.9625880718231201 lr:3.817960435893807e-05 tokens_per_second_per_gpu:849.9133932240206 mfu:12.489235153487867 
Step 3606 | loss:1.9908902645111084 lr:3.813015050806964e-05 tokens_per_second_per_gpu:863.6988031901507 mfu:12.691807825158724 
Step 3607 | loss:2.030062437057495 lr:3.808072116078666e-05 tokens_per_second_per_gpu:852.2586992965191 mfu:12.52369875799141 
Step 3608 | loss:1.9374606609344482 lr:3.803131633666572e-05 tokens_per_second_per_gpu:867.3235382274422 mfu:12.745072273761064 
Step 3609 | loss:1.9825756549835205 lr:3.798193605527357e-05 tokens_per_second_per_gpu:916.6567188376195 mfu:13.470009306666006 
Step 3610 | loss:1.9575324058532715 lr:3.7932580336167355e-05 tokens_per_second_per_gpu:883.5421044116574 mfu:12.983399482794326 
Step 3611 | loss:1.9942004680633545 lr:3.788324919889435e-05 tokens_per_second_per_gpu:882.3564352781368 mfu:12.965976412701739 
Step 3612 | loss:1.991140365600586 lr:3.783394266299228e-05 tokens_per_second_per_gpu:853.4577008707352 mfu:12.541317744501297 
Step 3613 | loss:2.030503273010254 lr:3.778466074798893e-05 tokens_per_second_per_gpu:881.104092748796 mfu:12.947573596054362 
Step 3614 | loss:1.9859528541564941 lr:3.773540347340248e-05 tokens_per_second_per_gpu:858.13865348246 mfu:12.610103009419174 
Step 3615 | loss:1.9297215938568115 lr:3.76861708587413e-05 tokens_per_second_per_gpu:848.4785348693005 mfu:12.468150318789514 
Step 3616 | loss:1.996874451637268 lr:3.7636962923503985e-05 tokens_per_second_per_gpu:860.6729227301716 mfu:12.647343373942503 
Step 3617 | loss:1.9935579299926758 lr:3.758777968717929e-05 tokens_per_second_per_gpu:894.1402417503466 mfu:13.139136091332464 
Step 3618 | loss:2.023007869720459 lr:3.75386211692464e-05 tokens_per_second_per_gpu:902.3632218408476 mfu:13.259970440845587 
Step 3619 | loss:2.057918071746826 lr:3.748948738917449e-05 tokens_per_second_per_gpu:881.7401125023154 mfu:12.956919725115624 
Step 3620 | loss:1.9882795810699463 lr:3.7440378366423e-05 tokens_per_second_per_gpu:894.0999684556386 mfu:13.13854428674152 
Step 3621 | loss:2.039031505584717 lr:3.739129412044161e-05 tokens_per_second_per_gpu:873.3326636642842 mfu:12.833374659916947 
Step 3622 | loss:1.9514039754867554 lr:3.7342234670670194e-05 tokens_per_second_per_gpu:863.4886458033975 mfu:12.688719622239075 
Step 3623 | loss:1.994307518005371 lr:3.729320003653871e-05 tokens_per_second_per_gpu:842.9173172992269 mfu:12.386429811116502 
Step 3624 | loss:2.0276424884796143 lr:3.7244190237467405e-05 tokens_per_second_per_gpu:879.931929848073 mfu:12.930348996204497 
Step 3625 | loss:1.991715908050537 lr:3.719520529286659e-05 tokens_per_second_per_gpu:895.5216866677094 mfu:13.159436030787573 
Step 3626 | loss:1.998988389968872 lr:3.714624522213681e-05 tokens_per_second_per_gpu:890.5452584778261 mfu:13.08630883643647 
Step 3627 | loss:1.953397274017334 lr:3.70973100446687e-05 tokens_per_second_per_gpu:901.7334281905734 mfu:13.25071580259755 
Step 3628 | loss:1.9570873975753784 lr:3.704839977984309e-05 tokens_per_second_per_gpu:852.5306937806286 mfu:12.527695639437892 
Step 3629 | loss:2.008627414703369 lr:3.699951444703088e-05 tokens_per_second_per_gpu:854.5112841083575 mfu:12.556799849987978 
Step 3630 | loss:1.9773646593093872 lr:3.6950654065593147e-05 tokens_per_second_per_gpu:887.5017992950447 mfu:13.041586070897253 
Step 3631 | loss:1.9899648427963257 lr:3.6901818654881106e-05 tokens_per_second_per_gpu:838.8981965141221 mfu:12.327369976319648 
Step 3632 | loss:2.017612934112549 lr:3.685300823423602e-05 tokens_per_second_per_gpu:848.8169511454676 mfu:12.47312324954518 
Step 3633 | loss:2.037907838821411 lr:3.68042228229892e-05 tokens_per_second_per_gpu:866.0345307057542 mfu:12.726130675497846 
Step 3634 | loss:1.9426004886627197 lr:3.675546244046228e-05 tokens_per_second_per_gpu:861.725853019971 mfu:12.662815884546967 
Step 3635 | loss:1.9858850240707397 lr:3.670672710596676e-05 tokens_per_second_per_gpu:838.2076068333741 mfu:12.317221957725993 
Step 3636 | loss:1.975441336631775 lr:3.665801683880428e-05 tokens_per_second_per_gpu:876.3744244968085 mfu:12.878072468683037 
Step 3637 | loss:2.0058913230895996 lr:3.6609331658266566e-05 tokens_per_second_per_gpu:876.7272286672843 mfu:12.883256825446129 
Step 3638 | loss:2.0410611629486084 lr:3.6560671583635467e-05 tokens_per_second_per_gpu:862.2800076311496 mfu:12.6709590286668 
Step 3639 | loss:1.9940564632415771 lr:3.6512036634182753e-05 tokens_per_second_per_gpu:883.0297631044049 mfu:12.97587077326211 
Step 3640 | loss:2.0163917541503906 lr:3.6463426829170356e-05 tokens_per_second_per_gpu:885.2171283612392 mfu:13.008013482480454 
Step 3641 | loss:1.989544153213501 lr:3.641484218785025e-05 tokens_per_second_per_gpu:878.4509054416305 mfu:12.908585764529855 
Step 3642 | loss:2.0036463737487793 lr:3.636628272946434e-05 tokens_per_second_per_gpu:852.1333208743122 mfu:12.521856357800285 
Step 3643 | loss:1.984361171722412 lr:3.63177484732447e-05 tokens_per_second_per_gpu:830.2102114201218 mfu:12.19970251077076 
Step 3644 | loss:1.9958434104919434 lr:3.626923943841325e-05 tokens_per_second_per_gpu:872.837805562509 mfu:12.826102861107852 
Step 3645 | loss:1.9939634799957275 lr:3.6220755644182116e-05 tokens_per_second_per_gpu:861.2737786734107 mfu:12.656172780830676 
Step 3646 | loss:1.9359493255615234 lr:3.617229710975325e-05 tokens_per_second_per_gpu:879.1018641297453 mfu:12.918151416978551 
Step 3647 | loss:1.9994926452636719 lr:3.612386385431875e-05 tokens_per_second_per_gpu:872.4303587046655 mfu:12.820115545622857 
Step 3648 | loss:1.9793128967285156 lr:3.6075455897060564e-05 tokens_per_second_per_gpu:858.5030154624594 mfu:12.615457204900128 
Step 3649 | loss:1.9727306365966797 lr:3.602707325715071e-05 tokens_per_second_per_gpu:853.7176387008388 mfu:12.545137456852384 
Step 3650 | loss:1.9763797521591187 lr:3.597871595375121e-05 tokens_per_second_per_gpu:856.6619034559048 mfu:12.588402588539106 
Step 3651 | loss:2.0249176025390625 lr:3.593038400601395e-05 tokens_per_second_per_gpu:886.5289078182961 mfu:13.027289707845664 
Step 3652 | loss:1.937528371810913 lr:3.588207743308076e-05 tokens_per_second_per_gpu:894.7276536119379 mfu:13.14776794127135 
Step 3653 | loss:1.9955719709396362 lr:3.583379625408363e-05 tokens_per_second_per_gpu:891.9831942612619 mfu:13.10743889307297 
Step 3654 | loss:1.9512168169021606 lr:3.578554048814426e-05 tokens_per_second_per_gpu:881.5840919527649 mfu:12.954627047593835 
Step 3655 | loss:2.0448520183563232 lr:3.573731015437435e-05 tokens_per_second_per_gpu:879.7367210215555 mfu:12.927480458118323 
Step 3656 | loss:2.0159974098205566 lr:3.5689105271875564e-05 tokens_per_second_per_gpu:861.7764096672018 mfu:12.66355880007327 
Step 3657 | loss:1.9833945035934448 lr:3.564092585973953e-05 tokens_per_second_per_gpu:870.257881359419 mfu:12.78819161002339 
Step 3658 | loss:1.9736367464065552 lr:3.559277193704763e-05 tokens_per_second_per_gpu:873.3064018049341 mfu:12.832988749376408 
Step 3659 | loss:1.9830443859100342 lr:3.554464352287135e-05 tokens_per_second_per_gpu:861.2463315597909 mfu:12.65576945331635 
Step 3660 | loss:1.9856884479522705 lr:3.549654063627188e-05 tokens_per_second_per_gpu:867.792391078012 mfu:12.75196193281319 
Step 3661 | loss:1.9525209665298462 lr:3.5448463296300483e-05 tokens_per_second_per_gpu:900.8341198105193 mfu:13.237500722186367 
Step 3662 | loss:1.9887664318084717 lr:3.5400411521998126e-05 tokens_per_second_per_gpu:867.7699427266197 mfu:12.751632060685534 
Step 3663 | loss:1.9617528915405273 lr:3.535238533239581e-05 tokens_per_second_per_gpu:873.9348044930456 mfu:12.842222947831779 
Step 3664 | loss:1.9973948001861572 lr:3.530438474651428e-05 tokens_per_second_per_gpu:875.3391895583452 mfu:12.862859986224642 
Step 3665 | loss:2.013913631439209 lr:3.52564097833642e-05 tokens_per_second_per_gpu:859.899831289119 mfu:12.635983015487827 
Step 3666 | loss:1.977607011795044 lr:3.520846046194614e-05 tokens_per_second_per_gpu:822.6432227005492 mfu:12.08850776754635 
Step 3667 | loss:2.013503074645996 lr:3.51605368012504e-05 tokens_per_second_per_gpu:858.9048864969694 mfu:12.621362585249921 
Step 3668 | loss:1.9580614566802979 lr:3.5112638820257115e-05 tokens_per_second_per_gpu:860.3996087202017 mfu:12.643327102439464 
Step 3669 | loss:1.998920202255249 lr:3.506476653793643e-05 tokens_per_second_per_gpu:886.3001603288197 mfu:13.02392832866325 
Step 3670 | loss:1.9990825653076172 lr:3.501691997324813e-05 tokens_per_second_per_gpu:890.5527599638772 mfu:13.086419068636644 
Step 3671 | loss:2.0135364532470703 lr:3.496909914514183e-05 tokens_per_second_per_gpu:863.0483887745578 mfu:12.682250170639664 
Step 3672 | loss:1.9990835189819336 lr:3.4921304072557017e-05 tokens_per_second_per_gpu:873.4714682391532 mfu:12.83541435359602 
Step 3673 | loss:1.9623184204101562 lr:3.487353477442301e-05 tokens_per_second_per_gpu:897.5293247913983 mfu:13.18893770099275 
Step 3674 | loss:2.0245649814605713 lr:3.482579126965878e-05 tokens_per_second_per_gpu:895.3449782347857 mfu:13.156839350714069 
Step 3675 | loss:1.9896094799041748 lr:3.4778073577173256e-05 tokens_per_second_per_gpu:888.8270364909105 mfu:13.06106005389984 
Step 3676 | loss:2.011105537414551 lr:3.473038171586496e-05 tokens_per_second_per_gpu:868.6678116565273 mfu:12.764825988786948 
Step 3677 | loss:1.9668009281158447 lr:3.468271570462235e-05 tokens_per_second_per_gpu:884.7537079140351 mfu:13.001203651047968 
Step 3678 | loss:2.0209386348724365 lr:3.463507556232352e-05 tokens_per_second_per_gpu:859.1623503966392 mfu:12.625145943898161 
Step 3679 | loss:2.037419557571411 lr:3.458746130783639e-05 tokens_per_second_per_gpu:875.3867907738118 mfu:12.863559472523239 
Step 3680 | loss:1.9934037923812866 lr:3.453987296001866e-05 tokens_per_second_per_gpu:863.9593498611315 mfu:12.69563648425303 
Step 3681 | loss:1.9693394899368286 lr:3.4492310537717646e-05 tokens_per_second_per_gpu:889.2253826045741 mfu:13.066913636542127 
Step 3682 | loss:1.9820202589035034 lr:3.4444774059770536e-05 tokens_per_second_per_gpu:870.6895200244885 mfu:12.794534417222769 
Step 3683 | loss:1.9747815132141113 lr:3.439726354500411e-05 tokens_per_second_per_gpu:851.8808269844047 mfu:12.518146032029431 
Step 3684 | loss:2.0160045623779297 lr:3.434977901223496e-05 tokens_per_second_per_gpu:870.9299826195293 mfu:12.798067946543549 
Step 3685 | loss:2.0400211811065674 lr:3.43023204802694e-05 tokens_per_second_per_gpu:850.5762985684617 mfu:12.498976358647397 
Step 3686 | loss:2.0236191749572754 lr:3.425488796790337e-05 tokens_per_second_per_gpu:888.0993979486943 mfu:13.050367612842985 
Step 3687 | loss:1.965506911277771 lr:3.42074814939225e-05 tokens_per_second_per_gpu:846.8524019673688 mfu:12.444254759118417 
Step 3688 | loss:1.9723955392837524 lr:3.416010107710219e-05 tokens_per_second_per_gpu:881.4788430289994 mfu:12.953080444646949 
Step 3689 | loss:1.947881817817688 lr:3.411274673620751e-05 tokens_per_second_per_gpu:852.0383396624743 mfu:12.520460635954667 
Step 3690 | loss:1.9954537153244019 lr:3.406541848999312e-05 tokens_per_second_per_gpu:862.9914087994164 mfu:12.68141286613987 
Step 3691 | loss:1.9564621448516846 lr:3.40181163572034e-05 tokens_per_second_per_gpu:889.9293293190138 mfu:13.077257932940155 
Step 3692 | loss:2.016847610473633 lr:3.397084035657243e-05 tokens_per_second_per_gpu:872.2248050596043 mfu:12.817094993375658 
Step 3693 | loss:1.9686123132705688 lr:3.3923590506823866e-05 tokens_per_second_per_gpu:874.3579083490042 mfu:12.848440338443039 
Step 3694 | loss:1.986952543258667 lr:3.3876366826670994e-05 tokens_per_second_per_gpu:871.707563150988 mfu:12.809494270902698 
Step 3695 | loss:2.0211665630340576 lr:3.382916933481681e-05 tokens_per_second_per_gpu:862.2035745460284 mfu:12.669835866258493 
Step 3696 | loss:2.0763163566589355 lr:3.3781998049953955e-05 tokens_per_second_per_gpu:907.9933973541931 mfu:13.342704265847267 
Step 3697 | loss:1.9910554885864258 lr:3.3734852990764555e-05 tokens_per_second_per_gpu:888.618828635344 mfu:13.058000498785514 
Step 3698 | loss:1.9687323570251465 lr:3.36877341759205e-05 tokens_per_second_per_gpu:819.0358735301478 mfu:12.035498799304325 
Step 3699 | loss:1.9511743783950806 lr:3.364064162408317e-05 tokens_per_second_per_gpu:883.17779390767 mfu:12.9780460437387 
Step 3700 | loss:1.980168342590332 lr:3.359357535390361e-05 tokens_per_second_per_gpu:879.8306348233682 mfu:12.92886049467775 
Step 3701 | loss:1.9860714673995972 lr:3.354653538402248e-05 tokens_per_second_per_gpu:854.4657690455681 mfu:12.556131019108582 
Step 3702 | loss:1.9946008920669556 lr:3.349952173306996e-05 tokens_per_second_per_gpu:878.8293338416762 mfu:12.914146662045543 
Step 3703 | loss:1.9881892204284668 lr:3.345253441966579e-05 tokens_per_second_per_gpu:875.2054210133988 mfu:12.8608942955704 
Step 3704 | loss:1.9894307851791382 lr:3.340557346241936e-05 tokens_per_second_per_gpu:883.4797517465477 mfu:12.982483228146252 
Step 3705 | loss:2.06204891204834 lr:3.335863887992959e-05 tokens_per_second_per_gpu:865.5551042926254 mfu:12.71908564095657 
Step 3706 | loss:2.0159518718719482 lr:3.331173069078492e-05 tokens_per_second_per_gpu:844.2609456733464 mfu:12.406174047243459 
Step 3707 | loss:1.995921015739441 lr:3.326484891356335e-05 tokens_per_second_per_gpu:853.8110683208051 mfu:12.546510378497535 
Step 3708 | loss:2.057445764541626 lr:3.3217993566832483e-05 tokens_per_second_per_gpu:886.9196988343729 mfu:13.033032270481534 
Step 3709 | loss:1.9965468645095825 lr:3.317116466914939e-05 tokens_per_second_per_gpu:863.9889642454144 mfu:12.696071659192246 
Step 3710 | loss:2.0041005611419678 lr:3.312436223906062e-05 tokens_per_second_per_gpu:854.410367595221 mfu:12.555316910580883 
Step 3711 | loss:2.004096269607544 lr:3.307758629510235e-05 tokens_per_second_per_gpu:798.4487043896038 mfu:11.732976214543607 
Step 3712 | loss:2.0054426193237305 lr:3.303083685580024e-05 tokens_per_second_per_gpu:876.9895333496843 mfu:12.88711131801734 
Step 3713 | loss:1.9594908952713013 lr:3.298411393966936e-05 tokens_per_second_per_gpu:868.1131549959912 mfu:12.756675467194851 
Step 3714 | loss:1.9909617900848389 lr:3.293741756521442e-05 tokens_per_second_per_gpu:893.7513055788816 mfu:13.133420785109674 
Step 3715 | loss:1.9762686491012573 lr:3.289074775092947e-05 tokens_per_second_per_gpu:848.4349067480135 mfu:12.46750921597786 
Step 3716 | loss:1.9903624057769775 lr:3.2844104515298155e-05 tokens_per_second_per_gpu:843.7440473935312 mfu:12.398578374297822 
Step 3717 | loss:2.000209093093872 lr:3.2797487876793575e-05 tokens_per_second_per_gpu:866.8284822454025 mfu:12.737797567157864 
Step 3718 | loss:2.036883592605591 lr:3.275089785387822e-05 tokens_per_second_per_gpu:863.6464696438093 mfu:12.691038798606272 
Step 3719 | loss:1.9436534643173218 lr:3.270433446500412e-05 tokens_per_second_per_gpu:837.7464843856552 mfu:12.310445894741191 
Step 3720 | loss:2.045964002609253 lr:3.265779772861275e-05 tokens_per_second_per_gpu:828.5248496763619 mfu:12.17493660014466 
Step 3721 | loss:1.9611326456069946 lr:3.261128766313498e-05 tokens_per_second_per_gpu:874.7779281888533 mfu:12.854612410316275 
Step 3722 | loss:2.0189433097839355 lr:3.2564804286991135e-05 tokens_per_second_per_gpu:878.1100562355155 mfu:12.9035770825618 
Step 3723 | loss:1.9427903890609741 lr:3.2518347618590986e-05 tokens_per_second_per_gpu:885.6189829691232 mfu:13.013918621445656 
Step 3724 | loss:1.9650300741195679 lr:3.247191767633376e-05 tokens_per_second_per_gpu:894.7841427130902 mfu:13.148598032517738 
Step 3725 | loss:1.9927482604980469 lr:3.2425514478608e-05 tokens_per_second_per_gpu:889.3913187375994 mfu:13.069352020737899 
Step 3726 | loss:1.9464211463928223 lr:3.2379138043791746e-05 tokens_per_second_per_gpu:877.1093180753275 mfu:12.888871520431232 
Step 3727 | loss:1.976037621498108 lr:3.2332788390252436e-05 tokens_per_second_per_gpu:852.8648583114448 mfu:12.532606092007052 
Step 3728 | loss:1.9888969659805298 lr:3.2286465536346854e-05 tokens_per_second_per_gpu:890.376465963839 mfu:13.083828478536313 
Step 3729 | loss:2.0261735916137695 lr:3.2240169500421135e-05 tokens_per_second_per_gpu:867.2931644353848 mfu:12.744625939540974 
Step 3730 | loss:2.0220072269439697 lr:3.219390030081091e-05 tokens_per_second_per_gpu:875.614665219413 mfu:12.866908022574663 
Step 3731 | loss:1.990797519683838 lr:3.2147657955841125e-05 tokens_per_second_per_gpu:883.8180066472358 mfu:12.987453787535237 
Step 3732 | loss:1.9751372337341309 lr:3.210144248382604e-05 tokens_per_second_per_gpu:886.0306335978731 mfu:13.019967710146373 
Step 3733 | loss:2.0241384506225586 lr:3.205525390306936e-05 tokens_per_second_per_gpu:823.1236569749269 mfu:12.095567612321517 
Step 3734 | loss:1.9876097440719604 lr:3.2009092231864044e-05 tokens_per_second_per_gpu:853.6537762410672 mfu:12.54419901620193 
Step 3735 | loss:2.028092861175537 lr:3.196295748849249e-05 tokens_per_second_per_gpu:881.1800134297571 mfu:12.948689228829531 
Step 3736 | loss:1.9834649562835693 lr:3.191684969122639e-05 tokens_per_second_per_gpu:895.4094234732978 mfu:13.15778635513207 
Step 3737 | loss:2.0177175998687744 lr:3.187076885832675e-05 tokens_per_second_per_gpu:854.2927306709398 mfu:12.553588269496045 
Step 3738 | loss:1.9562839269638062 lr:3.1824715008043874e-05 tokens_per_second_per_gpu:891.3323913206243 mfu:13.097875529289079 
Step 3739 | loss:2.0116567611694336 lr:3.177868815861743e-05 tokens_per_second_per_gpu:871.407528731123 mfu:12.805085350589511 
Step 3740 | loss:1.95888352394104 lr:3.173268832827643e-05 tokens_per_second_per_gpu:877.5446520752112 mfu:12.895268629522823 
Step 3741 | loss:2.007133960723877 lr:3.168671553523904e-05 tokens_per_second_per_gpu:836.2465960029065 mfu:12.28840546230951 
Step 3742 | loss:1.9796788692474365 lr:3.164076979771287e-05 tokens_per_second_per_gpu:859.2980200367731 mfu:12.627139570604518 
Step 3743 | loss:1.9894440174102783 lr:3.159485113389475e-05 tokens_per_second_per_gpu:887.8731594135278 mfu:13.047043102029294 
Step 3744 | loss:2.0052075386047363 lr:3.154895956197079e-05 tokens_per_second_per_gpu:908.8724121788961 mfu:13.35562113824467 
Step 3745 | loss:1.924773931503296 lr:3.150309510011632e-05 tokens_per_second_per_gpu:881.0747295743591 mfu:12.947142112572259 
Step 3746 | loss:1.9605759382247925 lr:3.1457257766496015e-05 tokens_per_second_per_gpu:893.8033786907896 mfu:13.134185984652332 
Step 3747 | loss:1.9660547971725464 lr:3.141144757926383e-05 tokens_per_second_per_gpu:904.7785470005085 mfu:13.295462955884927 
Step 3748 | loss:1.9949195384979248 lr:3.136566455656281e-05 tokens_per_second_per_gpu:892.3709638771415 mfu:13.11313705709381 
Step 3749 | loss:1.9924442768096924 lr:3.1319908716525445e-05 tokens_per_second_per_gpu:885.366668066806 mfu:13.010210925846444 
Step 3750 | loss:1.968332052230835 lr:3.127418007727328e-05 tokens_per_second_per_gpu:860.3986209466624 mfu:12.643312587388744 
Step 3751 | loss:1.9351041316986084 lr:3.1228478656917196e-05 tokens_per_second_per_gpu:870.6584249509918 mfu:12.79407748397744 
Step 3752 | loss:2.014293909072876 lr:3.118280447355729e-05 tokens_per_second_per_gpu:875.2519067500235 mfu:12.861577390225243 
Step 3753 | loss:2.0111899375915527 lr:3.113715754528283e-05 tokens_per_second_per_gpu:868.8160097334637 mfu:12.767003717302476 
Step 3754 | loss:1.9849648475646973 lr:3.109153789017226e-05 tokens_per_second_per_gpu:857.811411758028 mfu:12.605294285517363 
Step 3755 | loss:1.985582947731018 lr:3.104594552629331e-05 tokens_per_second_per_gpu:880.6645352497728 mfu:12.941114423846292 
Step 3756 | loss:1.961249828338623 lr:3.1000380471702885e-05 tokens_per_second_per_gpu:887.789671054855 mfu:13.045816264386357 
Step 3757 | loss:2.0141756534576416 lr:3.0954842744446976e-05 tokens_per_second_per_gpu:884.4501737978625 mfu:12.996743303694686 
Step 3758 | loss:1.9842513799667358 lr:3.090933236256087e-05 tokens_per_second_per_gpu:895.3474135224418 mfu:13.156875136572307 
Step 3759 | loss:2.0460550785064697 lr:3.086384934406899e-05 tokens_per_second_per_gpu:881.9112099560207 mfu:12.95943395344821 
Step 3760 | loss:1.9738473892211914 lr:3.08183937069849e-05 tokens_per_second_per_gpu:878.7528341638173 mfu:12.913022521075929 
Step 3761 | loss:2.0311365127563477 lr:3.0772965469311265e-05 tokens_per_second_per_gpu:851.9535060533174 mfu:12.519214030239159 
Step 3762 | loss:1.9681907892227173 lr:3.072756464904006e-05 tokens_per_second_per_gpu:878.2822243439282 mfu:12.906107043860258 
Step 3763 | loss:2.004365921020508 lr:3.068219126415227e-05 tokens_per_second_per_gpu:890.0018145545554 mfu:13.07832308282372 
Step 3764 | loss:1.9870250225067139 lr:3.0636845332617994e-05 tokens_per_second_per_gpu:885.2683474806645 mfu:13.008766132846898 
Step 3765 | loss:1.9839016199111938 lr:3.059152687239655e-05 tokens_per_second_per_gpu:884.8310267005883 mfu:13.002339828586459 
Step 3766 | loss:1.984100341796875 lr:3.054623590143638e-05 tokens_per_second_per_gpu:872.9627802093038 mfu:12.827939327934343 
Step 3767 | loss:2.0055465698242188 lr:3.0500972437674912e-05 tokens_per_second_per_gpu:824.2401266347274 mfu:12.111973815864316 
Step 3768 | loss:2.0108752250671387 lr:3.0455736499038845e-05 tokens_per_second_per_gpu:886.3961114542209 mfu:13.025338303112328 
Step 3769 | loss:2.045713424682617 lr:3.0410528103443837e-05 tokens_per_second_per_gpu:850.2921395431335 mfu:12.494800722733665 
Step 3770 | loss:1.9742695093154907 lr:3.036534726879473e-05 tokens_per_second_per_gpu:844.9045395243986 mfu:12.41563147550993 
Step 3771 | loss:1.9650487899780273 lr:3.0320194012985383e-05 tokens_per_second_per_gpu:875.1927726003137 mfu:12.860708430743939 
Step 3772 | loss:1.9827265739440918 lr:3.0275068353898815e-05 tokens_per_second_per_gpu:857.2291924981205 mfu:12.596738739380726 
Step 3773 | loss:2.0110666751861572 lr:3.022997030940701e-05 tokens_per_second_per_gpu:885.2041557624673 mfu:13.007822853837693 
Step 3774 | loss:1.994402527809143 lr:3.01848998973711e-05 tokens_per_second_per_gpu:863.5379351554126 mfu:12.689443915223265 
Step 3775 | loss:1.9487953186035156 lr:3.013985713564127e-05 tokens_per_second_per_gpu:899.4869543523245 mfu:13.217704509616722 
Step 3776 | loss:2.016244888305664 lr:3.0094842042056704e-05 tokens_per_second_per_gpu:874.1130146723593 mfu:12.844841695640602 
Step 3777 | loss:2.053619861602783 lr:3.0049854634445597e-05 tokens_per_second_per_gpu:825.4709314761265 mfu:12.130060142323972 
Step 3778 | loss:1.9660248756408691 lr:3.000489493062535e-05 tokens_per_second_per_gpu:886.1847836791927 mfu:13.02223290167045 
Step 3779 | loss:2.006331205368042 lr:2.995996294840221e-05 tokens_per_second_per_gpu:897.2429872523273 mfu:13.184730052440274 
Step 3780 | loss:1.9772107601165771 lr:2.9915058705571485e-05 tokens_per_second_per_gpu:850.353015978117 mfu:12.495695284600647 
Step 3781 | loss:2.0111465454101562 lr:2.9870182219917564e-05 tokens_per_second_per_gpu:868.3386588644518 mfu:12.759989182290623 
Step 3782 | loss:1.945361614227295 lr:2.9825333509213827e-05 tokens_per_second_per_gpu:875.0198772687456 mfu:12.858167783108417 
Step 3783 | loss:1.9742941856384277 lr:2.9780512591222553e-05 tokens_per_second_per_gpu:875.8620793003555 mfu:12.87054370200013 
Step 3784 | loss:1.9909251928329468 lr:2.973571948369517e-05 tokens_per_second_per_gpu:818.8942264190514 mfu:12.033417335365295 
Step 3785 | loss:2.0142171382904053 lr:2.9690954204371945e-05 tokens_per_second_per_gpu:864.5504565653276 mfu:12.70432262885125 
Step 3786 | loss:2.0200483798980713 lr:2.9646216770982248e-05 tokens_per_second_per_gpu:865.0801391613761 mfu:12.712106163681387 
Step 3787 | loss:2.008247137069702 lr:2.9601507201244305e-05 tokens_per_second_per_gpu:833.6013917365775 mfu:12.249534939295545 
Step 3788 | loss:1.9665664434432983 lr:2.9556825512865415e-05 tokens_per_second_per_gpu:860.3947677042738 mfu:12.643255965089722 
Step 3789 | loss:2.012071371078491 lr:2.9512171723541736e-05 tokens_per_second_per_gpu:879.5931720580568 mfu:12.925371047000121 
Step 3790 | loss:1.999335765838623 lr:2.9467545850958445e-05 tokens_per_second_per_gpu:898.7550930922541 mfu:13.20695001692415 
Step 3791 | loss:1.9845609664916992 lr:2.9422947912789678e-05 tokens_per_second_per_gpu:866.0026311402077 mfu:12.725661920471063 
Step 3792 | loss:1.935746669769287 lr:2.937837792669843e-05 tokens_per_second_per_gpu:857.9375805013224 mfu:12.607148299251687 
Step 3793 | loss:1.9877774715423584 lr:2.9333835910336628e-05 tokens_per_second_per_gpu:876.4473739358414 mfu:12.879144439904646 
Step 3794 | loss:1.9893449544906616 lr:2.9289321881345254e-05 tokens_per_second_per_gpu:901.2067333370679 mfu:13.242976171792808 
Step 3795 | loss:1.9475778341293335 lr:2.9244835857354068e-05 tokens_per_second_per_gpu:897.6398292980231 mfu:13.190561533232318 
Step 3796 | loss:1.9662426710128784 lr:2.920037785598172e-05 tokens_per_second_per_gpu:874.1590830462222 mfu:12.845518657268574 
Step 3797 | loss:1.9727134704589844 lr:2.9155947894835955e-05 tokens_per_second_per_gpu:819.2194474253388 mfu:12.038196365389718 
Step 3798 | loss:1.994917869567871 lr:2.91115459915132e-05 tokens_per_second_per_gpu:894.3664977381704 mfu:13.142460858607983 
Step 3799 | loss:2.0099258422851562 lr:2.9067172163598832e-05 tokens_per_second_per_gpu:884.6075658755708 mfu:12.999056135431974 
Step 3800 | loss:2.0467329025268555 lr:2.902282642866716e-05 tokens_per_second_per_gpu:840.8386962304278 mfu:12.35588506675761 
Step 3801 | loss:2.002835273742676 lr:2.8978508804281357e-05 tokens_per_second_per_gpu:853.3715428434003 mfu:12.540051676838022 
Step 3802 | loss:2.0110628604888916 lr:2.8934219307993394e-05 tokens_per_second_per_gpu:844.1874236891707 mfu:12.405093662634107 
Step 3803 | loss:1.9511666297912598 lr:2.8889957957344205e-05 tokens_per_second_per_gpu:881.2340661649765 mfu:12.949483518372709 
Step 3804 | loss:1.996299147605896 lr:2.8845724769863448e-05 tokens_per_second_per_gpu:886.9563550402314 mfu:13.033570922982426 
Step 3805 | loss:1.9957767724990845 lr:2.8801519763069774e-05 tokens_per_second_per_gpu:874.7339580544692 mfu:12.853966281719607 
Step 3806 | loss:1.9824793338775635 lr:2.8757342954470533e-05 tokens_per_second_per_gpu:883.3211020516513 mfu:12.980151916082708 
Step 3807 | loss:2.034233570098877 lr:2.8713194361562036e-05 tokens_per_second_per_gpu:861.9580304161404 mfu:12.666227665230979 
Step 3808 | loss:1.9831581115722656 lr:2.8669074001829288e-05 tokens_per_second_per_gpu:892.2254644069768 mfu:13.110998983835897 
Step 3809 | loss:1.9357396364212036 lr:2.8624981892746217e-05 tokens_per_second_per_gpu:866.3598469518058 mfu:12.730911105043472 
Step 3810 | loss:2.0291497707366943 lr:2.858091805177554e-05 tokens_per_second_per_gpu:833.5730539923943 mfu:12.24911852421885 
Step 3811 | loss:2.0355896949768066 lr:2.8536882496368766e-05 tokens_per_second_per_gpu:850.8845908563244 mfu:12.503506625977954 
Step 3812 | loss:1.989959955215454 lr:2.849287524396611e-05 tokens_per_second_per_gpu:898.9009871227869 mfu:13.209093888134253 
Step 3813 | loss:2.0118565559387207 lr:2.8448896311996797e-05 tokens_per_second_per_gpu:830.4919923343816 mfu:12.203843201019922 
Step 3814 | loss:2.001141309738159 lr:2.840494571787864e-05 tokens_per_second_per_gpu:863.9075645794369 mfu:12.694875514293347 
Step 3815 | loss:2.0189476013183594 lr:2.8361023479018278e-05 tokens_per_second_per_gpu:870.8703732641708 mfu:12.797192004050638 
Step 3816 | loss:1.968064308166504 lr:2.8317129612811156e-05 tokens_per_second_per_gpu:872.939021896776 mfu:12.82759020630104 
Step 3817 | loss:1.9954931735992432 lr:2.8273264136641485e-05 tokens_per_second_per_gpu:879.9132411832129 mfu:12.93007437159921 
Step 3818 | loss:2.0073506832122803 lr:2.8229427067882164e-05 tokens_per_second_per_gpu:892.570030948492 mfu:13.116062290988504 
Step 3819 | loss:1.993259310722351 lr:2.8185618423894944e-05 tokens_per_second_per_gpu:869.3737079744193 mfu:12.77519893405222 
Step 3820 | loss:1.9651752710342407 lr:2.814183822203019e-05 tokens_per_second_per_gpu:873.0289742453215 mfu:12.828912030433413 
Step 3821 | loss:1.9554290771484375 lr:2.809808647962715e-05 tokens_per_second_per_gpu:868.611096611815 mfu:12.763992577364325 
Step 3822 | loss:1.9678488969802856 lr:2.8054363214013647e-05 tokens_per_second_per_gpu:880.7660254351885 mfu:12.942605793204079 
Step 3823 | loss:2.0108938217163086 lr:2.801066844250637e-05 tokens_per_second_per_gpu:864.4569057681888 mfu:12.702947926542075 
Step 3824 | loss:1.9633593559265137 lr:2.7967002182410596e-05 tokens_per_second_per_gpu:889.179189894838 mfu:13.066234847833925 
Step 3825 | loss:1.9608832597732544 lr:2.7923364451020405e-05 tokens_per_second_per_gpu:857.2280963404893 mfu:12.596722631656656 
Step 3826 | loss:1.9998176097869873 lr:2.7879755265618555e-05 tokens_per_second_per_gpu:873.6585171626617 mfu:12.838162984232424 
Step 3827 | loss:2.0547895431518555 lr:2.7836174643476488e-05 tokens_per_second_per_gpu:865.7251660707493 mfu:12.721584650331573 
Step 3828 | loss:1.962439775466919 lr:2.7792622601854235e-05 tokens_per_second_per_gpu:881.6890903164104 mfu:12.95616996863115 
Step 3829 | loss:1.9713730812072754 lr:2.7749099158000748e-05 tokens_per_second_per_gpu:866.269706817077 mfu:12.729586521446635 
Step 3830 | loss:2.008824348449707 lr:2.7705604329153434e-05 tokens_per_second_per_gpu:891.3994848604583 mfu:13.09886144974044 
Step 3831 | loss:2.0545880794525146 lr:2.7662138132538428e-05 tokens_per_second_per_gpu:888.7239395950993 mfu:13.05954507439058 
Step 3832 | loss:2.0039660930633545 lr:2.7618700585370562e-05 tokens_per_second_per_gpu:872.3171887514046 mfu:12.81845254540442 
Step 3833 | loss:1.955275058746338 lr:2.7575291704853323e-05 tokens_per_second_per_gpu:874.184351311771 mfu:12.845889967231301 
Step 3834 | loss:1.9937231540679932 lr:2.7531911508178765e-05 tokens_per_second_per_gpu:868.4522593080095 mfu:12.761658508441318 
Step 3835 | loss:1.9509367942810059 lr:2.7488560012527675e-05 tokens_per_second_per_gpu:876.6975492082915 mfu:12.882820694252594 
Step 3836 | loss:2.0401339530944824 lr:2.7445237235069455e-05 tokens_per_second_per_gpu:864.6297223328926 mfu:12.70548741672097 
Step 3837 | loss:1.996443271636963 lr:2.7401943192962088e-05 tokens_per_second_per_gpu:867.3181686109913 mfu:12.744993368777244 
Step 3838 | loss:1.9950228929519653 lr:2.735867790335217e-05 tokens_per_second_per_gpu:891.478930228489 mfu:13.100028876787833 
Step 3839 | loss:1.9496967792510986 lr:2.7315441383374964e-05 tokens_per_second_per_gpu:847.8100579774131 mfu:12.45832724132772 
Step 3840 | loss:1.9772733449935913 lr:2.7272233650154355e-05 tokens_per_second_per_gpu:877.5015131082449 mfu:12.89463471469454 
Step 3841 | loss:2.0078659057617188 lr:2.7229054720802728e-05 tokens_per_second_per_gpu:894.3514831475848 mfu:13.142240223477328 
Step 3842 | loss:2.0082027912139893 lr:2.7185904612421176e-05 tokens_per_second_per_gpu:857.6800912937572 mfu:12.603364568711134 
Step 3843 | loss:2.010728597640991 lr:2.7142783342099264e-05 tokens_per_second_per_gpu:883.3789466263056 mfu:12.981001925625998 
Step 3844 | loss:1.9949952363967896 lr:2.7099690926915222e-05 tokens_per_second_per_gpu:875.331525436547 mfu:12.862747364138503 
Step 3845 | loss:1.972931146621704 lr:2.7056627383935852e-05 tokens_per_second_per_gpu:888.0039234801385 mfu:13.048964642730438 
Step 3846 | loss:2.0015645027160645 lr:2.7013592730216465e-05 tokens_per_second_per_gpu:872.8401983230416 mfu:12.826138022042128 
Step 3847 | loss:1.9983298778533936 lr:2.6970586982800915e-05 tokens_per_second_per_gpu:878.6839657472065 mfu:12.912010519316036 
Step 3848 | loss:1.976937174797058 lr:2.6927610158721706e-05 tokens_per_second_per_gpu:889.3360238958838 mfu:13.068539478793667 
Step 3849 | loss:2.0377063751220703 lr:2.6884662274999837e-05 tokens_per_second_per_gpu:864.7496449891034 mfu:12.707249645985256 
Step 3850 | loss:2.000253677368164 lr:2.6841743348644787e-05 tokens_per_second_per_gpu:900.4839957611739 mfu:13.232355749039659 
Step 3851 | loss:1.991971731185913 lr:2.6798853396654657e-05 tokens_per_second_per_gpu:891.0593938863113 mfu:13.093863909775118 
Step 3852 | loss:1.9986681938171387 lr:2.675599243601605e-05 tokens_per_second_per_gpu:903.5844650509658 mfu:13.2779162618579 
Step 3853 | loss:2.00386905670166 lr:2.6713160483704057e-05 tokens_per_second_per_gpu:884.2990034078184 mfu:12.99452189788492 
Step 3854 | loss:1.9722329378128052 lr:2.6670357556682247e-05 tokens_per_second_per_gpu:901.3740164977949 mfu:13.245434350176856 
Step 3855 | loss:1.979443073272705 lr:2.662758367190279e-05 tokens_per_second_per_gpu:853.1732799751849 mfu:12.537138260479264 
Step 3856 | loss:1.9992797374725342 lr:2.6584838846306316e-05 tokens_per_second_per_gpu:881.8868881589019 mfu:12.95907655156939 
Step 3857 | loss:1.9870784282684326 lr:2.654212309682189e-05 tokens_per_second_per_gpu:893.2629140476444 mfu:13.126244010712162 
Step 3858 | loss:1.9429800510406494 lr:2.6499436440367165e-05 tokens_per_second_per_gpu:885.7196290334026 mfu:13.015397586683855 
Step 3859 | loss:2.0452117919921875 lr:2.6456778893848144e-05 tokens_per_second_per_gpu:882.880964628979 mfu:12.973684222061848 
Step 3860 | loss:1.9861165285110474 lr:2.6414150474159403e-05 tokens_per_second_per_gpu:897.5679480815012 mfu:13.189505259236144 
Step 3861 | loss:1.9976716041564941 lr:2.6371551198183984e-05 tokens_per_second_per_gpu:849.5628617569122 mfu:12.484084193453214 
Step 3862 | loss:2.0251240730285645 lr:2.6328981082793313e-05 tokens_per_second_per_gpu:889.1123423172912 mfu:13.065252541728292 
Step 3863 | loss:1.994389295578003 lr:2.628644014484729e-05 tokens_per_second_per_gpu:890.7409737223358 mfu:13.08918481619075 
Step 3864 | loss:1.985317349433899 lr:2.6243928401194297e-05 tokens_per_second_per_gpu:844.6416323808996 mfu:12.411768129944525 
Step 3865 | loss:1.9823588132858276 lr:2.620144586867116e-05 tokens_per_second_per_gpu:894.141193754722 mfu:13.139150080765512 
Step 3866 | loss:1.987699270248413 lr:2.6158992564103058e-05 tokens_per_second_per_gpu:870.7278181654857 mfu:12.795097197492698 
Step 3867 | loss:1.9975814819335938 lr:2.6116568504303653e-05 tokens_per_second_per_gpu:874.1707919242218 mfu:12.84569071589465 
Step 3868 | loss:1.9573695659637451 lr:2.6074173706075065e-05 tokens_per_second_per_gpu:881.4188889902414 mfu:12.952199437129687 
Step 3869 | loss:1.964369535446167 lr:2.603180818620774e-05 tokens_per_second_per_gpu:866.3121452067495 mfu:12.730210141491195 
Step 3870 | loss:2.02445650100708 lr:2.598947196148053e-05 tokens_per_second_per_gpu:858.4553887015098 mfu:12.614757343217937 
Step 3871 | loss:1.9571888446807861 lr:2.5947165048660747e-05 tokens_per_second_per_gpu:884.6501262577847 mfu:12.999681548122172 
Step 3872 | loss:1.9555881023406982 lr:2.5904887464504114e-05 tokens_per_second_per_gpu:877.1464201493724 mfu:12.889416724838087 
Step 3873 | loss:1.9826551675796509 lr:2.5862639225754605e-05 tokens_per_second_per_gpu:875.3810481671368 mfu:12.86347508655435 
Step 3874 | loss:1.9876790046691895 lr:2.5820420349144693e-05 tokens_per_second_per_gpu:887.7664843589401 mfu:13.045475542496312 
Step 3875 | loss:1.996458888053894 lr:2.5778230851395223e-05 tokens_per_second_per_gpu:880.0835206432257 mfu:12.93257657974755 
Step 3876 | loss:1.99202299118042 lr:2.5736070749215313e-05 tokens_per_second_per_gpu:863.4766173226869 mfu:12.688542867142226 
Step 3877 | loss:1.9912629127502441 lr:2.5693940059302536e-05 tokens_per_second_per_gpu:906.5915063379352 mfu:13.32210387679446 
Step 3878 | loss:2.0047264099121094 lr:2.565183879834272e-05 tokens_per_second_per_gpu:886.0374557017416 mfu:13.020067959018945 
Step 3879 | loss:1.9495360851287842 lr:2.5609766983010118e-05 tokens_per_second_per_gpu:859.1205987143902 mfu:12.62453241482353 
Step 3880 | loss:1.9782285690307617 lr:2.556772462996734e-05 tokens_per_second_per_gpu:854.5656707500699 mfu:12.557599046191934 
Step 3881 | loss:1.9973645210266113 lr:2.5525711755865235e-05 tokens_per_second_per_gpu:869.0206262964022 mfu:12.770010499394875 
Step 3882 | loss:1.9935178756713867 lr:2.5483728377342984e-05 tokens_per_second_per_gpu:887.3162662726912 mfu:13.038859715996407 
Step 3883 | loss:1.93925142288208 lr:2.5441774511028184e-05 tokens_per_second_per_gpu:862.5464467820358 mfu:12.67487427607441 
Step 3884 | loss:1.9792828559875488 lr:2.53998501735367e-05 tokens_per_second_per_gpu:857.8902497200947 mfu:12.60645278690718 
Step 3885 | loss:1.9528491497039795 lr:2.535795538147262e-05 tokens_per_second_per_gpu:864.7923823085835 mfu:12.707877658718166 
Step 3886 | loss:2.032759666442871 lr:2.531609015142844e-05 tokens_per_second_per_gpu:891.1282502152412 mfu:13.094875733909985 
Step 3887 | loss:1.981986165046692 lr:2.5274254499984928e-05 tokens_per_second_per_gpu:902.0745610061772 mfu:13.255728652126237 
Step 3888 | loss:1.9641575813293457 lr:2.5232448443711088e-05 tokens_per_second_per_gpu:869.418706802349 mfu:12.775860179007442 
Step 3889 | loss:1.9757320880889893 lr:2.5190671999164205e-05 tokens_per_second_per_gpu:876.2559192099544 mfu:12.876331067257608 
Step 3890 | loss:1.9985671043395996 lr:2.514892518288988e-05 tokens_per_second_per_gpu:858.1166716740076 mfu:12.60977999300709 
Step 3891 | loss:1.9598054885864258 lr:2.5107208011422013e-05 tokens_per_second_per_gpu:866.8032524999205 mfu:12.737426823236543 
Step 3892 | loss:2.025679111480713 lr:2.5065520501282613e-05 tokens_per_second_per_gpu:897.9671175491299 mfu:13.195370940830356 
Step 3893 | loss:1.992440104484558 lr:2.5023862668982135e-05 tokens_per_second_per_gpu:879.5090308179641 mfu:12.92413461545074 
Step 3894 | loss:1.9971227645874023 lr:2.498223453101911e-05 tokens_per_second_per_gpu:880.6245048816277 mfu:12.940526188991974 
Step 3895 | loss:2.033506155014038 lr:2.494063610388041e-05 tokens_per_second_per_gpu:879.2038541702776 mfu:12.919650131564858 
Step 3896 | loss:1.9601413011550903 lr:2.4899067404041153e-05 tokens_per_second_per_gpu:871.6241341396383 mfu:12.808268305351765 
Step 3897 | loss:1.9744492769241333 lr:2.4857528447964606e-05 tokens_per_second_per_gpu:854.1048537836136 mfu:12.550827472167247 
Step 3898 | loss:1.9751064777374268 lr:2.4816019252102273e-05 tokens_per_second_per_gpu:859.9035632746522 mfu:12.636037855951908 
Step 3899 | loss:1.9895445108413696 lr:2.4774539832893916e-05 tokens_per_second_per_gpu:811.1056997807686 mfu:11.918967155546703 
Step 3900 | loss:2.013302803039551 lr:2.4733090206767507e-05 tokens_per_second_per_gpu:849.4388539911054 mfu:12.482261934667356 
Step 3901 | loss:1.985168218612671 lr:2.469167039013913e-05 tokens_per_second_per_gpu:879.3339420335153 mfu:12.921561735650101 
Step 3902 | loss:1.9853745698928833 lr:2.465028039941316e-05 tokens_per_second_per_gpu:862.6072983442526 mfu:12.675768472443172 
Step 3903 | loss:1.9493046998977661 lr:2.460892025098216e-05 tokens_per_second_per_gpu:880.4460791626025 mfu:12.937904273888503 
Step 3904 | loss:1.93938148021698 lr:2.45675899612268e-05 tokens_per_second_per_gpu:860.7275857629211 mfu:12.648146631633997 
Step 3905 | loss:1.993473768234253 lr:2.4526289546515936e-05 tokens_per_second_per_gpu:897.9238029170835 mfu:13.194734444653772 
Step 3906 | loss:1.9781622886657715 lr:2.4485019023206635e-05 tokens_per_second_per_gpu:865.7321728008532 mfu:12.721687612234073 
Step 3907 | loss:1.9721293449401855 lr:2.4443778407644158e-05 tokens_per_second_per_gpu:898.4903204014485 mfu:13.20305925767261 
Step 3908 | loss:2.024721622467041 lr:2.4402567716161805e-05 tokens_per_second_per_gpu:861.7939797243681 mfu:12.663816987057213 
Step 3909 | loss:1.9875919818878174 lr:2.4361386965081146e-05 tokens_per_second_per_gpu:851.8524946182552 mfu:12.517729695981409 
Step 3910 | loss:1.9669619798660278 lr:2.4320236170711786e-05 tokens_per_second_per_gpu:846.5190351680341 mfu:12.439356028986086 
Step 3911 | loss:1.9974863529205322 lr:2.4279115349351543e-05 tokens_per_second_per_gpu:875.1114305652183 mfu:12.859513132714435 
Step 3912 | loss:1.9531172513961792 lr:2.423802451728636e-05 tokens_per_second_per_gpu:904.166294567946 mfu:13.286466080833268 
Step 3913 | loss:2.00573468208313 lr:2.4196963690790254e-05 tokens_per_second_per_gpu:869.1553122618956 mfu:12.771989671282661 
Step 3914 | loss:1.969864010810852 lr:2.415593288612541e-05 tokens_per_second_per_gpu:895.6870487686849 mfu:13.16186597974593 
Step 3915 | loss:1.9793306589126587 lr:2.4114932119542067e-05 tokens_per_second_per_gpu:890.9185970344689 mfu:13.091794940153566 
Step 3916 | loss:1.9992142915725708 lr:2.4073961407278632e-05 tokens_per_second_per_gpu:848.6661044149439 mfu:12.470906599819852 
Step 3917 | loss:1.9655121564865112 lr:2.4033020765561544e-05 tokens_per_second_per_gpu:870.8221214220579 mfu:12.796482956978853 
Step 3918 | loss:1.979469656944275 lr:2.399211021060538e-05 tokens_per_second_per_gpu:879.7748456183434 mfu:12.928040688205543 
Step 3919 | loss:1.9904104471206665 lr:2.3951229758612816e-05 tokens_per_second_per_gpu:899.207491144278 mfu:13.213597877399996 
Step 3920 | loss:1.9606883525848389 lr:2.391037942577454e-05 tokens_per_second_per_gpu:882.4341156587071 mfu:12.967117903761284 
Step 3921 | loss:2.018141746520996 lr:2.386955922826931e-05 tokens_per_second_per_gpu:861.5094429252463 mfu:12.659635799865217 
Step 3922 | loss:1.9673376083374023 lr:2.382876918226409e-05 tokens_per_second_per_gpu:861.818483179079 mfu:12.664177058342588 
Step 3923 | loss:2.0249907970428467 lr:2.378800930391374e-05 tokens_per_second_per_gpu:863.9339289356313 mfu:12.695262930995813 
Step 3924 | loss:1.9951293468475342 lr:2.3747279609361196e-05 tokens_per_second_per_gpu:896.2687306310714 mfu:13.170413628979114 
Step 3925 | loss:2.003561019897461 lr:2.3706580114737507e-05 tokens_per_second_per_gpu:829.8876393477839 mfu:12.19496240607598 
Step 3926 | loss:1.9849011898040771 lr:2.3665910836161775e-05 tokens_per_second_per_gpu:874.5013774887949 mfu:12.850548576574592 
Step 3927 | loss:1.9991004467010498 lr:2.3625271789741e-05 tokens_per_second_per_gpu:896.7466956253623 mfu:13.177437188386962 
Step 3928 | loss:2.0376152992248535 lr:2.3584662991570382e-05 tokens_per_second_per_gpu:874.3008011263311 mfu:12.847601164077023 
Step 3929 | loss:1.9797098636627197 lr:2.3544084457732983e-05 tokens_per_second_per_gpu:893.9361137358319 mfu:13.136136488319952 
Step 3930 | loss:1.969780683517456 lr:2.3503536204300015e-05 tokens_per_second_per_gpu:849.3402541028528 mfu:12.480813037402868 
Step 3931 | loss:1.97658371925354 lr:2.346301824733057e-05 tokens_per_second_per_gpu:874.3781854135254 mfu:12.848738304128775 
Step 3932 | loss:1.965350866317749 lr:2.3422530602871872e-05 tokens_per_second_per_gpu:864.4410881769998 mfu:12.70271549154635 
Step 3933 | loss:1.9726221561431885 lr:2.3382073286959015e-05 tokens_per_second_per_gpu:883.7563734616114 mfu:12.986548105433203 
Step 3934 | loss:1.9910743236541748 lr:2.3341646315615162e-05 tokens_per_second_per_gpu:843.9644080464982 mfu:12.401816511307336 
Step 3935 | loss:1.9782392978668213 lr:2.330124970485148e-05 tokens_per_second_per_gpu:891.0732254582402 mfu:13.094067160783679 
Step 3936 | loss:2.0239386558532715 lr:2.3260883470667016e-05 tokens_per_second_per_gpu:882.6297033952757 mfu:12.9699920098227 
Step 3937 | loss:1.9542698860168457 lr:2.3220547629048796e-05 tokens_per_second_per_gpu:857.3572963632087 mfu:12.598621189178449 
Step 3938 | loss:2.011101722717285 lr:2.318024219597196e-05 tokens_per_second_per_gpu:878.5801159282968 mfu:12.910484475816366 
Step 3939 | loss:2.01767897605896 lr:2.3139967187399424e-05 tokens_per_second_per_gpu:889.3016803614298 mfu:13.06803481034013 
Step 3940 | loss:1.97054922580719 lr:2.3099722619282127e-05 tokens_per_second_per_gpu:891.2964585048929 mfu:13.097347506799993 
Step 3941 | loss:1.9631699323654175 lr:2.3059508507558968e-05 tokens_per_second_per_gpu:901.187403314302 mfu:13.24269212261583 
Step 3942 | loss:2.010270595550537 lr:2.3019324868156777e-05 tokens_per_second_per_gpu:891.8538761286558 mfu:13.105538599960045 
Step 3943 | loss:1.9774436950683594 lr:2.297917171699028e-05 tokens_per_second_per_gpu:836.485804925583 mfu:12.2919205692721 
Step 3944 | loss:2.035649538040161 lr:2.2939049069962183e-05 tokens_per_second_per_gpu:899.844498685102 mfu:13.222958521714256 
Step 3945 | loss:2.0108354091644287 lr:2.2898956942963025e-05 tokens_per_second_per_gpu:837.0706511083839 mfu:12.300514717292186 
Step 3946 | loss:1.9791442155838013 lr:2.285889535187139e-05 tokens_per_second_per_gpu:838.9233071292073 mfu:12.327738969653732 
Step 3947 | loss:1.955800175666809 lr:2.281886431255361e-05 tokens_per_second_per_gpu:878.157454660034 mfu:12.904273588905195 
Step 3948 | loss:1.9385216236114502 lr:2.2778863840864083e-05 tokens_per_second_per_gpu:878.464282815572 mfu:12.908782341228404 
Step 3949 | loss:1.9876153469085693 lr:2.2738893952644936e-05 tokens_per_second_per_gpu:862.8586124394747 mfu:12.679461461467273 
Step 3950 | loss:1.9356188774108887 lr:2.26989546637263e-05 tokens_per_second_per_gpu:852.530347553375 mfu:12.527690551727051 
Step 3951 | loss:1.9550230503082275 lr:2.2659045989926187e-05 tokens_per_second_per_gpu:885.7789402659264 mfu:13.016269148346653 
Step 3952 | loss:1.939584732055664 lr:2.261916794705038e-05 tokens_per_second_per_gpu:827.8540605842658 mfu:12.165079545559601 
Step 3953 | loss:2.0371599197387695 lr:2.2579320550892635e-05 tokens_per_second_per_gpu:888.5960837564953 mfu:13.057666269271373 
Step 3954 | loss:1.9718132019042969 lr:2.2539503817234553e-05 tokens_per_second_per_gpu:855.1112196532806 mfu:12.565615731885144 
Step 3955 | loss:1.9733123779296875 lr:2.249971776184554e-05 tokens_per_second_per_gpu:862.3146075428068 mfu:12.67146746451029 
Step 3956 | loss:1.9601136445999146 lr:2.2459962400482847e-05 tokens_per_second_per_gpu:887.9450255996552 mfu:13.0480991551581 
Step 3957 | loss:1.9246476888656616 lr:2.2420237748891702e-05 tokens_per_second_per_gpu:846.20663130102 mfu:12.434765343171387 
Step 3958 | loss:2.0636188983917236 lr:2.238054382280502e-05 tokens_per_second_per_gpu:836.5540457687305 mfu:12.29292334901876 
Step 3959 | loss:2.0142056941986084 lr:2.2340880637943572e-05 tokens_per_second_per_gpu:878.5262596348557 mfu:12.909693072929151 
Step 3960 | loss:1.9849109649658203 lr:2.2301248210016023e-05 tokens_per_second_per_gpu:895.2396837745762 mfu:13.155292078622113 
Step 3961 | loss:1.959662914276123 lr:2.2261646554718817e-05 tokens_per_second_per_gpu:895.1601032366027 mfu:13.154122665290924 
Step 3962 | loss:1.9980826377868652 lr:2.2222075687736187e-05 tokens_per_second_per_gpu:906.3807621514608 mfu:13.3190070510201 
Step 3963 | loss:1.9747467041015625 lr:2.218253562474023e-05 tokens_per_second_per_gpu:873.2823015693808 mfu:12.832634603281665 
Step 3964 | loss:1.9935234785079956 lr:2.2143026381390753e-05 tokens_per_second_per_gpu:870.6615792672685 mfu:12.794123835756388 
Step 3965 | loss:1.9514471292495728 lr:2.210354797333547e-05 tokens_per_second_per_gpu:870.0145852202318 mfu:12.784616442578717 
Step 3966 | loss:2.001617431640625 lr:2.2064100416209775e-05 tokens_per_second_per_gpu:895.1493564407706 mfu:13.153964744188182 
Step 3967 | loss:1.9796603918075562 lr:2.202468372563694e-05 tokens_per_second_per_gpu:871.2016411471334 mfu:12.802059891204909 
Step 3968 | loss:1.9898910522460938 lr:2.198529791722792e-05 tokens_per_second_per_gpu:845.429550746693 mfu:12.423346365833734 
Step 3969 | loss:1.9566094875335693 lr:2.1945943006581504e-05 tokens_per_second_per_gpu:855.7520522695568 mfu:12.57503258459332 
Step 3970 | loss:1.9808695316314697 lr:2.1906619009284257e-05 tokens_per_second_per_gpu:877.0713390025726 mfu:12.888313428778215 
Step 3971 | loss:1.9820764064788818 lr:2.1867325940910434e-05 tokens_per_second_per_gpu:893.2456622348358 mfu:13.12599050023838 
Step 3972 | loss:1.9702036380767822 lr:2.1828063817022025e-05 tokens_per_second_per_gpu:904.6387823877006 mfu:13.29340915472188 
Step 3973 | loss:2.0022871494293213 lr:2.1788832653168923e-05 tokens_per_second_per_gpu:883.2641825038526 mfu:12.979315499545498 
Step 3974 | loss:2.043958902359009 lr:2.1749632464888592e-05 tokens_per_second_per_gpu:894.7341072163871 mfu:13.147862775149951 
Step 3975 | loss:1.9564896821975708 lr:2.171046326770627e-05 tokens_per_second_per_gpu:871.133901582708 mfu:12.801064477606243 
Step 3976 | loss:2.0087571144104004 lr:2.1671325077134963e-05 tokens_per_second_per_gpu:882.3720743480382 mfu:12.966206224378006 
Step 3977 | loss:1.9653489589691162 lr:2.163221790867538e-05 tokens_per_second_per_gpu:884.3453514768369 mfu:12.995202969553512 
Step 3978 | loss:1.9673714637756348 lr:2.1593141777815906e-05 tokens_per_second_per_gpu:854.3717627962315 mfu:12.554749624059129 
Step 3979 | loss:2.04042911529541 lr:2.15540967000327e-05 tokens_per_second_per_gpu:878.4271393364656 mfu:12.90823652838597 
Step 3980 | loss:2.0332162380218506 lr:2.1515082690789535e-05 tokens_per_second_per_gpu:883.4255346203373 mfu:12.9816865229243 
Step 3981 | loss:2.0076920986175537 lr:2.1476099765537983e-05 tokens_per_second_per_gpu:873.7101758702386 mfu:12.838922094221507 
Step 3982 | loss:1.9988222122192383 lr:2.1437147939717193e-05 tokens_per_second_per_gpu:868.2005706520351 mfu:12.75796001535368 
Step 3983 | loss:1.997801423072815 lr:2.139822722875413e-05 tokens_per_second_per_gpu:830.9140863226531 mfu:12.210045751913254 
Step 3984 | loss:1.969224214553833 lr:2.1359337648063284e-05 tokens_per_second_per_gpu:857.8629718339029 mfu:12.606051946141688 
Step 3985 | loss:1.995415210723877 lr:2.132047921304693e-05 tokens_per_second_per_gpu:869.7018330804161 mfu:12.780020638994428 
Step 3986 | loss:1.994191288948059 lr:2.1281651939094992e-05 tokens_per_second_per_gpu:866.1350843494849 mfu:12.727608282642416 
Step 3987 | loss:1.9893715381622314 lr:2.1242855841585017e-05 tokens_per_second_per_gpu:876.7913294956907 mfu:12.884198768855756 
Step 3988 | loss:1.987149715423584 lr:2.120409093588216e-05 tokens_per_second_per_gpu:877.8353253209364 mfu:12.899539990049238 
Step 3989 | loss:1.969136118888855 lr:2.116535723733938e-05 tokens_per_second_per_gpu:856.5703397742345 mfu:12.587057086325567 
Step 3990 | loss:2.002110004425049 lr:2.112665476129714e-05 tokens_per_second_per_gpu:856.1802440142992 mfu:12.581324740280602 
Step 3991 | loss:1.940999984741211 lr:2.1087983523083532e-05 tokens_per_second_per_gpu:826.4083219519487 mfu:12.143834828282 
Step 3992 | loss:2.0235345363616943 lr:2.1049343538014355e-05 tokens_per_second_per_gpu:848.4967918922114 mfu:12.46841860053934 
Step 3993 | loss:1.990661382675171 lr:2.1010734821393018e-05 tokens_per_second_per_gpu:889.100468701673 mfu:13.065078062329848 
Step 3994 | loss:2.000072479248047 lr:2.0972157388510484e-05 tokens_per_second_per_gpu:877.4329776375941 mfu:12.893627605480663 
Step 3995 | loss:2.042841672897339 lr:2.0933611254645367e-05 tokens_per_second_per_gpu:862.7459518588538 mfu:12.67780594633465 
Step 3996 | loss:1.9518094062805176 lr:2.0895096435063943e-05 tokens_per_second_per_gpu:867.9309727357445 mfu:12.753998350788457 
Step 3997 | loss:1.938826084136963 lr:2.085661294501996e-05 tokens_per_second_per_gpu:875.1361547203003 mfu:12.859876447128883 
Step 3998 | loss:1.9680956602096558 lr:2.0818160799754828e-05 tokens_per_second_per_gpu:892.2581060903043 mfu:13.111478644072024 
Step 3999 | loss:1.9867699146270752 lr:2.077974001449755e-05 tokens_per_second_per_gpu:879.2311262921792 mfu:12.920050887625743 
Step 4000 | loss:1.9993252754211426 lr:2.0741350604464728e-05 tokens_per_second_per_gpu:829.8720339249414 mfu:12.194733088833656 
Step 4001 | loss:2.0123190879821777 lr:2.0702992584860458e-05 tokens_per_second_per_gpu:863.1687385945257 mfu:12.684018676953652 
Step 4002 | loss:1.9963710308074951 lr:2.0664665970876496e-05 tokens_per_second_per_gpu:886.4708015895743 mfu:13.026435853370403 
Step 4003 | loss:2.019514560699463 lr:2.0626370777692083e-05 tokens_per_second_per_gpu:878.1014009647812 mfu:12.903449895824446 
Step 4004 | loss:1.9820778369903564 lr:2.0588107020474056e-05 tokens_per_second_per_gpu:885.4038988386426 mfu:13.010758021430677 
Step 4005 | loss:1.9870787858963013 lr:2.0549874714376827e-05 tokens_per_second_per_gpu:889.3731448243303 mfu:13.069084960260579 
Step 4006 | loss:2.0698211193084717 lr:2.0511673874542302e-05 tokens_per_second_per_gpu:883.1096427899704 mfu:12.97704458248193 
Step 4007 | loss:1.9726399183273315 lr:2.0473504516099906e-05 tokens_per_second_per_gpu:831.5512225835622 mfu:12.219408287732488 
Step 4008 | loss:1.9392547607421875 lr:2.0435366654166677e-05 tokens_per_second_per_gpu:903.1427062208126 mfu:13.271424741716084 
Step 4009 | loss:1.9933669567108154 lr:2.0397260303847143e-05 tokens_per_second_per_gpu:889.3572316998456 mfu:13.06885112143029 
Step 4010 | loss:2.0262551307678223 lr:2.03591854802333e-05 tokens_per_second_per_gpu:864.6472447707896 mfu:12.70574490395332 
Step 4011 | loss:2.0347726345062256 lr:2.0321142198404718e-05 tokens_per_second_per_gpu:867.4123240006958 mfu:12.746376955401908 
Step 4012 | loss:1.976203441619873 lr:2.028313047342849e-05 tokens_per_second_per_gpu:830.4055686030971 mfu:12.202573228912811 
Step 4013 | loss:1.9441492557525635 lr:2.0245150320359164e-05 tokens_per_second_per_gpu:872.4532345487195 mfu:12.820451699633374 
Step 4014 | loss:1.9823532104492188 lr:2.0207201754238758e-05 tokens_per_second_per_gpu:847.0026665134106 mfu:12.446462853808665 
Step 4015 | loss:1.992997407913208 lr:2.0169284790096853e-05 tokens_per_second_per_gpu:890.0783367604828 mfu:13.079447554836882 
Step 4016 | loss:1.9609706401824951 lr:2.0131399442950505e-05 tokens_per_second_per_gpu:865.4713056498492 mfu:12.71785424377714 
Step 4017 | loss:1.9794344902038574 lr:2.0093545727804176e-05 tokens_per_second_per_gpu:893.1709080167636 mfu:13.12489200830301 
Step 4018 | loss:1.9608967304229736 lr:2.0055723659649904e-05 tokens_per_second_per_gpu:867.6988499392605 mfu:12.750587372431266 
Step 4019 | loss:1.9878236055374146 lr:2.001793325346708e-05 tokens_per_second_per_gpu:891.2644623759718 mfu:13.096877332801933 
Step 4020 | loss:1.9880212545394897 lr:1.9980174524222638e-05 tokens_per_second_per_gpu:839.3814433379811 mfu:12.334471150708083 
Step 4021 | loss:1.9670683145523071 lr:1.9942447486870987e-05 tokens_per_second_per_gpu:864.7797594303581 mfu:12.707692169119195 
Step 4022 | loss:2.0160534381866455 lr:1.9904752156353878e-05 tokens_per_second_per_gpu:900.8432926949602 mfu:13.237635515109659 
Step 4023 | loss:1.9712629318237305 lr:1.9867088547600555e-05 tokens_per_second_per_gpu:861.9560229760854 mfu:12.666198166471334 
Step 4024 | loss:1.9593632221221924 lr:1.982945667552778e-05 tokens_per_second_per_gpu:905.8925328415658 mfu:13.31183266041899 
Step 4025 | loss:2.005310297012329 lr:1.9791856555039646e-05 tokens_per_second_per_gpu:881.4538478174909 mfu:12.952713147135544 
Step 4026 | loss:1.9532418251037598 lr:1.975428820102766e-05 tokens_per_second_per_gpu:859.3362743410939 mfu:12.62770170670698 
Step 4027 | loss:1.9806163311004639 lr:1.9716751628370813e-05 tokens_per_second_per_gpu:896.6617182036971 mfu:13.176188469387618 
Step 4028 | loss:2.037324905395508 lr:1.967924685193552e-05 tokens_per_second_per_gpu:856.0766175223107 mfu:12.579801978506408 
Step 4029 | loss:2.0227913856506348 lr:1.9641773886575534e-05 tokens_per_second_per_gpu:895.2509865819197 mfu:13.155458170155594 
Step 4030 | loss:2.0355958938598633 lr:1.9604332747131993e-05 tokens_per_second_per_gpu:895.388208668619 mfu:13.1574746096219 
Step 4031 | loss:2.028958797454834 lr:1.9566923448433584e-05 tokens_per_second_per_gpu:869.7216053281236 mfu:12.78031118654092 
Step 4032 | loss:1.979203462600708 lr:1.952954600529623e-05 tokens_per_second_per_gpu:877.6924409136839 mfu:12.897440344395728 
Step 4033 | loss:1.9739985466003418 lr:1.9492200432523245e-05 tokens_per_second_per_gpu:893.5156462818416 mfu:13.129957838884444 
Step 4034 | loss:1.9457659721374512 lr:1.94548867449054e-05 tokens_per_second_per_gpu:849.7763059790133 mfu:12.487220695481804 
Step 4035 | loss:1.9732264280319214 lr:1.9417604957220824e-05 tokens_per_second_per_gpu:878.7620891313416 mfu:12.913158520186744 
Step 4036 | loss:1.986278772354126 lr:1.938035508423495e-05 tokens_per_second_per_gpu:893.7654143655546 mfu:13.133628109709917 
Step 4037 | loss:1.9313188791275024 lr:1.934313714070064e-05 tokens_per_second_per_gpu:854.5438638545747 mfu:12.55727860007592 
Step 4038 | loss:2.0044729709625244 lr:1.9305951141358026e-05 tokens_per_second_per_gpu:880.187406597386 mfu:12.934103154244431 
Step 4039 | loss:1.9432793855667114 lr:1.9268797100934688e-05 tokens_per_second_per_gpu:873.1226598622683 mfu:12.830288713881254 
Step 4040 | loss:1.9894516468048096 lr:1.9231675034145513e-05 tokens_per_second_per_gpu:859.6169670286813 mfu:12.63182640577525 
Step 4041 | loss:1.9856234788894653 lr:1.9194584955692706e-05 tokens_per_second_per_gpu:836.9232076483999 mfu:12.298348077657764 
Step 4042 | loss:1.9958131313323975 lr:1.9157526880265765e-05 tokens_per_second_per_gpu:863.7612187548851 mfu:12.692725004098863 
Step 4043 | loss:1.9557418823242188 lr:1.9120500822541587e-05 tokens_per_second_per_gpu:872.5676781187977 mfu:12.822133415288059 
Step 4044 | loss:1.9578697681427002 lr:1.9083506797184402e-05 tokens_per_second_per_gpu:891.876827443404 mfu:13.10587586299091 
Step 4045 | loss:1.9777175188064575 lr:1.9046544818845658e-05 tokens_per_second_per_gpu:848.5126415951999 mfu:12.468651507408811 
Step 4046 | loss:1.9549980163574219 lr:1.9009614902164174e-05 tokens_per_second_per_gpu:877.9783404698258 mfu:12.901641556913852 
Step 4047 | loss:1.9968510866165161 lr:1.897271706176611e-05 tokens_per_second_per_gpu:876.8806815542184 mfu:12.885511771897358 
Step 4048 | loss:1.9654157161712646 lr:1.893585131226484e-05 tokens_per_second_per_gpu:847.5554438199368 mfu:12.454585758829056 
Step 4049 | loss:1.968023419380188 lr:1.8899017668261033e-05 tokens_per_second_per_gpu:886.2721423361987 mfu:13.023516612244654 
Step 4050 | loss:2.051478147506714 lr:1.8862216144342692e-05 tokens_per_second_per_gpu:882.6842382726144 mfu:12.97079338430695 
Step 4051 | loss:1.9787535667419434 lr:1.882544675508513e-05 tokens_per_second_per_gpu:899.7824975136579 mfu:13.222047432165448 
Step 4052 | loss:1.950944185256958 lr:1.8788709515050808e-05 tokens_per_second_per_gpu:871.8016041639859 mfu:12.810876176794247 
Step 4053 | loss:1.9758644104003906 lr:1.8752004438789583e-05 tokens_per_second_per_gpu:865.6992890776146 mfu:12.721204395290412 
Step 4054 | loss:2.006063938140869 lr:1.8715331540838487e-05 tokens_per_second_per_gpu:847.3855959701725 mfu:12.452089893070342 
Step 4055 | loss:1.9874831438064575 lr:1.8678690835721836e-05 tokens_per_second_per_gpu:896.3961035735407 mfu:13.172285338077208 
Step 4056 | loss:2.011972427368164 lr:1.864208233795125e-05 tokens_per_second_per_gpu:825.0275723873481 mfu:12.123545106837609 
Step 4057 | loss:2.045323133468628 lr:1.8605506062025502e-05 tokens_per_second_per_gpu:870.0878746485232 mfu:12.78569340984561 
Step 4058 | loss:1.985759973526001 lr:1.8568962022430636e-05 tokens_per_second_per_gpu:879.5108952867994 mfu:12.924162013289045 
Step 4059 | loss:1.9745473861694336 lr:1.8532450233639943e-05 tokens_per_second_per_gpu:860.9918598829112 mfu:12.652030064529457 
Step 4060 | loss:1.942517638206482 lr:1.8495970710113976e-05 tokens_per_second_per_gpu:868.7772456756834 mfu:12.766434090518167 
Step 4061 | loss:1.952417254447937 lr:1.845952346630041e-05 tokens_per_second_per_gpu:902.1290619188874 mfu:13.256529527509946 
Step 4062 | loss:1.9608409404754639 lr:1.8423108516634212e-05 tokens_per_second_per_gpu:885.7653338592874 mfu:13.016069206077873 
Step 4063 | loss:2.017254114151001 lr:1.838672587553759e-05 tokens_per_second_per_gpu:876.1536014656349 mfu:12.874827537157518 
Step 4064 | loss:1.9539780616760254 lr:1.8350375557419875e-05 tokens_per_second_per_gpu:867.5717522644804 mfu:12.748719708313432 
Step 4065 | loss:1.9780319929122925 lr:1.831405757667759e-05 tokens_per_second_per_gpu:869.849941879368 mfu:12.782197055595411 
Step 4066 | loss:1.9778292179107666 lr:1.8277771947694523e-05 tokens_per_second_per_gpu:874.5534001090309 mfu:12.851313034156515 
Step 4067 | loss:1.9779884815216064 lr:1.824151868484164e-05 tokens_per_second_per_gpu:866.7763686765767 mfu:12.737031773112326 
Step 4068 | loss:1.9616289138793945 lr:1.8205297802477027e-05 tokens_per_second_per_gpu:883.6835042209319 mfu:12.985477312703546 
Step 4069 | loss:1.9803355932235718 lr:1.8169109314945986e-05 tokens_per_second_per_gpu:903.0795353238904 mfu:13.270496463384658 
Step 4070 | loss:1.9935550689697266 lr:1.813295323658103e-05 tokens_per_second_per_gpu:843.7104754610712 mfu:12.39808504431574 
Step 4071 | loss:1.9900527000427246 lr:1.8096829581701725e-05 tokens_per_second_per_gpu:876.82891662972 mfu:12.884751101080873 
Step 4072 | loss:1.9822317361831665 lr:1.8060738364614926e-05 tokens_per_second_per_gpu:883.6311935133792 mfu:12.984708621760587 
Step 4073 | loss:2.008162260055542 lr:1.8024679599614525e-05 tokens_per_second_per_gpu:866.1509249368881 mfu:12.727841055560958 
Step 4074 | loss:1.930104374885559 lr:1.7988653300981663e-05 tokens_per_second_per_gpu:869.7707808198677 mfu:12.781033806380867 
Step 4075 | loss:2.027784824371338 lr:1.7952659482984525e-05 tokens_per_second_per_gpu:864.0190142411797 mfu:12.696513235318077 
Step 4076 | loss:1.9588532447814941 lr:1.791669815987852e-05 tokens_per_second_per_gpu:877.9156193114505 mfu:12.900719887362232 
Step 4077 | loss:2.015315055847168 lr:1.7880769345906123e-05 tokens_per_second_per_gpu:868.2516269370024 mfu:12.75871027291416 
Step 4078 | loss:1.9632611274719238 lr:1.7844873055296962e-05 tokens_per_second_per_gpu:870.501150876504 mfu:12.791766386263852 
Step 4079 | loss:2.0204339027404785 lr:1.780900930226781e-05 tokens_per_second_per_gpu:858.4955895231477 mfu:12.615348082837764 
Step 4080 | loss:1.9887804985046387 lr:1.7773178101022514e-05 tokens_per_second_per_gpu:877.5088415637075 mfu:12.894742404259516 
Step 4081 | loss:1.9988083839416504 lr:1.773737946575197e-05 tokens_per_second_per_gpu:865.0375865094593 mfu:12.711480864585702 
Step 4082 | loss:1.9854743480682373 lr:1.7701613410634365e-05 tokens_per_second_per_gpu:853.4319802278937 mfu:12.540939786983147 
Step 4083 | loss:2.012291669845581 lr:1.7665879949834797e-05 tokens_per_second_per_gpu:893.521462767255 mfu:13.130043310480344 
Step 4084 | loss:1.9780182838439941 lr:1.7630179097505505e-05 tokens_per_second_per_gpu:871.7856290994513 mfu:12.810641427772577 
Step 4085 | loss:1.9556807279586792 lr:1.759451086778585e-05 tokens_per_second_per_gpu:865.0767424472714 mfu:12.71205624993542 
Step 4086 | loss:2.0288147926330566 lr:1.7558875274802276e-05 tokens_per_second_per_gpu:868.0053777049073 mfu:12.755091710610612 
Step 4087 | loss:1.9763563871383667 lr:1.7523272332668238e-05 tokens_per_second_per_gpu:891.0976117517888 mfu:13.094425510419157 
Step 4088 | loss:1.9465395212173462 lr:1.7487702055484345e-05 tokens_per_second_per_gpu:863.3614431494677 mfu:12.68685041548255 
Step 4089 | loss:2.06919527053833 lr:1.745216445733817e-05 tokens_per_second_per_gpu:861.4465917701815 mfu:12.658712220049285 
Step 4090 | loss:1.9599266052246094 lr:1.741665955230445e-05 tokens_per_second_per_gpu:870.1938536211061 mfu:12.78725074065186 
Step 4091 | loss:1.961775302886963 lr:1.738118735444486e-05 tokens_per_second_per_gpu:874.8433022892419 mfu:12.855573064094896 
Step 4092 | loss:2.0205066204071045 lr:1.734574787780826e-05 tokens_per_second_per_gpu:867.2033244967656 mfu:12.743305767240438 
Step 4093 | loss:2.0378284454345703 lr:1.7310341136430385e-05 tokens_per_second_per_gpu:808.1030959925531 mfu:11.874844748389988 
Step 4094 | loss:2.0066816806793213 lr:1.7274967144334153e-05 tokens_per_second_per_gpu:887.2309115087252 mfu:13.037605452059468 
Step 4095 | loss:1.9809246063232422 lr:1.7239625915529458e-05 tokens_per_second_per_gpu:904.1122639086368 mfu:13.285672115689302 
Step 4096 | loss:1.9400627613067627 lr:1.7204317464013177e-05 tokens_per_second_per_gpu:863.0762363872592 mfu:12.682659383373883 
Step 4097 | loss:2.0013110637664795 lr:1.7169041803769215e-05 tokens_per_second_per_gpu:853.8669487426929 mfu:12.547331525375553 
Step 4098 | loss:1.9578380584716797 lr:1.7133798948768597e-05 tokens_per_second_per_gpu:889.1070084973298 mfu:13.065174162763688 
Step 4099 | loss:1.958990454673767 lr:1.7098588912969237e-05 tokens_per_second_per_gpu:881.9685851852312 mfu:12.960277066093932 
Step 4100 | loss:1.995784044265747 lr:1.7063411710316046e-05 tokens_per_second_per_gpu:869.775376460508 mfu:12.781101338010673 
Step 4101 | loss:1.9868545532226562 lr:1.7028267354741024e-05 tokens_per_second_per_gpu:893.23008750869 mfu:13.125761634075266 
Step 4102 | loss:1.9732294082641602 lr:1.6993155860163102e-05 tokens_per_second_per_gpu:882.2553468423268 mfu:12.96449094693994 
Step 4103 | loss:1.989206075668335 lr:1.6958077240488178e-05 tokens_per_second_per_gpu:855.5663373133503 mfu:12.572303556226345 
Step 4104 | loss:2.0201621055603027 lr:1.692303150960921e-05 tokens_per_second_per_gpu:877.7772600188149 mfu:12.898686736978707 
Step 4105 | loss:2.018681049346924 lr:1.6888018681406016e-05 tokens_per_second_per_gpu:847.7779678615902 mfu:12.457855686218918 
Step 4106 | loss:2.0042219161987305 lr:1.6853038769745467e-05 tokens_per_second_per_gpu:867.5354797267651 mfu:12.748186693706588 
Step 4107 | loss:1.9725961685180664 lr:1.6818091788481415e-05 tokens_per_second_per_gpu:880.8535605352353 mfu:12.943892096558494 
Step 4108 | loss:2.0241611003875732 lr:1.6783177751454572e-05 tokens_per_second_per_gpu:877.91921988349 mfu:12.900772796742466 
Step 4109 | loss:1.9918317794799805 lr:1.6748296672492704e-05 tokens_per_second_per_gpu:897.3095871573464 mfu:13.18570871906868 
Step 4110 | loss:1.99391770362854 lr:1.6713448565410426e-05 tokens_per_second_per_gpu:882.2400258237807 mfu:12.964265808937714 
Step 4111 | loss:1.9641623497009277 lr:1.667863344400943e-05 tokens_per_second_per_gpu:880.3112961359458 mfu:12.935923675714578 
Step 4112 | loss:2.0193657875061035 lr:1.6643851322078174e-05 tokens_per_second_per_gpu:882.2356199186959 mfu:12.964201065417837 
Step 4113 | loss:1.990325689315796 lr:1.660910221339218e-05 tokens_per_second_per_gpu:880.117426074648 mfu:12.933074810401862 
Step 4114 | loss:1.9800317287445068 lr:1.657438613171387e-05 tokens_per_second_per_gpu:847.3119114038349 mfu:12.451007119362442 
Step 4115 | loss:1.9682707786560059 lr:1.653970309079256e-05 tokens_per_second_per_gpu:881.7066510838572 mfu:12.95642801910531 
Step 4116 | loss:2.002126455307007 lr:1.65050531043644e-05 tokens_per_second_per_gpu:876.4634585917246 mfu:12.87938079933996 
Step 4117 | loss:1.9923579692840576 lr:1.647043618615266e-05 tokens_per_second_per_gpu:876.943873882346 mfu:12.88644036515424 
Step 4118 | loss:2.011624336242676 lr:1.643585234986733e-05 tokens_per_second_per_gpu:883.2740842604181 mfu:12.97946100303699 
Step 4119 | loss:2.0057408809661865 lr:1.6401301609205335e-05 tokens_per_second_per_gpu:879.096245422278 mfu:12.918068851673217 
Step 4120 | loss:1.9739160537719727 lr:1.636678397785053e-05 tokens_per_second_per_gpu:828.9641533459383 mfu:12.181392042401331 
Step 4121 | loss:2.0262036323547363 lr:1.633229946947369e-05 tokens_per_second_per_gpu:856.7669754796486 mfu:12.589946591990577 
Step 4122 | loss:1.9946825504302979 lr:1.6297848097732338e-05 tokens_per_second_per_gpu:872.5212465828706 mfu:12.821451117097027 
Step 4123 | loss:1.9824646711349487 lr:1.626342987627103e-05 tokens_per_second_per_gpu:895.178455588739 mfu:13.154392347876557 
Step 4124 | loss:1.9614940881729126 lr:1.622904481872106e-05 tokens_per_second_per_gpu:863.7814759106232 mfu:12.693022677230703 
Step 4125 | loss:2.035536766052246 lr:1.6194692938700697e-05 tokens_per_second_per_gpu:891.7990089660912 mfu:13.104732342639078 
Step 4126 | loss:2.0326967239379883 lr:1.616037424981498e-05 tokens_per_second_per_gpu:855.3655182671554 mfu:12.56935257756049 
Step 4127 | loss:1.9533002376556396 lr:1.612608876565589e-05 tokens_per_second_per_gpu:841.4955302844172 mfu:12.365537056033807 
Step 4128 | loss:1.9908045530319214 lr:1.609183649980216e-05 tokens_per_second_per_gpu:881.5988587023373 mfu:12.954844040771414 
Step 4129 | loss:1.9708585739135742 lr:1.605761746581944e-05 tokens_per_second_per_gpu:818.9630968385337 mfu:12.034429366556816 
Step 4130 | loss:2.0094292163848877 lr:1.6023431677260214e-05 tokens_per_second_per_gpu:862.7504398594149 mfu:12.67787189622416 
Step 4131 | loss:2.003152370452881 lr:1.598927914766377e-05 tokens_per_second_per_gpu:889.0119926433807 mfu:13.063777931862115 
Step 4132 | loss:1.9709930419921875 lr:1.595515989055618e-05 tokens_per_second_per_gpu:897.2278623545752 mfu:13.18450779637724 
Step 4133 | loss:2.0651657581329346 lr:1.5921073919450502e-05 tokens_per_second_per_gpu:884.2729113195808 mfu:12.994138482082507 
Step 4134 | loss:1.9941948652267456 lr:1.5887021247846424e-05 tokens_per_second_per_gpu:859.1708083585695 mfu:12.62527023123886 
Step 4135 | loss:2.005035400390625 lr:1.5853001889230534e-05 tokens_per_second_per_gpu:861.1573509574973 mfu:12.654461908718273 
Step 4136 | loss:1.9895188808441162 lr:1.5819015857076213e-05 tokens_per_second_per_gpu:877.598353106053 mfu:12.896057750870378 
Step 4137 | loss:2.0000903606414795 lr:1.5785063164843682e-05 tokens_per_second_per_gpu:890.3134651315105 mfu:13.082902699255635 
Step 4138 | loss:1.9368417263031006 lr:1.5751143825979876e-05 tokens_per_second_per_gpu:860.0759981311447 mfu:12.638571737037395 
Step 4139 | loss:2.0165624618530273 lr:1.5717257853918622e-05 tokens_per_second_per_gpu:849.0637046052107 mfu:12.476749221330351 
Step 4140 | loss:1.9979125261306763 lr:1.568340526208041e-05 tokens_per_second_per_gpu:896.5142858952204 mfu:13.174021993621421 
Step 4141 | loss:2.041405200958252 lr:1.5649586063872635e-05 tokens_per_second_per_gpu:855.5066692030047 mfu:12.571426750345637 
Step 4142 | loss:1.9891704320907593 lr:1.5615800272689352e-05 tokens_per_second_per_gpu:877.6538702336339 mfu:12.89687355924207 
Step 4143 | loss:2.023650884628296 lr:1.55820479019115e-05 tokens_per_second_per_gpu:881.2095690894184 mfu:12.949123540827165 
Step 4144 | loss:2.011730194091797 lr:1.5548328964906677e-05 tokens_per_second_per_gpu:847.8382464522543 mfu:12.458741462933965 
Step 4145 | loss:2.002671241760254 lr:1.551464347502929e-05 tokens_per_second_per_gpu:892.2901912842085 mfu:13.111950126854635 
Step 4146 | loss:2.026125192642212 lr:1.5480991445620542e-05 tokens_per_second_per_gpu:873.3696361844063 mfu:12.833917960565817 
Step 4147 | loss:1.9937503337860107 lr:1.544737289000826e-05 tokens_per_second_per_gpu:862.0149630064693 mfu:12.667064273424453 
Step 4148 | loss:1.9964873790740967 lr:1.541378782150714e-05 tokens_per_second_per_gpu:868.9090484281538 mfu:12.768370894412076 
Step 4149 | loss:1.9893434047698975 lr:1.538023625341859e-05 tokens_per_second_per_gpu:894.2888736063657 mfu:13.141320194108017 
Step 4150 | loss:1.998685359954834 lr:1.5346718199030685e-05 tokens_per_second_per_gpu:870.8445968592882 mfu:12.796813227125181 
Step 4151 | loss:1.9735546112060547 lr:1.5313233671618243e-05 tokens_per_second_per_gpu:883.3274858131185 mfu:12.980245723638587 
Step 4152 | loss:1.9707911014556885 lr:1.527978268444287e-05 tokens_per_second_per_gpu:849.9696948023453 mfu:12.49006248913973 
Step 4153 | loss:1.9679591655731201 lr:1.5246365250752858e-05 tokens_per_second_per_gpu:888.4105868267295 mfu:13.05494044474082 
Step 4154 | loss:1.9663366079330444 lr:1.5212981383783154e-05 tokens_per_second_per_gpu:862.9452569574396 mfu:12.680734677971747 
Step 4155 | loss:1.959531307220459 lr:1.5179631096755475e-05 tokens_per_second_per_gpu:882.9991210469665 mfu:12.975420496958682 
Step 4156 | loss:1.9749093055725098 lr:1.5146314402878247e-05 tokens_per_second_per_gpu:868.9638120830178 mfu:12.769175630716873 
Step 4157 | loss:1.961493968963623 lr:1.5113031315346548e-05 tokens_per_second_per_gpu:876.877207105808 mfu:12.885460715867916 
Step 4158 | loss:2.0123000144958496 lr:1.5079781847342123e-05 tokens_per_second_per_gpu:876.7481923052807 mfu:12.883564880133461 
Step 4159 | loss:1.9715938568115234 lr:1.504656601203347e-05 tokens_per_second_per_gpu:903.5985631507084 mfu:13.278123429416743 
Step 4160 | loss:1.9724583625793457 lr:1.5013383822575766e-05 tokens_per_second_per_gpu:878.5844865906055 mfu:12.91054870145369 
Step 4161 | loss:1.999880075454712 lr:1.4980235292110777e-05 tokens_per_second_per_gpu:908.314789739504 mfu:13.347427035377304 
Step 4162 | loss:1.9408254623413086 lr:1.4947120433767047e-05 tokens_per_second_per_gpu:865.7952009483764 mfu:12.722613792903752 
Step 4163 | loss:1.9787623882293701 lr:1.4914039260659695e-05 tokens_per_second_per_gpu:880.6988024286509 mfu:12.941617970276393 
Step 4164 | loss:1.9230334758758545 lr:1.4880991785890552e-05 tokens_per_second_per_gpu:854.4952089235359 mfu:12.556563629727217 
Step 4165 | loss:1.9863324165344238 lr:1.4847978022548104e-05 tokens_per_second_per_gpu:888.3737458091381 mfu:13.05439907648417 
Step 4166 | loss:1.9466499090194702 lr:1.4814997983707458e-05 tokens_per_second_per_gpu:881.1106784773035 mfu:12.947670371458354 
Step 4167 | loss:1.977603793144226 lr:1.4782051682430354e-05 tokens_per_second_per_gpu:888.2679192775269 mfu:13.052843985754564 
Step 4168 | loss:1.9975252151489258 lr:1.4749139131765188e-05 tokens_per_second_per_gpu:856.4838083489401 mfu:12.585785531685666 
Step 4169 | loss:1.994385838508606 lr:1.4716260344747045e-05 tokens_per_second_per_gpu:844.7876508016333 mfu:12.413913829033188 
Step 4170 | loss:2.026939868927002 lr:1.4683415334397532e-05 tokens_per_second_per_gpu:893.7573892654204 mfu:13.133510183149982 
Step 4171 | loss:2.0370686054229736 lr:1.4650604113724953e-05 tokens_per_second_per_gpu:890.6219541647856 mfu:13.08743585770397 
Step 4172 | loss:1.9528782367706299 lr:1.4617826695724223e-05 tokens_per_second_per_gpu:894.1810199150659 mfu:13.139735314844373 
Step 4173 | loss:2.0074403285980225 lr:1.458508309337684e-05 tokens_per_second_per_gpu:893.5679780858769 mfu:13.130726839834205 
Step 4174 | loss:1.975211262702942 lr:1.4552373319650914e-05 tokens_per_second_per_gpu:815.0796274671444 mfu:11.977362890634291 
Step 4175 | loss:1.9750339984893799 lr:1.4519697387501164e-05 tokens_per_second_per_gpu:899.0270381596456 mfu:13.210946172206043 
Step 4176 | loss:2.0151381492614746 lr:1.4487055309868946e-05 tokens_per_second_per_gpu:883.4821018091552 mfu:12.982517761646681 
Step 4177 | loss:1.927289605140686 lr:1.4454447099682134e-05 tokens_per_second_per_gpu:890.0999108172481 mfu:13.079764579454102 
Step 4178 | loss:1.99104905128479 lr:1.442187276985526e-05 tokens_per_second_per_gpu:906.5551455209579 mfu:13.321569564949014 
Step 4179 | loss:1.9496358633041382 lr:1.4389332333289374e-05 tokens_per_second_per_gpu:871.7680143858736 mfu:12.810382584575391 
Step 4180 | loss:1.9514026641845703 lr:1.4356825802872132e-05 tokens_per_second_per_gpu:840.6030645794783 mfu:12.352422526783803 
Step 4181 | loss:1.9978148937225342 lr:1.432435319147779e-05 tokens_per_second_per_gpu:854.294419537784 mfu:12.553613086913124 
Step 4182 | loss:1.9618855714797974 lr:1.4291914511967142e-05 tokens_per_second_per_gpu:827.1171549187699 mfu:12.154250926766567 
Step 4183 | loss:2.0746054649353027 lr:1.4259509777187474e-05 tokens_per_second_per_gpu:876.3775498977664 mfu:12.878118395559614 
Step 4184 | loss:1.987221121788025 lr:1.42271389999728e-05 tokens_per_second_per_gpu:902.2140932735181 mfu:13.25777903903885 
Step 4185 | loss:1.96092689037323 lr:1.4194802193143531e-05 tokens_per_second_per_gpu:884.0992621422278 mfu:12.991586756897961 
Step 4186 | loss:1.977123737335205 lr:1.4162499369506654e-05 tokens_per_second_per_gpu:880.2848021074678 mfu:12.935534353514853 
Step 4187 | loss:1.9826862812042236 lr:1.413023054185575e-05 tokens_per_second_per_gpu:870.5173331835615 mfu:12.79200418065535 
Step 4188 | loss:1.94443678855896 lr:1.4097995722970914e-05 tokens_per_second_per_gpu:877.2102884182941 mfu:12.890355250852348 
Step 4189 | loss:1.9967577457427979 lr:1.4065794925618759e-05 tokens_per_second_per_gpu:876.6827331360254 mfu:12.882602976292082 
Step 4190 | loss:1.9679155349731445 lr:1.4033628162552359e-05 tokens_per_second_per_gpu:873.8271011322714 mfu:12.840640277632374 
Step 4191 | loss:1.9961391687393188 lr:1.4001495446511481e-05 tokens_per_second_per_gpu:873.810436033566 mfu:12.84039538875517 
Step 4192 | loss:1.9916447401046753 lr:1.3969396790222256e-05 tokens_per_second_per_gpu:876.1819797405361 mfu:12.875244547821566 
Step 4193 | loss:2.0300309658050537 lr:1.3937332206397357e-05 tokens_per_second_per_gpu:884.2191284639042 mfu:12.993348158342316 
Step 4194 | loss:2.0004663467407227 lr:1.3905301707735985e-05 tokens_per_second_per_gpu:852.2464868493839 mfu:12.523519299560366 
Step 4195 | loss:1.9830615520477295 lr:1.3873305306923878e-05 tokens_per_second_per_gpu:866.1845076775778 mfu:12.728334544366897 
Step 4196 | loss:2.0179309844970703 lr:1.3841343016633167e-05 tokens_per_second_per_gpu:896.9646024507346 mfu:13.180639267099123 
Step 4197 | loss:1.9682589769363403 lr:1.3809414849522584e-05 tokens_per_second_per_gpu:859.7521658301298 mfu:12.633813113641278 
Step 4198 | loss:1.9588547945022583 lr:1.3777520818237243e-05 tokens_per_second_per_gpu:881.981600577946 mfu:12.960468323581491 
Step 4199 | loss:1.9708701372146606 lr:1.3745660935408833e-05 tokens_per_second_per_gpu:848.8898746190633 mfu:12.474194839212089 
Step 4200 | loss:1.9680447578430176 lr:1.3713835213655479e-05 tokens_per_second_per_gpu:854.4218628244656 mfu:12.555485829699377 
Step 4201 | loss:1.983211636543274 lr:1.3682043665581768e-05 tokens_per_second_per_gpu:865.7433221315384 mfu:12.72185144847179 
Step 4202 | loss:1.9766961336135864 lr:1.3650286303778714e-05 tokens_per_second_per_gpu:846.2553180964352 mfu:12.43548078175802 
Step 4203 | loss:1.9963059425354004 lr:1.3618563140823882e-05 tokens_per_second_per_gpu:870.8159891043944 mfu:12.796392844318026 
Step 4204 | loss:2.0182557106018066 lr:1.3586874189281263e-05 tokens_per_second_per_gpu:880.523640151902 mfu:12.939044010527345 
Step 4205 | loss:1.9547770023345947 lr:1.355521946170123e-05 tokens_per_second_per_gpu:898.3179174240955 mfu:13.200525845041996 
Step 4206 | loss:1.981197714805603 lr:1.3523598970620687e-05 tokens_per_second_per_gpu:897.8831139221007 mfu:13.194136531465734 
Step 4207 | loss:1.985490083694458 lr:1.3492012728562964e-05 tokens_per_second_per_gpu:881.8650761882473 mfu:12.958756030875355 
Step 4208 | loss:2.032764434814453 lr:1.3460460748037774e-05 tokens_per_second_per_gpu:834.3490221585326 mfu:12.260521155329016 
Step 4209 | loss:1.9835149049758911 lr:1.3428943041541298e-05 tokens_per_second_per_gpu:850.9374913110336 mfu:12.504283983087344 
Step 4210 | loss:2.0078866481781006 lr:1.339745962155613e-05 tokens_per_second_per_gpu:885.6487002029744 mfu:13.014355307729975 
Step 4211 | loss:1.9949430227279663 lr:1.3366010500551352e-05 tokens_per_second_per_gpu:879.7298934865241 mfu:12.92738012943636 
Step 4212 | loss:1.9379793405532837 lr:1.3334595690982332e-05 tokens_per_second_per_gpu:879.4964894930879 mfu:12.923950324254998 
Step 4213 | loss:1.9913532733917236 lr:1.3303215205290975e-05 tokens_per_second_per_gpu:874.2679066051835 mfu:12.847117788461167 
Step 4214 | loss:1.9819629192352295 lr:1.3271869055905495e-05 tokens_per_second_per_gpu:854.9264737185177 mfu:12.562900943012183 
Step 4215 | loss:1.9914623498916626 lr:1.324055725524057e-05 tokens_per_second_per_gpu:857.7968231582156 mfu:12.605079910199748 
Step 4216 | loss:1.9935275316238403 lr:1.3209279815697295e-05 tokens_per_second_per_gpu:897.5841439904611 mfu:13.189743253503723 
Step 4217 | loss:1.9615180492401123 lr:1.317803674966306e-05 tokens_per_second_per_gpu:881.53974674302 mfu:12.953975407371608 
Step 4218 | loss:2.0400571823120117 lr:1.3146828069511707e-05 tokens_per_second_per_gpu:874.5419213088343 mfu:12.851144356458201 
Step 4219 | loss:1.9441578388214111 lr:1.3115653787603444e-05 tokens_per_second_per_gpu:898.1580458275445 mfu:13.198176577481785 
Step 4220 | loss:1.9858895540237427 lr:1.3084513916284913e-05 tokens_per_second_per_gpu:861.741082848794 mfu:12.663039682542193 
Step 4221 | loss:1.9965388774871826 lr:1.3053408467889006e-05 tokens_per_second_per_gpu:840.3897718233403 mfu:12.349288250504383 
Step 4222 | loss:2.001513719558716 lr:1.302233745473509e-05 tokens_per_second_per_gpu:850.2073970689584 mfu:12.493555456220747 
Step 4223 | loss:1.9635764360427856 lr:1.2991300889128866e-05 tokens_per_second_per_gpu:892.1765734788836 mfu:13.11028054557772 
Step 4224 | loss:1.9747881889343262 lr:1.2960298783362368e-05 tokens_per_second_per_gpu:872.931327496966 mfu:12.827477139288142 
Step 4225 | loss:1.9972779750823975 lr:1.2929331149713952e-05 tokens_per_second_per_gpu:856.1036522368832 mfu:12.580199245934239 
Step 4226 | loss:1.9953645467758179 lr:1.2898398000448443e-05 tokens_per_second_per_gpu:877.1786222146901 mfu:12.889889925012818 
Step 4227 | loss:1.9509800672531128 lr:1.2867499347816903e-05 tokens_per_second_per_gpu:886.5879788461791 mfu:13.028157739769707 
Step 4228 | loss:1.990364909172058 lr:1.2836635204056724e-05 tokens_per_second_per_gpu:885.9844287099435 mfu:13.019288742483084 
Step 4229 | loss:2.0139448642730713 lr:1.2805805581391683e-05 tokens_per_second_per_gpu:869.1498844252078 mfu:12.771909910769052 
Step 4230 | loss:1.9945265054702759 lr:1.2775010492031913e-05 tokens_per_second_per_gpu:854.5033054344469 mfu:12.556682605648174 
Step 4231 | loss:2.0286669731140137 lr:1.2744249948173758e-05 tokens_per_second_per_gpu:886.1126839592285 mfu:13.021173416828448 
Step 4232 | loss:1.9745746850967407 lr:1.2713523961999996e-05 tokens_per_second_per_gpu:863.7705280950661 mfu:12.692861802200374 
Step 4233 | loss:2.0058465003967285 lr:1.2682832545679635e-05 tokens_per_second_per_gpu:871.6729573291904 mfu:12.80898574821138 
Step 4234 | loss:2.0028154850006104 lr:1.2652175711368075e-05 tokens_per_second_per_gpu:876.6981369651354 mfu:12.88282933117195 
Step 4235 | loss:2.030095338821411 lr:1.2621553471206905e-05 tokens_per_second_per_gpu:856.5193123903404 mfu:12.586307253458122 
Step 4236 | loss:1.9951765537261963 lr:1.2590965837324131e-05 tokens_per_second_per_gpu:856.0166699239056 mfu:12.578921065628302 
Step 4237 | loss:2.0011370182037354 lr:1.2560412821833966e-05 tokens_per_second_per_gpu:915.170648656402 mfu:13.448171928768703 
Step 4238 | loss:2.001340627670288 lr:1.2529894436836965e-05 tokens_per_second_per_gpu:884.9800957565903 mfu:13.004530355891196 
Step 4239 | loss:1.970849871635437 lr:1.2499410694419967e-05 tokens_per_second_per_gpu:885.3384291076435 mfu:13.00979596238748 
Step 4240 | loss:2.0608580112457275 lr:1.246896160665605e-05 tokens_per_second_per_gpu:888.6660707722332 mfu:13.058694708526724 
Step 4241 | loss:1.9936645030975342 lr:1.2438547185604554e-05 tokens_per_second_per_gpu:873.45887453232 mfu:12.835229292662344 
Step 4242 | loss:1.9601190090179443 lr:1.2408167443311214e-05 tokens_per_second_per_gpu:879.6357425377951 mfu:12.925996608070562 
Step 4243 | loss:1.9885450601577759 lr:1.2377822391807902e-05 tokens_per_second_per_gpu:854.8299881670512 mfu:12.561483115324343 
Step 4244 | loss:2.017977714538574 lr:1.2347512043112752e-05 tokens_per_second_per_gpu:849.9818020387919 mfu:12.49024040152968 
Step 4245 | loss:1.9783539772033691 lr:1.2317236409230238e-05 tokens_per_second_per_gpu:870.3281288978309 mfu:12.789223877585206 
Step 4246 | loss:2.0072803497314453 lr:1.2286995502151044e-05 tokens_per_second_per_gpu:880.7802442620899 mfu:12.942814734814123 
Step 4247 | loss:2.0255286693573 lr:1.225678933385207e-05 tokens_per_second_per_gpu:860.5442150246218 mfu:12.645452050881245 
Step 4248 | loss:1.938564419746399 lr:1.22266179162965e-05 tokens_per_second_per_gpu:887.2980063196904 mfu:13.038591391189742 
Step 4249 | loss:1.9835138320922852 lr:1.2196481261433735e-05 tokens_per_second_per_gpu:907.6357710289101 mfu:13.337449048893227 
Step 4250 | loss:2.0195956230163574 lr:1.2166379381199423e-05 tokens_per_second_per_gpu:893.0678231041409 mfu:13.12337720488329 
Step 4251 | loss:1.989844799041748 lr:1.2136312287515394e-05 tokens_per_second_per_gpu:883.4252761579335 mfu:12.981682724892918 
Step 4252 | loss:1.9904465675354004 lr:1.2106279992289783e-05 tokens_per_second_per_gpu:890.488387201272 mfu:13.085473129231445 
Step 4253 | loss:1.9860258102416992 lr:1.2076282507416858e-05 tokens_per_second_per_gpu:872.788880184265 mfu:12.825383916614529 
Step 4254 | loss:1.9673138856887817 lr:1.2046319844777143e-05 tokens_per_second_per_gpu:863.1290602748649 mfu:12.683435615351502 
Step 4255 | loss:1.994244933128357 lr:1.201639201623741e-05 tokens_per_second_per_gpu:859.4348163593844 mfu:12.629149753588862 
Step 4256 | loss:1.9495488405227661 lr:1.1986499033650556e-05 tokens_per_second_per_gpu:880.1840851580259 mfu:12.934054346639389 
Step 4257 | loss:1.9821596145629883 lr:1.1956640908855666e-05 tokens_per_second_per_gpu:891.7778674085508 mfu:13.104421673474741 
Step 4258 | loss:1.9751942157745361 lr:1.1926817653678157e-05 tokens_per_second_per_gpu:880.4734753047436 mfu:12.938306852391474 
Step 4259 | loss:1.9901111125946045 lr:1.1897029279929494e-05 tokens_per_second_per_gpu:870.0831240825333 mfu:12.785623601631935 
Step 4260 | loss:1.9982373714447021 lr:1.1867275799407374e-05 tokens_per_second_per_gpu:876.5046087574488 mfu:12.879985489300644 
Step 4261 | loss:1.9657986164093018 lr:1.183755722389569e-05 tokens_per_second_per_gpu:884.7056171533843 mfu:13.000496971022372 
Step 4262 | loss:2.004051446914673 lr:1.1807873565164506e-05 tokens_per_second_per_gpu:898.741415088385 mfu:13.206749022554472 
Step 4263 | loss:2.0084192752838135 lr:1.177822483497003e-05 tokens_per_second_per_gpu:888.675323416389 mfu:13.058830673496303 
Step 4264 | loss:1.973750352859497 lr:1.1748611045054658e-05 tokens_per_second_per_gpu:903.1733748007106 mfu:13.271875407759499 
Step 4265 | loss:1.9379806518554688 lr:1.1719032207146984e-05 tokens_per_second_per_gpu:870.3118267717567 mfu:12.7889843224874 
Step 4266 | loss:2.0182042121887207 lr:1.1689488332961685e-05 tokens_per_second_per_gpu:858.826487608317 mfu:12.620210535918828 
Step 4267 | loss:2.004399061203003 lr:1.1659979434199642e-05 tokens_per_second_per_gpu:883.4937134980244 mfu:12.982688392106176 
Step 4268 | loss:1.944250464439392 lr:1.1630505522547853e-05 tokens_per_second_per_gpu:854.3431538188215 mfu:12.554329223287448 
Step 4269 | loss:2.0182981491088867 lr:1.1601066609679501e-05 tokens_per_second_per_gpu:873.4272524355192 mfu:12.834764614959722 
Step 4270 | loss:1.9711449146270752 lr:1.157166270725385e-05 tokens_per_second_per_gpu:879.8829633270026 mfu:12.92962944712906 
Step 4271 | loss:1.985029935836792 lr:1.1542293826916373e-05 tokens_per_second_per_gpu:880.8666361699483 mfu:12.944084239285052 
Step 4272 | loss:1.9791494607925415 lr:1.1512959980298588e-05 tokens_per_second_per_gpu:879.4647827113622 mfu:12.923484402131532 
Step 4273 | loss:1.9735885858535767 lr:1.148366117901819e-05 tokens_per_second_per_gpu:839.9300671947418 mfu:12.342533021967585 
Step 4274 | loss:1.9887069463729858 lr:1.1454397434679021e-05 tokens_per_second_per_gpu:872.6890901116063 mfu:12.823917529929302 
Step 4275 | loss:1.9756869077682495 lr:1.1425168758870964e-05 tokens_per_second_per_gpu:883.3913002753814 mfu:12.981183458979327 
Step 4276 | loss:2.0071465969085693 lr:1.1395975163170025e-05 tokens_per_second_per_gpu:889.2760098264848 mfu:13.06765758914324 
Step 4277 | loss:2.0146517753601074 lr:1.1366816659138424e-05 tokens_per_second_per_gpu:882.3240830596294 mfu:12.965501006068665 
Step 4278 | loss:2.0236520767211914 lr:1.1337693258324345e-05 tokens_per_second_per_gpu:893.2572950921171 mfu:13.12616144176166 
Step 4279 | loss:1.988553524017334 lr:1.1308604972262126e-05 tokens_per_second_per_gpu:845.2319950905043 mfu:12.420443341754206 
Step 4280 | loss:1.9975314140319824 lr:1.12795518124722e-05 tokens_per_second_per_gpu:876.4729202362156 mfu:12.879519835509916 
Step 4281 | loss:1.9806053638458252 lr:1.1250533790461115e-05 tokens_per_second_per_gpu:891.8385915623476 mfu:13.10531399761307 
Step 4282 | loss:2.0324618816375732 lr:1.1221550917721436e-05 tokens_per_second_per_gpu:889.8795274229099 mfu:13.076526108266616 
Step 4283 | loss:1.9657549858093262 lr:1.1192603205731877e-05 tokens_per_second_per_gpu:895.3507196593016 mfu:13.156923719311466 
Step 4284 | loss:2.0006263256073 lr:1.116369066595716e-05 tokens_per_second_per_gpu:841.5081822314436 mfu:12.365722972790525 
Step 4285 | loss:2.034409523010254 lr:1.1134813309848146e-05 tokens_per_second_per_gpu:867.1228140344565 mfu:12.742122688936092 
Step 4286 | loss:1.953090786933899 lr:1.11059711488417e-05 tokens_per_second_per_gpu:862.2197166284238 mfu:12.670073069560043 
Step 4287 | loss:1.9934868812561035 lr:1.107716419436079e-05 tokens_per_second_per_gpu:890.0394183444514 mfu:13.078875659802057 
Step 4288 | loss:1.981406331062317 lr:1.1048392457814405e-05 tokens_per_second_per_gpu:879.6986912736687 mfu:12.92692162180868 
Step 4289 | loss:2.0411951541900635 lr:1.1019655950597618e-05 tokens_per_second_per_gpu:843.2578501647164 mfu:12.3914338445492 
Step 4290 | loss:1.9857938289642334 lr:1.0990954684091558e-05 tokens_per_second_per_gpu:880.9447699013701 mfu:12.945232392206194 
Step 4291 | loss:1.9786477088928223 lr:1.0962288669663356e-05 tokens_per_second_per_gpu:870.3316110980932 mfu:12.789275047525901 
Step 4292 | loss:1.9842448234558105 lr:1.0933657918666174e-05 tokens_per_second_per_gpu:872.7614436094844 mfu:12.82498074396544 
Step 4293 | loss:2.012669086456299 lr:1.0905062442439296e-05 tokens_per_second_per_gpu:884.545529675208 mfu:12.998144531143188 
Step 4294 | loss:2.0068349838256836 lr:1.087650225230794e-05 tokens_per_second_per_gpu:853.7491667772445 mfu:12.545600752952089 
Step 4295 | loss:1.9850404262542725 lr:1.0847977359583373e-05 tokens_per_second_per_gpu:877.2877318327711 mfu:12.89149325976267 
Step 4296 | loss:1.975629448890686 lr:1.0819487775562909e-05 tokens_per_second_per_gpu:892.9365943890613 mfu:13.121448836305285 
Step 4297 | loss:1.9606472253799438 lr:1.079103351152988e-05 tokens_per_second_per_gpu:885.0037182993724 mfu:13.004877482426771 
Step 4298 | loss:1.9429652690887451 lr:1.0762614578753572e-05 tokens_per_second_per_gpu:874.4570685353477 mfu:12.84989746912833 
Step 4299 | loss:1.9701039791107178 lr:1.0734230988489357e-05 tokens_per_second_per_gpu:907.6460863694364 mfu:13.337600629883182 
Step 4300 | loss:2.0292062759399414 lr:1.0705882751978535e-05 tokens_per_second_per_gpu:879.7890886759684 mfu:12.928249985879166 
Step 4301 | loss:1.9709813594818115 lr:1.067756988044848e-05 tokens_per_second_per_gpu:881.4949788879582 mfu:12.953317556496868 
Step 4302 | loss:1.9297170639038086 lr:1.0649292385112475e-05 tokens_per_second_per_gpu:857.2324182700157 mfu:12.59678614117963 
Step 4303 | loss:1.957239031791687 lr:1.0621050277169854e-05 tokens_per_second_per_gpu:894.6959508080708 mfu:13.147302077601386 
Step 4304 | loss:1.9431092739105225 lr:1.0592843567805943e-05 tokens_per_second_per_gpu:888.161763987321 mfu:13.051284064011082 
Step 4305 | loss:1.9667950868606567 lr:1.0564672268191989e-05 tokens_per_second_per_gpu:868.5641034074181 mfu:12.763302025615161 
Step 4306 | loss:2.0249640941619873 lr:1.0536536389485275e-05 tokens_per_second_per_gpu:877.796525913493 mfu:12.898969843811706 
Step 4307 | loss:1.9627760648727417 lr:1.0508435942828997e-05 tokens_per_second_per_gpu:866.7405173994031 mfu:12.736504948809117 
Step 4308 | loss:1.9727752208709717 lr:1.048037093935238e-05 tokens_per_second_per_gpu:857.7441323664158 mfu:12.604305634027074 
Step 4309 | loss:2.0619897842407227 lr:1.0452341390170594e-05 tokens_per_second_per_gpu:886.163547579747 mfu:13.02192084323975 
Step 4310 | loss:1.983272671699524 lr:1.0424347306384729e-05 tokens_per_second_per_gpu:882.4363975349862 mfu:12.967151435283048 
Step 4311 | loss:1.9958487749099731 lr:1.039638869908185e-05 tokens_per_second_per_gpu:838.6362846438476 mfu:12.3235212560107 
Step 4312 | loss:2.0066514015197754 lr:1.0368465579334996e-05 tokens_per_second_per_gpu:874.8522224807409 mfu:12.855704143767406 
Step 4313 | loss:2.000472068786621 lr:1.0340577958203146e-05 tokens_per_second_per_gpu:872.045033728178 mfu:12.81445330488135 
Step 4314 | loss:2.0200376510620117 lr:1.0312725846731175e-05 tokens_per_second_per_gpu:849.8132535644119 mfu:12.487763629722016 
Step 4315 | loss:2.000399112701416 lr:1.0284909255949938e-05 tokens_per_second_per_gpu:891.142343052295 mfu:13.095082824135117 
Step 4316 | loss:2.0041942596435547 lr:1.025712819687623e-05 tokens_per_second_per_gpu:893.8532773948074 mfu:13.134919231890581 
Step 4317 | loss:2.000620126724243 lr:1.0229382680512734e-05 tokens_per_second_per_gpu:883.0312965477704 mfu:12.975893306775454 
Step 4318 | loss:1.9466884136199951 lr:1.0201672717848066e-05 tokens_per_second_per_gpu:853.4447828404285 mfu:12.541127917726586 
Step 4319 | loss:1.9960718154907227 lr:1.017399831985678e-05 tokens_per_second_per_gpu:878.7645344393272 mfu:12.91319445329087 
Step 4320 | loss:1.9566196203231812 lr:1.0146359497499358e-05 tokens_per_second_per_gpu:896.5855447165446 mfu:13.175069121697499 
Step 4321 | loss:2.007500171661377 lr:1.0118756261722129e-05 tokens_per_second_per_gpu:885.9895972289227 mfu:13.019364692396854 
Step 4322 | loss:2.0257530212402344 lr:1.0091188623457415e-05 tokens_per_second_per_gpu:884.1087753715977 mfu:12.991726551093016 
Step 4323 | loss:2.0355923175811768 lr:1.0063656593623349e-05 tokens_per_second_per_gpu:869.8460039820976 mfu:12.782139189317022 
Step 4324 | loss:1.9567254781723022 lr:1.0036160183124022e-05 tokens_per_second_per_gpu:861.833895473492 mfu:12.66440353761767 
Step 4325 | loss:1.981284737586975 lr:1.000869940284942e-05 tokens_per_second_per_gpu:858.6016224729642 mfu:12.616906206824083 
Step 4326 | loss:2.029823064804077 lr:9.98127426367539e-06 tokens_per_second_per_gpu:887.814860777672 mfu:13.04618642018602 
Step 4327 | loss:1.987986445426941 lr:9.953884776463652e-06 tokens_per_second_per_gpu:842.0790821024078 mfu:12.374112183731798 
Step 4328 | loss:1.9455485343933105 lr:9.92653095206183e-06 tokens_per_second_per_gpu:906.3579715770891 mfu:13.31867215002327 
Step 4329 | loss:1.9810717105865479 lr:9.899212801303447e-06 tokens_per_second_per_gpu:876.3026807843432 mfu:12.877018215269798 
Step 4330 | loss:2.027129650115967 lr:9.87193033500784e-06 tokens_per_second_per_gpu:852.1872912756752 mfu:12.522649437470902 
Step 4331 | loss:2.017343521118164 lr:9.844683563980262e-06 tokens_per_second_per_gpu:880.4442189483495 mfu:12.937876938570076 
Step 4332 | loss:2.029216766357422 lr:9.817472499011814e-06 tokens_per_second_per_gpu:844.2288938532205 mfu:12.40570305487901 
Step 4333 | loss:1.9987283945083618 lr:9.790297150879457e-06 tokens_per_second_per_gpu:867.642747634287 mfu:12.749762965044523 
Step 4334 | loss:1.9475090503692627 lr:9.763157530345957e-06 tokens_per_second_per_gpu:879.1333806209541 mfu:12.918614542837089 
Step 4335 | loss:1.979772686958313 lr:9.736053648160016e-06 tokens_per_second_per_gpu:894.9744927117445 mfu:13.151395171512855 
Step 4336 | loss:2.017500877380371 lr:9.708985515056146e-06 tokens_per_second_per_gpu:856.2988721280333 mfu:12.583067946612037 
Step 4337 | loss:2.049102544784546 lr:9.681953141754663e-06 tokens_per_second_per_gpu:848.651536814984 mfu:12.470692533089085 
Step 4338 | loss:1.9389536380767822 lr:9.65495653896179e-06 tokens_per_second_per_gpu:891.4699511818253 mfu:13.099896932255447 
Step 4339 | loss:2.0019705295562744 lr:9.627995717369497e-06 tokens_per_second_per_gpu:886.5817060815416 mfu:13.028065563280613 
Step 4340 | loss:1.9796870946884155 lr:9.601070687655667e-06 tokens_per_second_per_gpu:884.3329150788002 mfu:12.995020220227781 
Step 4341 | loss:1.9916139841079712 lr:9.574181460483977e-06 tokens_per_second_per_gpu:911.2394410795957 mfu:13.390403953519293 
Step 4342 | loss:2.030742645263672 lr:9.54732804650389e-06 tokens_per_second_per_gpu:875.843466305303 mfu:12.870270189341104 
Step 4343 | loss:1.9768908023834229 lr:9.520510456350729e-06 tokens_per_second_per_gpu:867.9883462836818 mfu:12.754841438728349 
Step 4344 | loss:2.01846981048584 lr:9.493728700645632e-06 tokens_per_second_per_gpu:870.8052369965488 mfu:12.796234845156759 
Step 4345 | loss:1.958327054977417 lr:9.466982789995504e-06 tokens_per_second_per_gpu:885.7499403126069 mfu:13.01584300229538 
Step 4346 | loss:1.9963313341140747 lr:9.440272734993072e-06 tokens_per_second_per_gpu:882.6512306635105 mfu:12.970308346895797 
Step 4347 | loss:1.9492826461791992 lr:9.413598546216872e-06 tokens_per_second_per_gpu:889.8320541336988 mfu:13.075828501807894 
Step 4348 | loss:1.9964873790740967 lr:9.386960234231268e-06 tokens_per_second_per_gpu:846.3797469129029 mfu:12.437309227763372 
Step 4349 | loss:1.9685053825378418 lr:9.360357809586307e-06 tokens_per_second_per_gpu:876.01291628781 mfu:12.872760208553835 
Step 4350 | loss:1.996417760848999 lr:9.333791282817939e-06 tokens_per_second_per_gpu:896.3640979403925 mfu:13.17181502441724 
Step 4351 | loss:1.9696532487869263 lr:9.30726066444787e-06 tokens_per_second_per_gpu:887.0892702339709 mfu:13.035524073883822 
Step 4352 | loss:1.9155040979385376 lr:9.280765964983529e-06 tokens_per_second_per_gpu:859.0688690515943 mfu:12.62377226216772 
Step 4353 | loss:1.9895341396331787 lr:9.254307194918144e-06 tokens_per_second_per_gpu:873.0346863484933 mfu:12.828995968162014 
Step 4354 | loss:1.989013433456421 lr:9.227884364730744e-06 tokens_per_second_per_gpu:869.8650104869263 mfu:12.782418484490087 
Step 4355 | loss:2.0311145782470703 lr:9.201497484886113e-06 tokens_per_second_per_gpu:898.7807691017346 mfu:13.207327318567778 
Step 4356 | loss:1.9739089012145996 lr:9.175146565834769e-06 tokens_per_second_per_gpu:890.6801073775708 mfu:13.088290402596655 
Step 4357 | loss:1.9417952299118042 lr:9.148831618013042e-06 tokens_per_second_per_gpu:853.1561569493921 mfu:12.536886642493982 
Step 4358 | loss:1.9971970319747925 lr:9.12255265184293e-06 tokens_per_second_per_gpu:852.8189635604195 mfu:12.531931681717209 
Step 4359 | loss:1.9663128852844238 lr:9.096309677732262e-06 tokens_per_second_per_gpu:884.9500973896754 mfu:13.00408953843661 
Step 4360 | loss:2.018949270248413 lr:9.07010270607459e-06 tokens_per_second_per_gpu:887.1019357807752 mfu:13.035710190485403 
Step 4361 | loss:2.029897689819336 lr:9.04393174724918e-06 tokens_per_second_per_gpu:879.6604450939689 mfu:12.92635960509521 
Step 4362 | loss:1.9458662271499634 lr:9.017796811621049e-06 tokens_per_second_per_gpu:889.633704511119 mfu:13.072913810618472 
Step 4363 | loss:1.984022855758667 lr:8.991697909540952e-06 tokens_per_second_per_gpu:889.5020570524939 mfu:13.070979288723374 
Step 4364 | loss:1.98122239112854 lr:8.965635051345411e-06 tokens_per_second_per_gpu:879.3492420613908 mfu:12.9217865652004 
Step 4365 | loss:2.003584623336792 lr:8.939608247356579e-06 tokens_per_second_per_gpu:863.2345884147178 mfu:12.68498632129924 
Step 4366 | loss:1.9753199815750122 lr:8.91361750788241e-06 tokens_per_second_per_gpu:864.0809157669407 mfu:12.697422860601963 
Step 4367 | loss:1.967165470123291 lr:8.887662843216572e-06 tokens_per_second_per_gpu:858.989622150112 mfu:12.622607751529708 
Step 4368 | loss:1.9486989974975586 lr:8.861744263638406e-06 tokens_per_second_per_gpu:870.340088158194 mfu:12.789399615508774 
Step 4369 | loss:1.9805514812469482 lr:8.835861779412946e-06 tokens_per_second_per_gpu:861.8260768555915 mfu:12.664288645255327 
Step 4370 | loss:2.038079023361206 lr:8.810015400790994e-06 tokens_per_second_per_gpu:851.1139471339108 mfu:12.50687695112819 
Step 4371 | loss:1.943373203277588 lr:8.784205138009038e-06 tokens_per_second_per_gpu:829.2410804633948 mfu:12.18546140748943 
Step 4372 | loss:1.950958251953125 lr:8.758431001289202e-06 tokens_per_second_per_gpu:842.340822233742 mfu:12.377958380385948 
Step 4373 | loss:2.037614107131958 lr:8.732693000839399e-06 tokens_per_second_per_gpu:898.3091611768579 mfu:13.200397174483696 
Step 4374 | loss:1.9697474241256714 lr:8.706991146853128e-06 tokens_per_second_per_gpu:849.9726040559083 mfu:12.490105239791925 
Step 4375 | loss:1.9487324953079224 lr:8.681325449509636e-06 tokens_per_second_per_gpu:881.8195846134685 mfu:12.95808754514558 
Step 4376 | loss:1.9860278367996216 lr:8.655695918973862e-06 tokens_per_second_per_gpu:891.0419539177241 mfu:13.093607634405778 
Step 4377 | loss:1.9999380111694336 lr:8.63010256539638e-06 tokens_per_second_per_gpu:873.9637882452525 mfu:12.842648855812321 
Step 4378 | loss:1.9992501735687256 lr:8.604545398913421e-06 tokens_per_second_per_gpu:889.4192199363304 mfu:13.069762020903555 
Step 4379 | loss:1.9670675992965698 lr:8.579024429646932e-06 tokens_per_second_per_gpu:874.1377258772859 mfu:12.845204819756205 
Step 4380 | loss:1.978435754776001 lr:8.553539667704536e-06 tokens_per_second_per_gpu:883.6435031430897 mfu:12.984889508261885 
Step 4381 | loss:1.9917690753936768 lr:8.528091123179449e-06 tokens_per_second_per_gpu:897.6589608640129 mfu:13.190842666143514 
Step 4382 | loss:1.9878138303756714 lr:8.502678806150588e-06 tokens_per_second_per_gpu:816.9773158641383 mfu:12.0052488809329 
Step 4383 | loss:1.9400548934936523 lr:8.477302726682535e-06 tokens_per_second_per_gpu:875.6720664284071 mfu:12.867751516985901 
Step 4384 | loss:2.003667116165161 lr:8.451962894825493e-06 tokens_per_second_per_gpu:856.328911388409 mfu:12.58350936498438 
Step 4385 | loss:1.9758511781692505 lr:8.42665932061526e-06 tokens_per_second_per_gpu:841.9194012312887 mfu:12.371765718827469 
Step 4386 | loss:2.0067596435546875 lr:8.401392014073405e-06 tokens_per_second_per_gpu:877.4930336291021 mfu:12.894510111164536 
Step 4387 | loss:1.9775277376174927 lr:8.376160985207038e-06 tokens_per_second_per_gpu:872.2659709980697 mfu:12.817699915112284 
Step 4388 | loss:1.9869753122329712 lr:8.350966244008895e-06 tokens_per_second_per_gpu:864.7986069194957 mfu:12.707969127601988 
Step 4389 | loss:1.9994556903839111 lr:8.325807800457375e-06 tokens_per_second_per_gpu:868.398428869539 mfu:12.760867485485527 
Step 4390 | loss:1.9520291090011597 lr:8.300685664516516e-06 tokens_per_second_per_gpu:840.4696944345873 mfu:12.35046269050486 
Step 4391 | loss:2.0351314544677734 lr:8.275599846135929e-06 tokens_per_second_per_gpu:831.8712328321415 mfu:12.224110747157056 
Step 4392 | loss:2.036931276321411 lr:8.250550355250875e-06 tokens_per_second_per_gpu:860.0962449440672 mfu:12.638869258184508 
Step 4393 | loss:2.0209813117980957 lr:8.225537201782207e-06 tokens_per_second_per_gpu:862.342966659931 mfu:12.671884193656263 
Step 4394 | loss:2.02508807182312 lr:8.200560395636414e-06 tokens_per_second_per_gpu:881.1011500947554 mfu:12.947530354591665 
Step 4395 | loss:1.9544856548309326 lr:8.17561994670556e-06 tokens_per_second_per_gpu:828.3412141180531 mfu:12.172238127937321 
Step 4396 | loss:2.0158772468566895 lr:8.150715864867332e-06 tokens_per_second_per_gpu:887.9431654175424 mfu:13.048071820311963 
Step 4397 | loss:1.9916075468063354 lr:8.125848159984983e-06 tokens_per_second_per_gpu:867.686694677772 mfu:12.750408754327008 
Step 4398 | loss:1.9897540807724 lr:8.101016841907395e-06 tokens_per_second_per_gpu:870.3055220899166 mfu:12.788891676984107 
Step 4399 | loss:2.0220491886138916 lr:8.076221920469052e-06 tokens_per_second_per_gpu:862.9567088310296 mfu:12.680902959991249 
Step 4400 | loss:2.010117530822754 lr:8.051463405489957e-06 tokens_per_second_per_gpu:875.7403507900569 mfu:12.868754936224555 
Step 4401 | loss:1.9698015451431274 lr:8.026741306775709e-06 tokens_per_second_per_gpu:867.1859417365513 mfu:12.743050332531837 
Step 4402 | loss:1.9396127462387085 lr:8.002055634117578e-06 tokens_per_second_per_gpu:883.4472512637394 mfu:12.98200564281152 
Step 4403 | loss:1.984485149383545 lr:7.977406397292309e-06 tokens_per_second_per_gpu:852.4639234871439 mfu:12.526714468999534 
Step 4404 | loss:2.000209331512451 lr:7.952793606062215e-06 tokens_per_second_per_gpu:876.8689767938292 mfu:12.885339773778394 
Step 4405 | loss:1.9690344333648682 lr:7.92821727017523e-06 tokens_per_second_per_gpu:845.3565187443035 mfu:12.422273181367121 
Step 4406 | loss:1.9899485111236572 lr:7.90367739936484e-06 tokens_per_second_per_gpu:863.5865444204134 mfu:12.690158214522548 
Step 4407 | loss:1.9780466556549072 lr:7.879174003350032e-06 tokens_per_second_per_gpu:876.4276135530528 mfu:12.878854066709756 
Step 4408 | loss:2.018969774246216 lr:7.854707091835434e-06 tokens_per_second_per_gpu:841.8933555667784 mfu:12.371382985208498 
Step 4409 | loss:2.0066895484924316 lr:7.83027667451114e-06 tokens_per_second_per_gpu:879.8416131830243 mfu:12.929021818544909 
Step 4410 | loss:1.989243507385254 lr:7.805882761052852e-06 tokens_per_second_per_gpu:906.5234451963629 mfu:13.321103737711246 
Step 4411 | loss:1.9974735975265503 lr:7.781525361121777e-06 tokens_per_second_per_gpu:854.2105773424391 mfu:12.552381049741106 
Step 4412 | loss:2.0064010620117188 lr:7.7572044843647e-06 tokens_per_second_per_gpu:876.8973126812289 mfu:12.885756161570184 
Step 4413 | loss:1.978585958480835 lr:7.73292014041389e-06 tokens_per_second_per_gpu:878.4217958264048 mfu:12.908158007028115 
Step 4414 | loss:1.9928348064422607 lr:7.708672338887179e-06 tokens_per_second_per_gpu:866.047610694031 mfu:12.726322882198785 
Step 4415 | loss:1.9678099155426025 lr:7.68446108938794e-06 tokens_per_second_per_gpu:896.1490033987973 mfu:13.168654271413896 
Step 4416 | loss:1.9571309089660645 lr:7.660286401505045e-06 tokens_per_second_per_gpu:870.397272908734 mfu:12.790239929124704 
Step 4417 | loss:1.9860278367996216 lr:7.636148284812849e-06 tokens_per_second_per_gpu:828.396166282628 mfu:12.173045634338608 
Step 4418 | loss:1.962630033493042 lr:7.612046748871327e-06 tokens_per_second_per_gpu:863.7705087166947 mfu:12.69286151744073 
Step 4419 | loss:1.996171236038208 lr:7.587981803225885e-06 tokens_per_second_per_gpu:862.3199374158391 mfu:12.671545785475896 
Step 4420 | loss:1.9962809085845947 lr:7.5639534574074135e-06 tokens_per_second_per_gpu:893.0917427310618 mfu:13.123728696985639 
Step 4421 | loss:1.9552128314971924 lr:7.5399617209324205e-06 tokens_per_second_per_gpu:883.1442930223088 mfu:12.977553757773494 
Step 4422 | loss:1.9031569957733154 lr:7.516006603302817e-06 tokens_per_second_per_gpu:842.8693417589802 mfu:12.385724824221917 
Step 4423 | loss:1.957263708114624 lr:7.492088114006013e-06 tokens_per_second_per_gpu:869.9034764991625 mfu:12.782983731580043 
Step 4424 | loss:1.9792627096176147 lr:7.4682062625149655e-06 tokens_per_second_per_gpu:809.1988611420122 mfu:11.89094670505251 
Step 4425 | loss:1.9559952020645142 lr:7.4443610582881075e-06 tokens_per_second_per_gpu:871.3565428749704 mfu:12.804336127960397 
Step 4426 | loss:1.9694925546646118 lr:7.420552510769307e-06 tokens_per_second_per_gpu:872.6449156390395 mfu:12.82326839864126 
Step 4427 | loss:1.957541584968567 lr:7.396780629387978e-06 tokens_per_second_per_gpu:894.6082552916145 mfu:13.146013416973535 
Step 4428 | loss:1.9951575994491577 lr:7.373045423558977e-06 tokens_per_second_per_gpu:884.8472168569302 mfu:13.002577738320957 
Step 4429 | loss:1.9929324388504028 lr:7.349346902682652e-06 tokens_per_second_per_gpu:890.5903205890894 mfu:13.086971011322248 
Step 4430 | loss:1.9528778791427612 lr:7.325685076144795e-06 tokens_per_second_per_gpu:860.4410447989425 mfu:12.643935993810464 
Step 4431 | loss:1.9933124780654907 lr:7.30205995331672e-06 tokens_per_second_per_gpu:885.2958146281285 mfu:13.009169754752858 
Step 4432 | loss:2.028122901916504 lr:7.278471543555121e-06 tokens_per_second_per_gpu:890.5363539089387 mfu:13.086177986333787 
Step 4433 | loss:2.004835844039917 lr:7.254919856202236e-06 tokens_per_second_per_gpu:835.9441281676101 mfu:12.283960783649897 
Step 4434 | loss:1.9940152168273926 lr:7.231404900585714e-06 tokens_per_second_per_gpu:871.7813172689041 mfu:12.810578066651226 
Step 4435 | loss:1.9382498264312744 lr:7.207926686018673e-06 tokens_per_second_per_gpu:872.6009313177512 mfu:12.822622061572076 
Step 4436 | loss:1.9630975723266602 lr:7.1844852217996305e-06 tokens_per_second_per_gpu:836.5649138162304 mfu:12.293083051880215 
Step 4437 | loss:1.986220359802246 lr:7.16108051721266e-06 tokens_per_second_per_gpu:852.938223205131 mfu:12.533684168216418 
Step 4438 | loss:1.9662153720855713 lr:7.137712581527156e-06 tokens_per_second_per_gpu:862.638872107424 mfu:12.676232439896882 
Step 4439 | loss:2.009521245956421 lr:7.1143814239980065e-06 tokens_per_second_per_gpu:832.9158768735562 mfu:12.23946149370245 
Step 4440 | loss:2.0620806217193604 lr:7.0910870538655306e-06 tokens_per_second_per_gpu:884.6896622111155 mfu:13.000262517691663 
Step 4441 | loss:2.017399787902832 lr:7.067829480355504e-06 tokens_per_second_per_gpu:892.5406422830472 mfu:13.1156304329233 
Step 4442 | loss:1.9819632768630981 lr:7.0446087126790575e-06 tokens_per_second_per_gpu:846.886734340627 mfu:12.444759263561359 
Step 4443 | loss:2.0308313369750977 lr:7.0214247600328245e-06 tokens_per_second_per_gpu:860.0232678483685 mfu:12.637796880556074 
Step 4444 | loss:1.9991986751556396 lr:6.998277631598793e-06 tokens_per_second_per_gpu:885.4649982363595 mfu:13.011655859671498 
Step 4445 | loss:1.9585856199264526 lr:6.975167336544419e-06 tokens_per_second_per_gpu:880.2374132387256 mfu:12.93483798759087 
Step 4446 | loss:1.9930758476257324 lr:6.952093884022514e-06 tokens_per_second_per_gpu:878.3403501395962 mfu:12.90696118586622 
Step 4447 | loss:2.0162227153778076 lr:6.92905728317137e-06 tokens_per_second_per_gpu:863.6456401767944 mfu:12.691026609824823 
Step 4448 | loss:1.963045597076416 lr:6.906057543114619e-06 tokens_per_second_per_gpu:865.548171091782 mfu:12.718983759545605 
Step 4449 | loss:2.001086711883545 lr:6.883094672961321e-06 tokens_per_second_per_gpu:859.3565655578691 mfu:12.627999880356052 
Step 4450 | loss:1.9563452005386353 lr:6.860168681805945e-06 tokens_per_second_per_gpu:883.6352597986413 mfu:12.984768374663934 
Step 4451 | loss:1.9608546495437622 lr:6.837279578728351e-06 tokens_per_second_per_gpu:848.7705855754173 mfu:12.472441920703913 
Step 4452 | loss:2.0256874561309814 lr:6.814427372793719e-06 tokens_per_second_per_gpu:837.4774543781127 mfu:12.30649257543321 
Step 4453 | loss:1.9956552982330322 lr:6.791612073052755e-06 tokens_per_second_per_gpu:869.3002329010621 mfu:12.77411923878398 
Step 4454 | loss:1.9745811223983765 lr:6.768833688541443e-06 tokens_per_second_per_gpu:876.7110361618223 mfu:12.883018881191983 
Step 4455 | loss:1.9610750675201416 lr:6.746092228281142e-06 tokens_per_second_per_gpu:860.567486042031 mfu:12.645794011851622 
Step 4456 | loss:1.9734715223312378 lr:6.723387701278649e-06 tokens_per_second_per_gpu:870.914372043566 mfu:12.797838553577582 
Step 4457 | loss:1.954306960105896 lr:6.700720116526116e-06 tokens_per_second_per_gpu:829.4394621501067 mfu:12.18837656985214 
Step 4458 | loss:2.0405941009521484 lr:6.678089483001015e-06 tokens_per_second_per_gpu:890.800518558354 mfu:13.09005981059034 
Step 4459 | loss:2.0601258277893066 lr:6.655495809666246e-06 tokens_per_second_per_gpu:869.4621531016309 mfu:12.776498609996535 
Step 4460 | loss:1.9479507207870483 lr:6.632939105470049e-06 tokens_per_second_per_gpu:866.9759628494335 mfu:12.73996475261347 
Step 4461 | loss:2.014463424682617 lr:6.610419379346011e-06 tokens_per_second_per_gpu:857.3927148929466 mfu:12.599141654381393 
Step 4462 | loss:1.9593671560287476 lr:6.587936640213055e-06 tokens_per_second_per_gpu:887.5187835514172 mfu:13.041835649705439 
Step 4463 | loss:1.999558925628662 lr:6.565490896975513e-06 tokens_per_second_per_gpu:869.953164188955 mfu:12.783713878024376 
Step 4464 | loss:1.9868204593658447 lr:6.543082158523028e-06 tokens_per_second_per_gpu:848.2143549523761 mfu:12.464268270181263 
Step 4465 | loss:1.9720414876937866 lr:6.520710433730581e-06 tokens_per_second_per_gpu:886.898615163654 mfu:13.032722451947544 
Step 4466 | loss:1.932861328125 lr:6.498375731458528e-06 tokens_per_second_per_gpu:867.5370582386419 mfu:12.748209889488864 
Step 4467 | loss:1.957830786705017 lr:6.476078060552504e-06 tokens_per_second_per_gpu:862.3459393113699 mfu:12.67192787592218 
Step 4468 | loss:1.9892892837524414 lr:6.453817429843534e-06 tokens_per_second_per_gpu:816.1398739033009 mfu:11.992942909924935 
Step 4469 | loss:2.0299365520477295 lr:6.431593848147966e-06 tokens_per_second_per_gpu:841.1164597397342 mfu:12.359966722385634 
Step 4470 | loss:1.9838554859161377 lr:6.409407324267447e-06 tokens_per_second_per_gpu:888.594546769032 mfu:13.057643683678524 
Step 4471 | loss:1.988684058189392 lr:6.387257866988938e-06 tokens_per_second_per_gpu:863.3179002825644 mfu:12.686210565459772 
Step 4472 | loss:2.004218578338623 lr:6.365145485084767e-06 tokens_per_second_per_gpu:857.7336538509226 mfu:12.60415165522747 
Step 4473 | loss:1.9791672229766846 lr:6.343070187312572e-06 tokens_per_second_per_gpu:826.2650037760651 mfu:12.141728808522046 
Step 4474 | loss:1.961761236190796 lr:6.321031982415238e-06 tokens_per_second_per_gpu:854.2681330012543 mfu:12.55322681374846 
Step 4475 | loss:2.003734588623047 lr:6.299030879121049e-06 tokens_per_second_per_gpu:884.882012413868 mfu:13.003089049116099 
Step 4476 | loss:1.961714267730713 lr:6.277066886143546e-06 tokens_per_second_per_gpu:841.6825430780448 mfu:12.368285155751902 
Step 4477 | loss:1.978097677230835 lr:6.25514001218157e-06 tokens_per_second_per_gpu:848.8524963889928 mfu:12.473645576771123 
Step 4478 | loss:1.9960023164749146 lr:6.233250265919266e-06 tokens_per_second_per_gpu:892.8693468544127 mfu:13.120460652943999 
Step 4479 | loss:1.9908385276794434 lr:6.2113976560260856e-06 tokens_per_second_per_gpu:907.311532819801 mfu:13.332684460793315 
Step 4480 | loss:1.9604061841964722 lr:6.189582191156784e-06 tokens_per_second_per_gpu:864.0367343486034 mfu:12.696773627247802 
Step 4481 | loss:1.9635690450668335 lr:6.167803879951351e-06 tokens_per_second_per_gpu:889.6165112343953 mfu:13.072661160315775 
Step 4482 | loss:1.985065221786499 lr:6.146062731035129e-06 tokens_per_second_per_gpu:883.4616483470883 mfu:12.98221720384927 
Step 4483 | loss:2.0060365200042725 lr:6.124358753018689e-06 tokens_per_second_per_gpu:831.9711471933679 mfu:12.225578960227372 
Step 4484 | loss:2.00449800491333 lr:6.102691954497907e-06 tokens_per_second_per_gpu:878.399781782169 mfu:12.90783451692038 
Step 4485 | loss:2.0351250171661377 lr:6.081062344053956e-06 tokens_per_second_per_gpu:886.3361503284294 mfu:13.02445719145313 
Step 4486 | loss:1.9760239124298096 lr:6.059469930253226e-06 tokens_per_second_per_gpu:882.0468087117035 mfu:12.961426538527755 
Step 4487 | loss:1.9939600229263306 lr:6.037914721647397e-06 tokens_per_second_per_gpu:903.9867019681024 mfu:13.28382701874864 
Step 4488 | loss:2.0486865043640137 lr:6.0163967267734435e-06 tokens_per_second_per_gpu:878.4134370560884 mfu:12.908035177279922 
Step 4489 | loss:1.977567434310913 lr:5.994915954153579e-06 tokens_per_second_per_gpu:901.4670685947262 mfu:13.246801724228574 
Step 4490 | loss:2.0304415225982666 lr:5.973472412295255e-06 tokens_per_second_per_gpu:862.8045759224428 mfu:12.678667410245742 
Step 4491 | loss:1.9548242092132568 lr:5.952066109691201e-06 tokens_per_second_per_gpu:892.3137022475257 mfu:13.112295613761766 
Step 4492 | loss:1.931410551071167 lr:5.9306970548194116e-06 tokens_per_second_per_gpu:881.4501633589888 mfu:12.952659005067641 
Step 4493 | loss:1.9692643880844116 lr:5.909365256143107e-06 tokens_per_second_per_gpu:880.7504588631392 mfu:12.94237704686309 
Step 4494 | loss:1.9806712865829468 lr:5.888070722110739e-06 tokens_per_second_per_gpu:853.8966501508764 mfu:12.547767979106194 
Step 4495 | loss:2.004411220550537 lr:5.8668134611560174e-06 tokens_per_second_per_gpu:867.2187780129294 mfu:12.7435328522574 
Step 4496 | loss:1.9422543048858643 lr:5.8455934816979305e-06 tokens_per_second_per_gpu:898.1430379431738 mfu:13.19795604089705 
Step 4497 | loss:1.9521617889404297 lr:5.824410792140622e-06 tokens_per_second_per_gpu:903.3233902866232 mfu:13.274079842582111 
Step 4498 | loss:1.9323351383209229 lr:5.803265400873514e-06 tokens_per_second_per_gpu:893.6344971806672 mfu:13.131704318979322 
Step 4499 | loss:2.0259735584259033 lr:5.782157316271264e-06 tokens_per_second_per_gpu:872.4472140649643 mfu:12.820363230339966 
Step 4500 | loss:1.974631667137146 lr:5.761086546693728e-06 tokens_per_second_per_gpu:866.7756516997297 mfu:12.737021237341843 
Step 4501 | loss:2.025129556655884 lr:5.740053100486009e-06 tokens_per_second_per_gpu:864.6479717593295 mfu:12.705755586842777 
Step 4502 | loss:2.0058586597442627 lr:5.719056985978388e-06 tokens_per_second_per_gpu:867.7656227372295 mfu:12.751568579672309 
Step 4503 | loss:1.9669578075408936 lr:5.698098211486402e-06 tokens_per_second_per_gpu:892.5726678838222 mfu:13.116101040001857 
Step 4504 | loss:1.9873086214065552 lr:5.6771767853108005e-06 tokens_per_second_per_gpu:870.8057039693972 mfu:12.796241707189715 
Step 4505 | loss:2.001129150390625 lr:5.65629271573751e-06 tokens_per_second_per_gpu:875.7667690078366 mfu:12.869143144407667 
Step 4506 | loss:1.996401071548462 lr:5.6354460110376705e-06 tokens_per_second_per_gpu:856.1805416312721 mfu:12.58132911367722 
Step 4507 | loss:2.022043466567993 lr:5.614636679467622e-06 tokens_per_second_per_gpu:870.9146724043611 mfu:12.797842967293889 
Step 4508 | loss:1.9639538526535034 lr:5.593864729268949e-06 tokens_per_second_per_gpu:875.4732755768727 mfu:12.864830342062701 
Step 4509 | loss:2.0377883911132812 lr:5.57313016866835e-06 tokens_per_second_per_gpu:886.4995788756131 mfu:13.026858727389431 
Step 4510 | loss:2.0322093963623047 lr:5.5524330058777774e-06 tokens_per_second_per_gpu:869.0973308178787 mfu:12.771137650483087 
Step 4511 | loss:2.005164623260498 lr:5.531773249094363e-06 tokens_per_second_per_gpu:897.2047689485337 mfu:13.184168445355303 
Step 4512 | loss:1.9973455667495728 lr:5.511150906500406e-06 tokens_per_second_per_gpu:872.8229235843148 mfu:12.82588417467851 
Step 4513 | loss:2.0528032779693604 lr:5.490565986263385e-06 tokens_per_second_per_gpu:892.5801648181897 mfu:13.116211205316336 
Step 4514 | loss:2.035252571105957 lr:5.470018496535967e-06 tokens_per_second_per_gpu:897.3021457217786 mfu:13.185599369293248 
Step 4515 | loss:1.991314172744751 lr:5.449508445456031e-06 tokens_per_second_per_gpu:857.4184051385226 mfu:12.599519165220388 
Step 4516 | loss:1.984309196472168 lr:5.429035841146546e-06 tokens_per_second_per_gpu:881.5199973075765 mfu:12.953685195044836 
Step 4517 | loss:1.9786288738250732 lr:5.408600691715737e-06 tokens_per_second_per_gpu:863.2420444438092 mfu:12.685095885522342 
Step 4518 | loss:2.0268869400024414 lr:5.38820300525692e-06 tokens_per_second_per_gpu:890.5858936859332 mfu:13.086905959241696 
Step 4519 | loss:1.997023344039917 lr:5.367842789848632e-06 tokens_per_second_per_gpu:888.1184526351948 mfu:13.05064761603199 
Step 4520 | loss:1.9494960308074951 lr:5.347520053554545e-06 tokens_per_second_per_gpu:888.7405266752603 mfu:13.059788816807503 
Step 4521 | loss:2.0104241371154785 lr:5.327234804423498e-06 tokens_per_second_per_gpu:888.7333145572892 mfu:13.059682836788816 
Step 4522 | loss:1.9890772104263306 lr:5.306987050489442e-06 tokens_per_second_per_gpu:871.9353502000451 mfu:12.812841536686806 
Step 4523 | loss:1.9947926998138428 lr:5.286776799771531e-06 tokens_per_second_per_gpu:896.7801885354637 mfu:13.177929357157998 
Step 4524 | loss:1.9637610912322998 lr:5.2666040602740495e-06 tokens_per_second_per_gpu:868.8147122315339 mfu:12.766984650881307 
Step 4525 | loss:1.9888885021209717 lr:5.246468839986407e-06 tokens_per_second_per_gpu:876.8544948817856 mfu:12.885126966207144 
Step 4526 | loss:2.026355743408203 lr:5.22637114688318e-06 tokens_per_second_per_gpu:874.2125619816989 mfu:12.84630451498802 
Step 4527 | loss:1.9926581382751465 lr:5.206310988924079e-06 tokens_per_second_per_gpu:858.0169606040091 mfu:12.608314767243447 
Step 4528 | loss:1.990361213684082 lr:5.186288374053938e-06 tokens_per_second_per_gpu:867.2252533311358 mfu:12.743628005213475 
Step 4529 | loss:1.9823873043060303 lr:5.16630331020268e-06 tokens_per_second_per_gpu:888.0659352738077 mfu:13.049875888369813 
Step 4530 | loss:1.9910635948181152 lr:5.146355805285452e-06 tokens_per_second_per_gpu:893.5249278560475 mfu:13.130094228972865 
Step 4531 | loss:2.046705961227417 lr:5.126445867202456e-06 tokens_per_second_per_gpu:867.362059226165 mfu:12.745638328861775 
Step 4532 | loss:1.9795796871185303 lr:5.106573503839018e-06 tokens_per_second_per_gpu:881.8531184533985 mfu:12.958580315368787 
Step 4533 | loss:1.947472095489502 lr:5.086738723065631e-06 tokens_per_second_per_gpu:885.6020774064262 mfu:13.013670199018609 
Step 4534 | loss:1.9719222784042358 lr:5.066941532737834e-06 tokens_per_second_per_gpu:895.4260699158215 mfu:13.158030969861999 
Step 4535 | loss:1.9608149528503418 lr:5.047181940696333e-06 tokens_per_second_per_gpu:889.8765909687098 mfu:13.07648295790881 
Step 4536 | loss:1.9404014348983765 lr:5.027459954766933e-06 tokens_per_second_per_gpu:875.6086081516173 mfu:12.866819015689202 
Step 4537 | loss:1.9876861572265625 lr:5.00777558276051e-06 tokens_per_second_per_gpu:901.2551765781823 mfu:13.243688031418385 
Step 4538 | loss:1.998765468597412 lr:4.9881288324731045e-06 tokens_per_second_per_gpu:887.0979557339315 mfu:13.035651704831043 
Step 4539 | loss:2.0288422107696533 lr:4.968519711685793e-06 tokens_per_second_per_gpu:852.614971373317 mfu:12.528934074649818 
Step 4540 | loss:1.9974822998046875 lr:4.9489482281647955e-06 tokens_per_second_per_gpu:886.3020225627852 mfu:13.023955693660776 
Step 4541 | loss:1.95566725730896 lr:4.92941438966138e-06 tokens_per_second_per_gpu:886.428265094526 mfu:13.025810791695296 
Step 4542 | loss:1.995195984840393 lr:4.909918203911968e-06 tokens_per_second_per_gpu:879.1152956787807 mfu:12.918348789764668 
Step 4543 | loss:2.014213800430298 lr:4.890459678638026e-06 tokens_per_second_per_gpu:889.1690006787688 mfu:13.06608512020693 
Step 4544 | loss:1.959371566772461 lr:4.871038821546103e-06 tokens_per_second_per_gpu:864.0766864063354 mfu:12.69736071135291 
Step 4545 | loss:1.9879436492919922 lr:4.8516556403278234e-06 tokens_per_second_per_gpu:880.6441834008319 mfu:12.940815359224816 
Step 4546 | loss:2.0132505893707275 lr:4.832310142659946e-06 tokens_per_second_per_gpu:865.5258038706623 mfu:12.718655079604188 
Step 4547 | loss:1.9478576183319092 lr:4.813002336204253e-06 tokens_per_second_per_gpu:873.3419869836592 mfu:12.833511663438735 
Step 4548 | loss:1.92142653465271 lr:4.7937322286075725e-06 tokens_per_second_per_gpu:858.9210517058618 mfu:12.621600128388753 
Step 4549 | loss:1.9556235074996948 lr:4.774499827501888e-06 tokens_per_second_per_gpu:895.7669247282004 mfu:13.163039734212505 
Step 4550 | loss:2.0363478660583496 lr:4.755305140504185e-06 tokens_per_second_per_gpu:888.1911154032576 mfu:13.051715374705376 
Step 4551 | loss:1.9898202419281006 lr:4.7361481752165256e-06 tokens_per_second_per_gpu:845.5163964672088 mfu:12.424622538952363 
Step 4552 | loss:1.9537811279296875 lr:4.7170289392260426e-06 tokens_per_second_per_gpu:843.2092687938806 mfu:12.390719955146722 
Step 4553 | loss:2.001828193664551 lr:4.6979474401049e-06 tokens_per_second_per_gpu:872.6073258604107 mfu:12.822716027554504 
Step 4554 | loss:1.9669764041900635 lr:4.678903685410374e-06 tokens_per_second_per_gpu:888.1683078551275 mfu:13.051380224284 
Step 4555 | loss:1.9700019359588623 lr:4.659897682684711e-06 tokens_per_second_per_gpu:846.397066651821 mfu:12.437563736391981 
Step 4556 | loss:1.9947035312652588 lr:4.640929439455277e-06 tokens_per_second_per_gpu:885.675030820494 mfu:13.014742228652224 
Step 4557 | loss:2.031024932861328 lr:4.6219989632344305e-06 tokens_per_second_per_gpu:886.2632230267682 mfu:13.02338554553389 
Step 4558 | loss:1.9533882141113281 lr:4.603106261519619e-06 tokens_per_second_per_gpu:872.865595997788 mfu:12.826511233636143 
Step 4559 | loss:1.9351238012313843 lr:4.5842513417933e-06 tokens_per_second_per_gpu:864.7758699912214 mfu:12.707635014919271 
Step 4560 | loss:1.9704381227493286 lr:4.5654342115229785e-06 tokens_per_second_per_gpu:878.2797517391012 mfu:12.906070709636829 
Step 4561 | loss:1.9705814123153687 lr:4.54665487816115e-06 tokens_per_second_per_gpu:892.1911147254436 mfu:13.110494225052785 
Step 4562 | loss:2.00174880027771 lr:4.527913349145441e-06 tokens_per_second_per_gpu:893.7390808631073 mfu:13.133241146394475 
Step 4563 | loss:1.9769352674484253 lr:4.509209631898415e-06 tokens_per_second_per_gpu:868.9857996927467 mfu:12.769498732377063 
Step 4564 | loss:2.0134458541870117 lr:4.490543733827668e-06 tokens_per_second_per_gpu:874.7237215270733 mfu:12.853815858866147 
Step 4565 | loss:1.9256713390350342 lr:4.471915662325854e-06 tokens_per_second_per_gpu:877.9045393539134 mfu:12.90055707054316 
Step 4566 | loss:1.9800959825515747 lr:4.45332542477066e-06 tokens_per_second_per_gpu:848.8746882373375 mfu:12.47397167965958 
Step 4567 | loss:1.982556700706482 lr:4.434773028524708e-06 tokens_per_second_per_gpu:890.5326609717434 mfu:13.086123719673905 
Step 4568 | loss:2.0133938789367676 lr:4.416258480935731e-06 tokens_per_second_per_gpu:882.3306067376132 mfu:12.96559686965789 
Step 4569 | loss:2.0034329891204834 lr:4.397781789336386e-06 tokens_per_second_per_gpu:889.4643348560775 mfu:13.070424971794958 
Step 4570 | loss:1.9696004390716553 lr:4.379342961044408e-06 tokens_per_second_per_gpu:897.6986976197749 mfu:13.191426586447516 
Step 4571 | loss:1.9448823928833008 lr:4.3609420033624675e-06 tokens_per_second_per_gpu:878.0253771658257 mfu:12.902332747759731 
Step 4572 | loss:2.0236754417419434 lr:4.342578923578322e-06 tokens_per_second_per_gpu:873.3730931417768 mfu:12.83396875956941 
Step 4573 | loss:2.028714895248413 lr:4.324253728964622e-06 tokens_per_second_per_gpu:858.2939603057089 mfu:12.612385198936318 
Step 4574 | loss:1.9459935426712036 lr:4.305966426779118e-06 tokens_per_second_per_gpu:875.6688344654344 mfu:12.867704024210877 
Step 4575 | loss:1.9663059711456299 lr:4.287717024264492e-06 tokens_per_second_per_gpu:893.8715894757503 mfu:13.135188322702502 
Step 4576 | loss:1.9879294633865356 lr:4.26950552864841e-06 tokens_per_second_per_gpu:880.7919542654273 mfu:12.942986809976716 
Step 4577 | loss:1.960915207862854 lr:4.251331947143555e-06 tokens_per_second_per_gpu:895.9615768117633 mfu:13.16590009111959 
Step 4578 | loss:1.9872139692306519 lr:4.233196286947605e-06 tokens_per_second_per_gpu:851.6215199949769 mfu:12.514335589702334 
Step 4579 | loss:1.9826914072036743 lr:4.21509855524318e-06 tokens_per_second_per_gpu:890.9713956688569 mfu:13.092570801042347 
Step 4580 | loss:1.988391637802124 lr:4.197038759197869e-06 tokens_per_second_per_gpu:879.9866607576424 mfu:12.93115325132652 
Step 4581 | loss:2.003232002258301 lr:4.179016905964317e-06 tokens_per_second_per_gpu:877.6331520010084 mfu:12.89656911071674 
Step 4582 | loss:1.9815325736999512 lr:4.16103300268006e-06 tokens_per_second_per_gpu:857.2437471195312 mfu:12.59695261539541 
Step 4583 | loss:1.9406147003173828 lr:4.1430870564676094e-06 tokens_per_second_per_gpu:865.9412295809774 mfu:12.724759642052895 
Step 4584 | loss:2.0222179889678955 lr:4.125179074434504e-06 tokens_per_second_per_gpu:877.5856244763318 mfu:12.895870707283306 
Step 4585 | loss:2.040895462036133 lr:4.107309063673204e-06 tokens_per_second_per_gpu:890.3405649421405 mfu:13.083300923251482 
Step 4586 | loss:1.9714492559432983 lr:4.089477031261113e-06 tokens_per_second_per_gpu:845.9456285379015 mfu:12.430929981933069 
Step 4587 | loss:1.9585535526275635 lr:4.071682984260638e-06 tokens_per_second_per_gpu:886.8996754662272 mfu:13.032738032791753 
Step 4588 | loss:1.9950230121612549 lr:4.05392692971911e-06 tokens_per_second_per_gpu:813.94866441368 mfu:11.960743710801106 
Step 4589 | loss:1.9828407764434814 lr:4.036208874668834e-06 tokens_per_second_per_gpu:870.5743854579556 mfu:12.792842547572063 
Step 4590 | loss:1.9886528253555298 lr:4.018528826127044e-06 tokens_per_second_per_gpu:891.9910281299198 mfu:13.107554009540848 
Step 4591 | loss:2.0102696418762207 lr:4.000886791095937e-06 tokens_per_second_per_gpu:861.08629069572 mfu:12.653417698418163 
Step 4592 | loss:1.9965403079986572 lr:3.9832827765626465e-06 tokens_per_second_per_gpu:851.5561163489743 mfu:12.513374501759335 
Step 4593 | loss:1.9758174419403076 lr:3.965716789499241e-06 tokens_per_second_per_gpu:864.698207818356 mfu:12.70649379141676 
Step 4594 | loss:2.0220179557800293 lr:3.948188836862776e-06 tokens_per_second_per_gpu:869.2438102064041 mfu:12.773290123362107 
Step 4595 | loss:1.9889357089996338 lr:3.930698925595178e-06 tokens_per_second_per_gpu:836.4811818070384 mfu:12.291852633862321 
Step 4596 | loss:1.9695019721984863 lr:3.913247062623315e-06 tokens_per_second_per_gpu:858.9867471263881 mfu:12.622565503875245 
Step 4597 | loss:1.9934031963348389 lr:3.8958332548590496e-06 tokens_per_second_per_gpu:879.3766883121469 mfu:12.92218988003519 
Step 4598 | loss:1.980797290802002 lr:3.878457509199107e-06 tokens_per_second_per_gpu:885.6795549467913 mfu:13.014808709399135 
Step 4599 | loss:1.9714100360870361 lr:3.861119832525162e-06 tokens_per_second_per_gpu:876.0498489035922 mfu:12.8733029228198 
Step 4600 | loss:1.9855289459228516 lr:3.8438202317037986e-06 tokens_per_second_per_gpu:891.6183187597596 mfu:13.102077151539847 
Step 4601 | loss:2.0268306732177734 lr:3.82655871358657e-06 tokens_per_second_per_gpu:888.349699272422 mfu:13.05404571947854 
Step 4602 | loss:1.9206395149230957 lr:3.809335285009863e-06 tokens_per_second_per_gpu:892.6347553180755 mfu:13.117013397158066 
Step 4603 | loss:1.994537591934204 lr:3.7921499527950654e-06 tokens_per_second_per_gpu:898.1634280289446 mfu:13.198255667397849 
Step 4604 | loss:2.0315184593200684 lr:3.7750027237484e-06 tokens_per_second_per_gpu:872.0605560270552 mfu:12.814681400640689 
Step 4605 | loss:1.9518418312072754 lr:3.757893604661067e-06 tokens_per_second_per_gpu:883.9829672860518 mfu:12.989877837121545 
Step 4606 | loss:1.991887092590332 lr:3.740822602309124e-06 tokens_per_second_per_gpu:874.2002785474396 mfu:12.846124013421413 
Step 4607 | loss:1.973949670791626 lr:3.723789723453552e-06 tokens_per_second_per_gpu:895.5214499093448 mfu:13.159432551690864 
Step 4608 | loss:1.9459476470947266 lr:3.706794974840233e-06 tokens_per_second_per_gpu:887.2513431645099 mfu:13.037905689419775 
Step 4609 | loss:1.9766578674316406 lr:3.689838363199949e-06 tokens_per_second_per_gpu:896.5905506788974 mfu:13.175142682887959 
Step 4610 | loss:1.9961460828781128 lr:3.6729198952483724e-06 tokens_per_second_per_gpu:885.810080760685 mfu:13.016726749044485 
Step 4611 | loss:1.9296238422393799 lr:3.656039577686077e-06 tokens_per_second_per_gpu:889.7738746419618 mfu:13.0749735707535 
Step 4612 | loss:1.9600117206573486 lr:3.639197417198492e-06 tokens_per_second_per_gpu:889.6098412854423 mfu:13.072563147316334 
Step 4613 | loss:1.9544804096221924 lr:3.622393420456016e-06 tokens_per_second_per_gpu:867.7731523373004 mfu:12.751679224999995 
Step 4614 | loss:2.0086617469787598 lr:3.6056275941138474e-06 tokens_per_second_per_gpu:871.6919655960496 mfu:12.809265069276982 
Step 4615 | loss:2.0123491287231445 lr:3.5888999448120965e-06 tokens_per_second_per_gpu:874.3238995118021 mfu:12.847940588270255 
Step 4616 | loss:1.9879405498504639 lr:3.572210479175753e-06 tokens_per_second_per_gpu:887.5887047398503 mfu:13.042863121647303 
Step 4617 | loss:1.9556875228881836 lr:3.555559203814729e-06 tokens_per_second_per_gpu:861.1319190497601 mfu:12.654088194080211 
Step 4618 | loss:2.0186643600463867 lr:3.5389461253237166e-06 tokens_per_second_per_gpu:881.3011913524056 mfu:12.950469903876463 
Step 4619 | loss:1.9493083953857422 lr:3.5223712502823636e-06 tokens_per_second_per_gpu:873.3189845780076 mfu:12.833173649641601 
Step 4620 | loss:2.011780261993408 lr:3.5058345852551746e-06 tokens_per_second_per_gpu:828.7857189581423 mfu:12.178769999912745 
Step 4621 | loss:2.0345258712768555 lr:3.4893361367914655e-06 tokens_per_second_per_gpu:842.1263378534935 mfu:12.374806593529748 
Step 4622 | loss:1.9827942848205566 lr:3.472875911425477e-06 tokens_per_second_per_gpu:881.8684579453378 mfu:12.95880572483226 
Step 4623 | loss:1.975363850593567 lr:3.456453915676283e-06 tokens_per_second_per_gpu:851.5286936177018 mfu:12.512971532536653 
Step 4624 | loss:1.9435217380523682 lr:3.4400701560478367e-06 tokens_per_second_per_gpu:897.3197677702061 mfu:13.185858320273962 
Step 4625 | loss:1.9584691524505615 lr:3.4237246390289135e-06 tokens_per_second_per_gpu:872.2468141844524 mfu:12.817418411194394 
Step 4626 | loss:2.008962392807007 lr:3.40741737109318e-06 tokens_per_second_per_gpu:875.3036724068252 mfu:12.86233807180271 
Step 4627 | loss:1.9732435941696167 lr:3.3911483586991256e-06 tokens_per_second_per_gpu:897.1773371687873 mfu:13.183765343167877 
Step 4628 | loss:1.97896409034729 lr:3.3749176082901067e-06 tokens_per_second_per_gpu:873.1307124786862 mfu:12.830407044785138 
Step 4629 | loss:2.0311412811279297 lr:3.3587251262943266e-06 tokens_per_second_per_gpu:857.1256390763407 mfu:12.595217051352432 
Step 4630 | loss:1.9427825212478638 lr:3.3425709191248324e-06 tokens_per_second_per_gpu:886.0500469203891 mfu:13.020252983389442 
Step 4631 | loss:1.9908314943313599 lr:3.326454993179473e-06 tokens_per_second_per_gpu:845.1720589857241 mfu:12.41956259777164 
Step 4632 | loss:1.9974932670593262 lr:3.310377354840999e-06 tokens_per_second_per_gpu:870.5783141874758 mfu:12.792900279132976 
Step 4633 | loss:1.9373300075531006 lr:3.2943380104769604e-06 tokens_per_second_per_gpu:876.1166465759479 mfu:12.874284495582868 
Step 4634 | loss:1.9570585489273071 lr:3.2783369664397436e-06 tokens_per_second_per_gpu:861.1544722464505 mfu:12.654419606879653 
Step 4635 | loss:2.018491506576538 lr:3.262374229066567e-06 tokens_per_second_per_gpu:891.7095851929043 mfu:13.103418285770994 
Step 4636 | loss:1.9641785621643066 lr:3.246449804679497e-06 tokens_per_second_per_gpu:831.701221480685 mfu:12.221612478787561 
Step 4637 | loss:1.9570984840393066 lr:3.230563699585398e-06 tokens_per_second_per_gpu:875.7899684811457 mfu:12.869484054057878 
Step 4638 | loss:2.0167081356048584 lr:3.2147159200759726e-06 tokens_per_second_per_gpu:879.2300356555921 mfu:12.920034861031844 
Step 4639 | loss:1.9980454444885254 lr:3.198906472427732e-06 tokens_per_second_per_gpu:890.9453106401679 mfu:13.09218748897799 
Step 4640 | loss:1.968153953552246 lr:3.1831353629020344e-06 tokens_per_second_per_gpu:902.150312531347 mfu:13.256841799205251 
Step 4641 | loss:1.989732027053833 lr:3.167402597745017e-06 tokens_per_second_per_gpu:890.3926335037617 mfu:13.08406605592897 
Step 4642 | loss:2.004277467727661 lr:3.1517081831876737e-06 tokens_per_second_per_gpu:830.405707266348 mfu:12.202575266529776 
Step 4643 | loss:2.0181725025177 lr:3.1360521254457543e-06 tokens_per_second_per_gpu:874.345951105291 mfu:12.848264630153567 
Step 4644 | loss:1.9243757724761963 lr:3.1204344307198653e-06 tokens_per_second_per_gpu:886.2083438935867 mfu:13.02257911230812 
Step 4645 | loss:1.9511234760284424 lr:3.1048551051954145e-06 tokens_per_second_per_gpu:860.1783177240651 mfu:12.640075294302147 
Step 4646 | loss:1.9734925031661987 lr:3.0893141550425884e-06 tokens_per_second_per_gpu:872.0194044573662 mfu:12.814076690049143 
Step 4647 | loss:1.948981523513794 lr:3.073811586416375e-06 tokens_per_second_per_gpu:863.8414942464841 mfu:12.693904629575568 
Step 4648 | loss:1.960881233215332 lr:3.0583474054566074e-06 tokens_per_second_per_gpu:883.7938755175102 mfu:12.987099187459433 
Step 4649 | loss:2.0346124172210693 lr:3.0429216182878527e-06 tokens_per_second_per_gpu:882.8569370370323 mfu:12.973331143444206 
Step 4650 | loss:1.9998714923858643 lr:3.027534231019513e-06 tokens_per_second_per_gpu:869.6168264696602 mfu:12.778771491069715 
Step 4651 | loss:1.999001383781433 lr:3.012185249745769e-06 tokens_per_second_per_gpu:843.3195692353012 mfu:12.392340788706255 
Step 4652 | loss:1.99674654006958 lr:2.996874680545603e-06 tokens_per_second_per_gpu:873.2997053553428 mfu:12.832890346957637 
Step 4653 | loss:1.9918569326400757 lr:2.981602529482763e-06 tokens_per_second_per_gpu:878.859886116486 mfu:12.914595619018826 
Step 4654 | loss:2.001936912536621 lr:2.966368802605779e-06 tokens_per_second_per_gpu:843.8109919138282 mfu:12.399562104949547 
Step 4655 | loss:2.0323739051818848 lr:2.951173505948013e-06 tokens_per_second_per_gpu:885.753400610807 mfu:13.015893850391512 
Step 4656 | loss:1.9212610721588135 lr:2.9360166455275394e-06 tokens_per_second_per_gpu:883.9768328711627 mfu:12.989787693642587 
Step 4657 | loss:1.9700043201446533 lr:2.920898227347246e-06 tokens_per_second_per_gpu:902.3003747433547 mfu:13.259046920654518 
Step 4658 | loss:1.9828137159347534 lr:2.905818257394799e-06 tokens_per_second_per_gpu:884.9206886029194 mfu:13.00365738469447 
Step 4659 | loss:1.9900506734848022 lr:2.8907767416426203e-06 tokens_per_second_per_gpu:867.9554726041002 mfu:12.754358369373367 
Step 4660 | loss:1.9777334928512573 lr:2.8757736860479113e-06 tokens_per_second_per_gpu:884.2105741613319 mfu:12.993222455303336 
Step 4661 | loss:2.02732515335083 lr:2.8608090965526523e-06 tokens_per_second_per_gpu:873.1660660191562 mfu:12.830926554989306 
Step 4662 | loss:1.948763370513916 lr:2.8458829790835474e-06 tokens_per_second_per_gpu:868.296262775937 mfu:12.759366183849522 
Step 4663 | loss:1.959808349609375 lr:2.8309953395521115e-06 tokens_per_second_per_gpu:879.5544457992838 mfu:12.924801975661456 
Step 4664 | loss:1.9949865341186523 lr:2.8161461838546176e-06 tokens_per_second_per_gpu:869.1885775529448 mfu:12.772478495256582 
Step 4665 | loss:1.972177267074585 lr:2.8013355178720612e-06 tokens_per_second_per_gpu:869.0027391946503 mfu:12.76974765353108 
Step 4666 | loss:2.003058910369873 lr:2.786563347470217e-06 tokens_per_second_per_gpu:880.2883337409097 mfu:12.93558624986204 
Step 4667 | loss:2.022498369216919 lr:2.7718296784996043e-06 tokens_per_second_per_gpu:885.5800787171706 mfu:13.013346934547933 
Step 4668 | loss:1.9798882007598877 lr:2.757134516795512e-06 tokens_per_second_per_gpu:831.7979289392533 mfu:12.223033567337035 
Step 4669 | loss:2.0174107551574707 lr:2.742477868177962e-06 tokens_per_second_per_gpu:902.5622158315477 mfu:13.262894600840946 
Step 4670 | loss:1.9911186695098877 lr:2.7278597384517214e-06 tokens_per_second_per_gpu:898.3009576581617 mfu:13.200276626113826 
Step 4671 | loss:2.002922534942627 lr:2.713280133406326e-06 tokens_per_second_per_gpu:855.0781041894745 mfu:12.565129109579873 
Step 4672 | loss:1.9477660655975342 lr:2.6987390588160245e-06 tokens_per_second_per_gpu:868.7879044996785 mfu:12.766590718899831 
Step 4673 | loss:1.9685595035552979 lr:2.6842365204397977e-06 tokens_per_second_per_gpu:848.134057879271 mfu:12.463088327570475 
Step 4674 | loss:1.9799315929412842 lr:2.6697725240214076e-06 tokens_per_second_per_gpu:835.9623232788252 mfu:12.284228155624996 
Step 4675 | loss:1.9572961330413818 lr:2.6553470752893384e-06 tokens_per_second_per_gpu:890.7595516813487 mfu:13.089457814005156 
Step 4676 | loss:1.9940729141235352 lr:2.6409601799567642e-06 tokens_per_second_per_gpu:875.0958754401524 mfu:12.859284554583608 
Step 4677 | loss:1.9868481159210205 lr:2.626611843721649e-06 tokens_per_second_per_gpu:872.7367945419329 mfu:12.824618532940859 
Step 4678 | loss:1.9647951126098633 lr:2.612302072266637e-06 tokens_per_second_per_gpu:827.3520185173649 mfu:12.157702180429862 
Step 4679 | loss:1.9714818000793457 lr:2.598030871259127e-06 tokens_per_second_per_gpu:885.6727633193877 mfu:13.014708908369531 
Step 4680 | loss:2.0044138431549072 lr:2.5837982463512543e-06 tokens_per_second_per_gpu:870.979121122308 mfu:12.79879002284119 
Step 4681 | loss:1.9878408908843994 lr:2.569604203179843e-06 tokens_per_second_per_gpu:898.4618791346132 mfu:13.20264132136004 
Step 4682 | loss:2.000741958618164 lr:2.55544874736644e-06 tokens_per_second_per_gpu:836.1313937077077 mfu:12.286712597405357 
Step 4683 | loss:1.9836376905441284 lr:2.5413318845173285e-06 tokens_per_second_per_gpu:859.6203576091267 mfu:12.63187622938884 
Step 4684 | loss:1.9998080730438232 lr:2.527253620223513e-06 tokens_per_second_per_gpu:889.3595001881141 mfu:13.068884456219052 
Step 4685 | loss:2.010617256164551 lr:2.5132139600606786e-06 tokens_per_second_per_gpu:885.5690193889591 mfu:13.013184420870921 
Step 4686 | loss:1.9810413122177124 lr:2.4992129095892434e-06 tokens_per_second_per_gpu:876.0837999338593 mfu:12.873801823536143 
Step 4687 | loss:1.9929614067077637 lr:2.48525047435435e-06 tokens_per_second_per_gpu:874.8177644356363 mfu:12.855197792612486 
Step 4688 | loss:1.9373868703842163 lr:2.4713266598858086e-06 tokens_per_second_per_gpu:870.8055013845342 mfu:12.796238730262873 
Step 4689 | loss:2.0128417015075684 lr:2.457441471698152e-06 tokens_per_second_per_gpu:866.1359233434267 mfu:12.727620611419344 
Step 4690 | loss:2.015883684158325 lr:2.4435949152906145e-06 tokens_per_second_per_gpu:841.8435193214036 mfu:12.370650655782214 
Step 4691 | loss:2.0397517681121826 lr:2.429786996147154e-06 tokens_per_second_per_gpu:878.9764751330143 mfu:12.916308861397807 
Step 4692 | loss:1.9694490432739258 lr:2.4160177197363743e-06 tokens_per_second_per_gpu:878.3855280263649 mfu:12.907625062040063 
Step 4693 | loss:1.9986186027526855 lr:2.4022870915116237e-06 tokens_per_second_per_gpu:877.4656955163181 mfu:12.894108385386433 
Step 4694 | loss:2.042973756790161 lr:2.3885951169109187e-06 tokens_per_second_per_gpu:887.2487150579656 mfu:13.037867070142914 
Step 4695 | loss:1.9546058177947998 lr:2.374941801356978e-06 tokens_per_second_per_gpu:887.8115244255897 mfu:13.046137393442773 
Step 4696 | loss:1.9926838874816895 lr:2.3613271502571975e-06 tokens_per_second_per_gpu:870.9120424991888 mfu:12.797804321586701 
Step 4697 | loss:1.9864588975906372 lr:2.3477511690036647e-06 tokens_per_second_per_gpu:874.5389582333595 mfu:12.85110081490835 
Step 4698 | loss:1.983019232749939 lr:2.334213862973167e-06 tokens_per_second_per_gpu:866.3729780796258 mfu:12.731104063225423 
Step 4699 | loss:2.0420572757720947 lr:2.320715237527149e-06 tokens_per_second_per_gpu:894.216071696165 mfu:13.140250390780563 
Step 4700 | loss:1.9568543434143066 lr:2.3072552980117566e-06 tokens_per_second_per_gpu:843.3588551656857 mfu:12.392918084259787 
Step 4701 | loss:1.960659384727478 lr:2.2938340497577926e-06 tokens_per_second_per_gpu:860.232564979731 mfu:12.640872442267863 
Step 4702 | loss:2.005521774291992 lr:2.280451498080749e-06 tokens_per_second_per_gpu:896.8185076092759 mfu:13.17849244502968 
Step 4703 | loss:2.0069305896759033 lr:2.2671076482808194e-06 tokens_per_second_per_gpu:882.2426083861986 mfu:12.964303758956616 
Step 4704 | loss:1.975807547569275 lr:2.2538025056428214e-06 tokens_per_second_per_gpu:873.857446915179 mfu:12.84108620026599 
Step 4705 | loss:2.006671190261841 lr:2.2405360754362504e-06 tokens_per_second_per_gpu:885.771259814047 mfu:13.016156286294624 
Step 4706 | loss:1.9692368507385254 lr:2.2273083629153147e-06 tokens_per_second_per_gpu:880.3401643308938 mfu:12.936347885614126 
Step 4707 | loss:1.994347095489502 lr:2.2141193733188346e-06 tokens_per_second_per_gpu:866.8872229336041 mfu:12.738660744834409 
Step 4708 | loss:1.9976669549942017 lr:2.2009691118703213e-06 tokens_per_second_per_gpu:870.9191098280834 mfu:12.797908173971162 
Step 4709 | loss:1.9731144905090332 lr:2.18785758377793e-06 tokens_per_second_per_gpu:870.1912576491611 mfu:12.787212593583781 
Step 4710 | loss:1.9578230381011963 lr:2.174784794234519e-06 tokens_per_second_per_gpu:827.8295926764943 mfu:12.16471999662637 
Step 4711 | loss:2.0318617820739746 lr:2.161750748417546e-06 tokens_per_second_per_gpu:866.5938872411143 mfu:12.73435026041138 
Step 4712 | loss:1.9572192430496216 lr:2.1487554514891704e-06 tokens_per_second_per_gpu:883.388740160301 mfu:12.981145838817659 
Step 4713 | loss:1.9723278284072876 lr:2.135798908596176e-06 tokens_per_second_per_gpu:867.8437368185871 mfu:12.752716443841354 
Step 4714 | loss:1.9343870878219604 lr:2.122881124870002e-06 tokens_per_second_per_gpu:878.584667549415 mfu:12.910551360591839 
Step 4715 | loss:1.9304231405258179 lr:2.110002105426756e-06 tokens_per_second_per_gpu:880.8121790850068 mfu:12.943284007937919 
Step 4716 | loss:1.9827768802642822 lr:2.097161855367169e-06 tokens_per_second_per_gpu:846.2069522120233 mfu:12.434770058867144 
Step 4717 | loss:2.0183873176574707 lr:2.0843603797766287e-06 tokens_per_second_per_gpu:833.0790339065701 mfu:12.241859039815386 
Step 4718 | loss:2.012674331665039 lr:2.071597683725179e-06 tokens_per_second_per_gpu:871.9792196741048 mfu:12.813486186108687 
Step 4719 | loss:1.9488874673843384 lr:2.058873772267489e-06 tokens_per_second_per_gpu:865.9754507148468 mfu:12.725262511864717 
Step 4720 | loss:2.03238844871521 lr:2.0461886504428594e-06 tokens_per_second_per_gpu:874.0446513090926 mfu:12.843837115495697 
Step 4721 | loss:1.9746201038360596 lr:2.033542323275239e-06 tokens_per_second_per_gpu:873.1431078540174 mfu:12.830589191293901 
Step 4722 | loss:1.9465348720550537 lr:2.0209347957732328e-06 tokens_per_second_per_gpu:886.4865061223807 mfu:13.026666627005408 
Step 4723 | loss:2.0177555084228516 lr:2.008366072930046e-06 tokens_per_second_per_gpu:858.8564160692454 mfu:12.620650326124858 
Step 4724 | loss:2.0353682041168213 lr:1.9958361597235076e-06 tokens_per_second_per_gpu:880.1902631553583 mfu:12.934145130549934 
Step 4725 | loss:1.9634244441986084 lr:1.9833450611161265e-06 tokens_per_second_per_gpu:862.1658592617706 mfu:12.669281650902281 
Step 4726 | loss:2.0115408897399902 lr:1.9708927820550003e-06 tokens_per_second_per_gpu:897.9609681159714 mfu:13.195280576662206 
Step 4727 | loss:2.009265422821045 lr:1.9584793274718406e-06 tokens_per_second_per_gpu:887.2133950663485 mfu:13.037348052929582 
Step 4728 | loss:1.9749083518981934 lr:1.946104702283036e-06 tokens_per_second_per_gpu:841.0301051593866 mfu:12.35869776643184 
Step 4729 | loss:1.9297376871109009 lr:1.933768911389544e-06 tokens_per_second_per_gpu:869.5660153152417 mfu:12.778024835632804 
Step 4730 | loss:1.9613503217697144 lr:1.921471959676957e-06 tokens_per_second_per_gpu:868.8719628007767 mfu:12.767825931684321 
Step 4731 | loss:1.9977952241897583 lr:1.9092138520155013e-06 tokens_per_second_per_gpu:892.8330575592204 mfu:13.119927392090805 
Step 4732 | loss:2.0429837703704834 lr:1.8969945932599931e-06 tokens_per_second_per_gpu:863.3199846315558 mfu:12.686241194374322 
Step 4733 | loss:2.0048606395721436 lr:1.8848141882498838e-06 tokens_per_second_per_gpu:881.0245756492553 mfu:12.946405114932869 
Step 4734 | loss:1.9714980125427246 lr:1.8726726418092255e-06 tokens_per_second_per_gpu:854.9508388055928 mfu:12.563258981024575 
Step 4735 | loss:2.0227317810058594 lr:1.8605699587467052e-06 tokens_per_second_per_gpu:843.012033275975 mfu:12.387821635408049 
Step 4736 | loss:1.9996955394744873 lr:1.848506143855555e-06 tokens_per_second_per_gpu:890.1380628103965 mfu:13.080325212123034 
Step 4737 | loss:1.9554460048675537 lr:1.8364812019136868e-06 tokens_per_second_per_gpu:868.5005626458335 mfu:12.762368312227906 
Step 4738 | loss:1.988952398300171 lr:1.8244951376835906e-06 tokens_per_second_per_gpu:874.8175690183709 mfu:12.855194921011451 
Step 4739 | loss:2.009927988052368 lr:1.8125479559123248e-06 tokens_per_second_per_gpu:828.3096431940437 mfu:12.171774202204288 
Step 4740 | loss:1.942170262336731 lr:1.8006396613315824e-06 tokens_per_second_per_gpu:859.8754509580547 mfu:12.635624753469356 
Step 4741 | loss:1.9934496879577637 lr:1.7887702586576794e-06 tokens_per_second_per_gpu:893.7488913715138 mfu:13.13338530902027 
Step 4742 | loss:1.9827035665512085 lr:1.7769397525914667e-06 tokens_per_second_per_gpu:844.409061792816 mfu:12.408350571417364 
Step 4743 | loss:1.9905433654785156 lr:1.7651481478184296e-06 tokens_per_second_per_gpu:882.2738899079201 mfu:12.964763432005483 
Step 4744 | loss:1.974067211151123 lr:1.7533954490086435e-06 tokens_per_second_per_gpu:898.7047591293473 mfu:13.206210373680541 
Step 4745 | loss:2.0299506187438965 lr:1.7416816608167851e-06 tokens_per_second_per_gpu:846.2978303614004 mfu:12.43610548737896 
Step 4746 | loss:1.9690382480621338 lr:1.730006787882077e-06 tokens_per_second_per_gpu:903.1768571423913 mfu:13.271926579778299 
Step 4747 | loss:1.9714818000793457 lr:1.7183708348283756e-06 tokens_per_second_per_gpu:883.0343650370795 mfu:12.97593839735157 
Step 4748 | loss:1.9596359729766846 lr:1.706773806264106e-06 tokens_per_second_per_gpu:880.5826405815841 mfu:12.93991100503094 
Step 4749 | loss:2.0405094623565674 lr:1.6952157067822717e-06 tokens_per_second_per_gpu:896.0564848968238 mfu:13.167294738388053 
Step 4750 | loss:1.917417049407959 lr:1.6836965409604666e-06 tokens_per_second_per_gpu:889.22169780867 mfu:13.0668594895162 
Step 4751 | loss:1.9695029258728027 lr:1.6722163133608636e-06 tokens_per_second_per_gpu:903.2811621122098 mfu:13.273459311590887 
Step 4752 | loss:1.9690361022949219 lr:1.6607750285302148e-06 tokens_per_second_per_gpu:875.4803574946085 mfu:12.864934408826029 
Step 4753 | loss:1.9923756122589111 lr:1.6493726909998397e-06 tokens_per_second_per_gpu:881.7359948402037 mfu:12.95685921724411 
Step 4754 | loss:1.9397419691085815 lr:1.6380093052856483e-06 tokens_per_second_per_gpu:824.4444484508203 mfu:12.1149762667358 
Step 4755 | loss:2.003732204437256 lr:1.626684875888107e-06 tokens_per_second_per_gpu:872.4675045266672 mfu:12.82066139289347 
Step 4756 | loss:2.008161783218384 lr:1.6153994072922506e-06 tokens_per_second_per_gpu:846.0699467838793 mfu:12.432756803136577 
Step 4757 | loss:1.9821906089782715 lr:1.6041529039677372e-06 tokens_per_second_per_gpu:878.1575860127281 mfu:12.90427551909561 
Step 4758 | loss:1.9460844993591309 lr:1.5929453703687148e-06 tokens_per_second_per_gpu:850.0114933680294 mfu:12.490676707153082 
Step 4759 | loss:1.9623347520828247 lr:1.5817768109339326e-06 tokens_per_second_per_gpu:891.7410628236215 mfu:13.10388084058568 
Step 4760 | loss:2.0121023654937744 lr:1.570647230086708e-06 tokens_per_second_per_gpu:891.156935700988 mfu:13.095297258949879 
Step 4761 | loss:2.041747570037842 lr:1.5595566322349376e-06 tokens_per_second_per_gpu:868.5695068429802 mfu:12.763381427561182 
Step 4762 | loss:2.0226120948791504 lr:1.5485050217710295e-06 tokens_per_second_per_gpu:819.025898282366 mfu:12.035352215880351 
Step 4763 | loss:1.9691171646118164 lr:1.537492403072005e-06 tokens_per_second_per_gpu:895.0276316848339 mfu:13.152176033581883 
Step 4764 | loss:2.0146853923797607 lr:1.5265187804993863e-06 tokens_per_second_per_gpu:873.3535436392717 mfu:12.833681485200202 
Step 4765 | loss:1.9714617729187012 lr:1.5155841583993191e-06 tokens_per_second_per_gpu:840.5619737800419 mfu:12.351818709193802 
Step 4766 | loss:1.968193531036377 lr:1.5046885411024391e-06 tokens_per_second_per_gpu:872.8627054098532 mfu:12.826468757270037 
Step 4767 | loss:1.9770280122756958 lr:1.4938319329239725e-06 tokens_per_second_per_gpu:883.7655360796775 mfu:12.986682747495044 
Step 4768 | loss:1.965705394744873 lr:1.4830143381636795e-06 tokens_per_second_per_gpu:895.9858502440063 mfu:13.166256782290342 
Step 4769 | loss:2.0307674407958984 lr:1.472235761105878e-06 tokens_per_second_per_gpu:881.9281831707763 mfu:12.959683370002983 
Step 4770 | loss:1.95381498336792 lr:1.4614962060194304e-06 tokens_per_second_per_gpu:877.5166413421866 mfu:12.894857019781929 
Step 4771 | loss:1.9880567789077759 lr:1.4507956771577347e-06 tokens_per_second_per_gpu:883.4281201132213 mfu:12.981724516005563 
Step 4772 | loss:1.9636199474334717 lr:1.4401341787587453e-06 tokens_per_second_per_gpu:881.4535453668559 mfu:12.952708702709636 
Step 4773 | loss:1.972710132598877 lr:1.429511715044951e-06 tokens_per_second_per_gpu:851.1301793844102 mfu:12.507115479424337 
Step 4774 | loss:2.0312798023223877 lr:1.418928290223398e-06 tokens_per_second_per_gpu:876.2357817796772 mfu:12.876035153457302 
Step 4775 | loss:1.927262306213379 lr:1.4083839084856442e-06 tokens_per_second_per_gpu:868.3352230709156 mfu:12.759938694283546 
Step 4776 | loss:1.980055570602417 lr:1.3978785740077937e-06 tokens_per_second_per_gpu:853.0254171836048 mfu:12.534965458886514 
Step 4777 | loss:1.988304615020752 lr:1.387412290950507e-06 tokens_per_second_per_gpu:909.6357320707045 mfu:13.366837906567342 
Step 4778 | loss:1.9731122255325317 lr:1.3769850634589354e-06 tokens_per_second_per_gpu:871.3347537818653 mfu:12.804015943445433 
Step 4779 | loss:1.9445406198501587 lr:1.3665968956628084e-06 tokens_per_second_per_gpu:874.5652826038108 mfu:12.85148764403171 
Step 4780 | loss:1.9947563409805298 lr:1.3562477916763684e-06 tokens_per_second_per_gpu:870.2149447576597 mfu:12.787560668894166 
Step 4781 | loss:1.9752578735351562 lr:1.3459377555983699e-06 tokens_per_second_per_gpu:896.9828109821902 mfu:13.180906836280833 
Step 4782 | loss:1.9795037508010864 lr:1.3356667915121025e-06 tokens_per_second_per_gpu:876.6261611825506 mfu:12.881771667554426 
Step 4783 | loss:1.9496095180511475 lr:1.3254349034854008e-06 tokens_per_second_per_gpu:897.8332785804868 mfu:13.193404215319955 
Step 4784 | loss:1.961460828781128 lr:1.3152420955706012e-06 tokens_per_second_per_gpu:854.665297876606 mfu:12.559063038430315 
Step 4785 | loss:2.0030484199523926 lr:1.3050883718045749e-06 tokens_per_second_per_gpu:892.9276020092469 mfu:13.12131669584605 
Step 4786 | loss:1.9145517349243164 lr:1.2949737362087156e-06 tokens_per_second_per_gpu:876.856883334115 mfu:12.885162063833599 
Step 4787 | loss:1.9868979454040527 lr:1.2848981927889193e-06 tokens_per_second_per_gpu:892.649364188582 mfu:13.117228070347755 
Step 4788 | loss:2.022010087966919 lr:1.2748617455356049e-06 tokens_per_second_per_gpu:886.174727139435 mfu:13.02208512368405 
Step 4789 | loss:1.9420897960662842 lr:1.2648643984237373e-06 tokens_per_second_per_gpu:867.5615501091922 mfu:12.748569790548302 
Step 4790 | loss:2.006608009338379 lr:1.2549061554127494e-06 tokens_per_second_per_gpu:869.3522283626189 mfu:12.77488329727685 
Step 4791 | loss:2.012989044189453 lr:1.2449870204465973e-06 tokens_per_second_per_gpu:881.6093828482799 mfu:12.954998690097469 
Step 4792 | loss:1.992772102355957 lr:1.2351069974537944e-06 tokens_per_second_per_gpu:831.5001968439427 mfu:12.21865847902719 
Step 4793 | loss:2.0210351943969727 lr:1.225266090347299e-06 tokens_per_second_per_gpu:873.2329821254013 mfu:12.831909868104635 
Step 4794 | loss:1.9930026531219482 lr:1.2154643030246271e-06 tokens_per_second_per_gpu:882.6872002461396 mfu:12.970836909663966 
Step 4795 | loss:2.0254995822906494 lr:1.2057016393677623e-06 tokens_per_second_per_gpu:881.6927105687241 mfu:12.956223167207405 
Step 4796 | loss:1.9954872131347656 lr:1.1959781032432337e-06 tokens_per_second_per_gpu:883.2928730172438 mfu:12.979737098465192 
Step 4797 | loss:1.967153549194336 lr:1.186293698502039e-06 tokens_per_second_per_gpu:878.5313071515634 mfu:12.909767244749018 
Step 4798 | loss:2.0005714893341064 lr:1.1766484289796986e-06 tokens_per_second_per_gpu:889.38032408477 mfu:13.069190457447203 
Step 4799 | loss:1.974826693534851 lr:1.1670422984962126e-06 tokens_per_second_per_gpu:866.0046881961454 mfu:12.725692148321965 
Step 4800 | loss:1.9958860874176025 lr:1.1574753108561154e-06 tokens_per_second_per_gpu:852.5481144259911 mfu:12.527951630857952 
Step 4801 | loss:1.9868998527526855 lr:1.1479474698483983e-06 tokens_per_second_per_gpu:899.2625304489454 mfu:13.214406664300116 
Step 4802 | loss:1.9980219602584839 lr:1.1384587792465872e-06 tokens_per_second_per_gpu:854.861927096598 mfu:12.561952448793896 
Step 4803 | loss:2.0321204662323 lr:1.129009242808654e-06 tokens_per_second_per_gpu:866.8110295829631 mfu:12.737541105255982 
Step 4804 | loss:2.020388126373291 lr:1.119598864277116e-06 tokens_per_second_per_gpu:861.9863821840354 mfu:12.666644286382121 
Step 4805 | loss:2.0162365436553955 lr:1.1102276473789585e-06 tokens_per_second_per_gpu:889.6314273625738 mfu:13.07288034856941 
Step 4806 | loss:2.005471706390381 lr:1.1008955958256461e-06 tokens_per_second_per_gpu:896.1591085181777 mfu:13.16880276326401 
Step 4807 | loss:1.9829704761505127 lr:1.0916027133131335e-06 tokens_per_second_per_gpu:877.0550696647379 mfu:12.888074355494243 
Step 4808 | loss:2.0016582012176514 lr:1.0823490035218987e-06 tokens_per_second_per_gpu:870.1882964086552 mfu:12.787169078998273 
Step 4809 | loss:1.9742748737335205 lr:1.0731344701168656e-06 tokens_per_second_per_gpu:880.4282471666544 mfu:12.937642237788793 
Step 4810 | loss:2.053349018096924 lr:1.0639591167474484e-06 tokens_per_second_per_gpu:868.4419907899719 mfu:12.761507615494493 
Step 4811 | loss:2.006589889526367 lr:1.0548229470475623e-06 tokens_per_second_per_gpu:801.7488586962197 mfu:11.78147104178921 
Step 4812 | loss:1.9573110342025757 lr:1.04572596463558e-06 tokens_per_second_per_gpu:877.6463117014702 mfu:12.896762488765525 
Step 4813 | loss:2.0067362785339355 lr:1.0366681731143747e-06 tokens_per_second_per_gpu:887.4622584299511 mfu:13.041005029150808 
Step 4814 | loss:1.9981526136398315 lr:1.0276495760712767e-06 tokens_per_second_per_gpu:854.0082711074824 mfu:12.549408217260133 
Step 4815 | loss:2.0064382553100586 lr:1.0186701770781183e-06 tokens_per_second_per_gpu:855.3404384944247 mfu:12.568984037446018 
Step 4816 | loss:2.0149290561676025 lr:1.0097299796911986e-06 tokens_per_second_per_gpu:898.5262504037175 mfu:13.203587238818669 
Step 4817 | loss:2.0223023891448975 lr:1.0008289874512744e-06 tokens_per_second_per_gpu:825.8398753289114 mfu:12.135481667120029 
Step 4818 | loss:1.9738984107971191 lr:9.919672038835925e-07 tokens_per_second_per_gpu:889.823010529922 mfu:13.075695608627127 
Step 4819 | loss:1.931369662284851 lr:9.831446324978788e-07 tokens_per_second_per_gpu:867.9208886628738 mfu:12.753850168210807 
Step 4820 | loss:1.9232213497161865 lr:9.743612767882936e-07 tokens_per_second_per_gpu:853.8523901114852 mfu:12.547117590438047 
Step 4821 | loss:1.9617128372192383 lr:9.656171402335213e-07 tokens_per_second_per_gpu:892.8223294617541 mfu:13.11976974575522 
Step 4822 | loss:1.9699548482894897 lr:9.569122262966468e-07 tokens_per_second_per_gpu:898.2981775296298 mfu:13.200235772917175 
Step 4823 | loss:1.9740238189697266 lr:9.482465384252792e-07 tokens_per_second_per_gpu:873.9446249222831 mfu:12.842367256241358 
Step 4824 | loss:1.9899673461914062 lr:9.396200800514621e-07 tokens_per_second_per_gpu:892.554826226055 mfu:13.115838861924466 
Step 4825 | loss:1.9937626123428345 lr:9.310328545917069e-07 tokens_per_second_per_gpu:888.8442259773735 mfu:13.061312648505734 
Step 4826 | loss:1.9408419132232666 lr:9.224848654469931e-07 tokens_per_second_per_gpu:891.7336703727279 mfu:13.103772210626078 
Step 4827 | loss:1.994915246963501 lr:9.13976116002746e-07 tokens_per_second_per_gpu:881.0631437674137 mfu:12.94697186244026 
Step 4828 | loss:1.9727768898010254 lr:9.0550660962887e-07 tokens_per_second_per_gpu:893.9270073144215 mfu:13.136002672051955 
Step 4829 | loss:2.0109567642211914 lr:8.970763496797152e-07 tokens_per_second_per_gpu:882.2817460470086 mfu:12.964878875730996 
Step 4830 | loss:1.951974868774414 lr:8.886853394940886e-07 tokens_per_second_per_gpu:849.4574596236212 mfu:12.482535339136001 
Step 4831 | loss:1.9895308017730713 lr:8.803335823952541e-07 tokens_per_second_per_gpu:837.7910898811714 mfu:12.311101359788665 
Step 4832 | loss:1.9442862272262573 lr:8.720210816909435e-07 tokens_per_second_per_gpu:883.7050731127806 mfu:12.985794261423786 
Step 4833 | loss:1.9987461566925049 lr:8.637478406733013e-07 tokens_per_second_per_gpu:867.4504360145957 mfu:12.746937000587176 
Step 4834 | loss:1.9845737218856812 lr:8.555138626189618e-07 tokens_per_second_per_gpu:865.4977395763871 mfu:12.718242682795978 
Step 4835 | loss:1.9870595932006836 lr:8.473191507889944e-07 tokens_per_second_per_gpu:880.5537814679124 mfu:12.93948692857816 
Step 4836 | loss:2.0283050537109375 lr:8.39163708428925e-07 tokens_per_second_per_gpu:867.0193803373227 mfu:12.74060276022736 
Step 4837 | loss:1.9712616205215454 lr:8.310475387687144e-07 tokens_per_second_per_gpu:884.2507747398894 mfu:12.993813191351164 
Step 4838 | loss:1.9693505764007568 lr:8.229706450227803e-07 tokens_per_second_per_gpu:895.3975501184625 mfu:13.157611879565758 
Step 4839 | loss:1.981036901473999 lr:8.149330303899749e-07 tokens_per_second_per_gpu:875.4315824963963 mfu:12.864217674124424 
Step 4840 | loss:1.983665943145752 lr:8.069346980536075e-07 tokens_per_second_per_gpu:888.0383838572825 mfu:13.049471028154011 
Step 4841 | loss:1.9928333759307861 lr:7.989756511814106e-07 tokens_per_second_per_gpu:905.9066446897305 mfu:13.31204003000698 
Step 4842 | loss:1.9552831649780273 lr:7.910558929255851e-07 tokens_per_second_per_gpu:867.723170367002 mfu:12.750944754187476 
Step 4843 | loss:2.0218052864074707 lr:7.831754264227332e-07 tokens_per_second_per_gpu:854.8307322119855 mfu:12.561494048852657 
Step 4844 | loss:1.9971089363098145 lr:7.753342547939357e-07 tokens_per_second_per_gpu:858.0858652503035 mfu:12.60932730138822 
Step 4845 | loss:2.0018272399902344 lr:7.675323811446756e-07 tokens_per_second_per_gpu:846.7524873069053 mfu:12.442786541650898 
Step 4846 | loss:2.0047361850738525 lr:7.597698085649141e-07 tokens_per_second_per_gpu:882.2501796991376 mfu:12.964415017243011 
Step 4847 | loss:1.9750306606292725 lr:7.520465401290033e-07 tokens_per_second_per_gpu:853.9579996137543 mfu:12.548669491983306 
Step 4848 | loss:1.9829342365264893 lr:7.44362578895752e-07 tokens_per_second_per_gpu:884.9294987159643 mfu:13.003786846795462 
Step 4849 | loss:2.0219037532806396 lr:7.367179279083924e-07 tokens_per_second_per_gpu:894.2843303343934 mfu:13.141253432020868 
Step 4850 | loss:1.9821383953094482 lr:7.291125901946027e-07 tokens_per_second_per_gpu:879.5360167018545 mfu:12.924531165325607 
Step 4851 | loss:1.9903879165649414 lr:7.215465687664735e-07 tokens_per_second_per_gpu:867.4783551544512 mfu:12.747347264392545 
Step 4852 | loss:2.01522159576416 lr:7.1401986662053e-07 tokens_per_second_per_gpu:900.4732427227432 mfu:13.232197736203709 
Step 4853 | loss:1.9903392791748047 lr:7.065324867377321e-07 tokens_per_second_per_gpu:881.1679611230052 mfu:12.948512123615792 
Step 4854 | loss:2.062750816345215 lr:6.990844320834633e-07 tokens_per_second_per_gpu:864.4899211421254 mfu:12.70343307805523 
Step 4855 | loss:2.019343137741089 lr:6.916757056075196e-07 tokens_per_second_per_gpu:854.234520725384 mfu:12.552732890931459 
Step 4856 | loss:1.9928874969482422 lr:6.843063102441316e-07 tokens_per_second_per_gpu:867.5112185637096 mfu:12.747830182828055 
Step 4857 | loss:2.0356976985931396 lr:6.769762489119535e-07 tokens_per_second_per_gpu:890.686398124576 mfu:13.088382843331518 
Step 4858 | loss:1.9744983911514282 lr:6.696855245140743e-07 tokens_per_second_per_gpu:826.5367317292487 mfu:12.145721773372514 
Step 4859 | loss:1.9861171245574951 lr:6.62434139937973e-07 tokens_per_second_per_gpu:842.6920721344242 mfu:12.383119897597272 
Step 4860 | loss:1.9654872417449951 lr:6.552220980555635e-07 tokens_per_second_per_gpu:873.131801344393 mfu:12.830423045356456 
Step 4861 | loss:1.9941039085388184 lr:6.480494017231831e-07 tokens_per_second_per_gpu:874.6416446504371 mfu:12.852609762549575 
Step 4862 | loss:1.9547350406646729 lr:6.409160537815817e-07 tokens_per_second_per_gpu:851.1617043703325 mfu:12.507578730110268 
Step 4863 | loss:2.022465705871582 lr:6.338220570559328e-07 tokens_per_second_per_gpu:864.3906475627357 mfu:12.701974281091434 
Step 4864 | loss:1.9951847791671753 lr:6.26767414355811e-07 tokens_per_second_per_gpu:858.5607568577653 mfu:12.616305698252292 
Step 4865 | loss:1.9190973043441772 lr:6.197521284751929e-07 tokens_per_second_per_gpu:877.9380968765337 mfu:12.901050188776752 
Step 4866 | loss:2.015712022781372 lr:6.127762021925221e-07 tokens_per_second_per_gpu:887.8623801276626 mfu:13.046884703494772 
Step 4867 | loss:1.9991464614868164 lr:6.058396382706e-07 tokens_per_second_per_gpu:879.4467085097729 mfu:12.923218806888935 
Step 4868 | loss:1.942647933959961 lr:5.989424394566401e-07 tokens_per_second_per_gpu:871.9584117876292 mfu:12.813180420145576 
Step 4869 | loss:1.9689114093780518 lr:5.920846084823017e-07 tokens_per_second_per_gpu:875.6573541660143 mfu:12.867535324481901 
Step 4870 | loss:1.9939296245574951 lr:5.852661480636346e-07 tokens_per_second_per_gpu:862.1850948611681 mfu:12.66956431255476 
Step 4871 | loss:1.9813027381896973 lr:5.784870609010895e-07 tokens_per_second_per_gpu:867.8917216904481 mfu:12.753421567861354 
Step 4872 | loss:1.9753769636154175 lr:5.717473496795189e-07 tokens_per_second_per_gpu:856.9466788210098 mfu:12.59258728139025 
Step 4873 | loss:1.9853984117507935 lr:5.650470170681876e-07 tokens_per_second_per_gpu:868.8833114966288 mfu:12.767992697536362 
Step 4874 | loss:1.984114408493042 lr:5.58386065720784e-07 tokens_per_second_per_gpu:828.4567250579611 mfu:12.173935528287537 
Step 4875 | loss:2.0048580169677734 lr:5.517644982753645e-07 tokens_per_second_per_gpu:893.2600192481851 mfu:13.126201472458904 
Step 4876 | loss:1.9916150569915771 lr:5.451823173544091e-07 tokens_per_second_per_gpu:864.8072779429491 mfu:12.708096545821059 
Step 4877 | loss:1.9473069906234741 lr:5.386395255647992e-07 tokens_per_second_per_gpu:892.5942646197491 mfu:13.116418397882892 
Step 4878 | loss:1.9824949502944946 lr:5.321361254977953e-07 tokens_per_second_per_gpu:882.6676813499615 mfu:12.970550085046014 
Step 4879 | loss:1.959214210510254 lr:5.256721197290926e-07 tokens_per_second_per_gpu:886.9127720472062 mfu:13.03293048331772 
Step 4880 | loss:1.9575788974761963 lr:5.192475108187544e-07 tokens_per_second_per_gpu:888.1917728345352 mfu:13.051725035470682 
Step 4881 | loss:1.970076560974121 lr:5.128623013112455e-07 tokens_per_second_per_gpu:854.2504071646727 mfu:12.552966337630393 
Step 4882 | loss:1.9668591022491455 lr:5.065164937354428e-07 tokens_per_second_per_gpu:894.8331611615898 mfu:13.149318344651952 
Step 4883 | loss:1.9861187934875488 lr:5.002100906045914e-07 tokens_per_second_per_gpu:882.7082798873362 mfu:12.971146668985273 
Step 4884 | loss:1.9367262125015259 lr:4.939430944163603e-07 tokens_per_second_per_gpu:868.0553640216499 mfu:12.755826245292887 
Step 4885 | loss:1.9381364583969116 lr:4.877155076527862e-07 tokens_per_second_per_gpu:866.8439428072071 mfu:12.738024755708512 
Step 4886 | loss:1.9514857530593872 lr:4.815273327803182e-07 tokens_per_second_per_gpu:873.563755595048 mfu:12.836770489996098 
Step 4887 | loss:1.9720113277435303 lr:4.753785722497739e-07 tokens_per_second_per_gpu:871.4832544711502 mfu:12.806198118763202 
Step 4888 | loss:1.959126353263855 lr:4.6926922849637176e-07 tokens_per_second_per_gpu:868.852405538932 mfu:12.767538543293828 
Step 4889 | loss:2.004474639892578 lr:4.6319930393974306e-07 tokens_per_second_per_gpu:863.4585337049563 mfu:12.688277133532115 
Step 4890 | loss:1.9951964616775513 lr:4.571688009838648e-07 tokens_per_second_per_gpu:867.7363299605216 mfu:12.751138130664776 
Step 4891 | loss:1.9942810535430908 lr:4.5117772201712647e-07 tokens_per_second_per_gpu:850.8665470443099 mfu:12.503241477301499 
Step 4892 | loss:1.9884999990463257 lr:4.452260694122856e-07 tokens_per_second_per_gpu:824.640402086622 mfu:12.117855749582192 
Step 4893 | loss:1.988978385925293 lr:4.393138455265233e-07 tokens_per_second_per_gpu:875.9697479405567 mfu:12.872125861990606 
Step 4894 | loss:1.9422119855880737 lr:4.334410527013555e-07 tokens_per_second_per_gpu:870.7495199391442 mfu:12.795416098873273 
Step 4895 | loss:1.955984115600586 lr:4.2760769326271044e-07 tokens_per_second_per_gpu:880.5334817541599 mfu:12.939188630068426 
Step 4896 | loss:2.051006317138672 lr:4.218137695209068e-07 tokens_per_second_per_gpu:884.4542111988918 mfu:12.996802632152463 
Step 4897 | loss:1.9703080654144287 lr:4.16059283770609e-07 tokens_per_second_per_gpu:857.1652320110064 mfu:12.595798858246404 
Step 4898 | loss:1.9949431419372559 lr:4.103442382909051e-07 tokens_per_second_per_gpu:869.2828878538617 mfu:12.773864358257374 
Step 4899 | loss:1.9876666069030762 lr:4.0466863534522893e-07 tokens_per_second_per_gpu:882.4375236629336 mfu:12.967167983412375 
Step 4900 | loss:1.972165822982788 lr:3.990324771814047e-07 tokens_per_second_per_gpu:861.1146718336602 mfu:12.653834751153752 
Step 4901 | loss:1.991074800491333 lr:3.934357660316468e-07 tokens_per_second_per_gpu:885.9061999495676 mfu:13.018139193138541 
Step 4902 | loss:1.9958065748214722 lr:3.8787850411252656e-07 tokens_per_second_per_gpu:857.9666299639254 mfu:12.607575172827778 
Step 4903 | loss:1.946793794631958 lr:3.823606936249946e-07 tokens_per_second_per_gpu:837.8891276286432 mfu:12.312541996554549 
Step 4904 | loss:1.937709927558899 lr:3.7688233675439166e-07 tokens_per_second_per_gpu:833.8476198530776 mfu:12.253153191311442 
Step 4905 | loss:1.9915452003479004 lr:3.714434356704377e-07 tokens_per_second_per_gpu:858.1012873692448 mfu:12.609553925031944 
Step 4906 | loss:2.0169677734375 lr:3.6604399252717636e-07 tokens_per_second_per_gpu:852.8546136212514 mfu:12.532455549203608 
Step 4907 | loss:2.012174129486084 lr:3.60684009463097e-07 tokens_per_second_per_gpu:892.6354841752053 mfu:13.11702410750592 
Step 4908 | loss:1.9966249465942383 lr:3.5536348860100156e-07 tokens_per_second_per_gpu:842.61235612246 mfu:12.381948493514392 
Step 4909 | loss:2.000462293624878 lr:3.500824320480933e-07 tokens_per_second_per_gpu:856.1808544112888 mfu:12.581333709890448 
Step 4910 | loss:1.9744696617126465 lr:3.4484084189593257e-07 tokens_per_second_per_gpu:880.8374723604798 mfu:12.943655685414356 
Step 4911 | loss:1.9660530090332031 lr:3.3963872022045875e-07 tokens_per_second_per_gpu:872.427844701303 mfu:12.820078603059741 
Step 4912 | loss:1.9346530437469482 lr:3.3447606908196817e-07 tokens_per_second_per_gpu:860.2566489610693 mfu:12.641226349511548 
Step 4913 | loss:2.0313892364501953 lr:3.293528905251364e-07 tokens_per_second_per_gpu:836.5077008990498 mfu:12.292242324363528 
Step 4914 | loss:1.9868029356002808 lr:3.2426918657900704e-07 tokens_per_second_per_gpu:871.6516775088977 mfu:12.80867304731529 
Step 4915 | loss:1.9368619918823242 lr:3.192249592569696e-07 tokens_per_second_per_gpu:858.0741607023695 mfu:12.609155306391225 
Step 4916 | loss:2.00058650970459 lr:3.1422021055679265e-07 tokens_per_second_per_gpu:871.1211748550156 mfu:12.800877461968943 
Step 4917 | loss:1.9414838552474976 lr:3.092549424606239e-07 tokens_per_second_per_gpu:872.1512561901442 mfu:12.816014213694713 
Step 4918 | loss:1.9157450199127197 lr:3.043291569349571e-07 tokens_per_second_per_gpu:847.6353881846472 mfu:12.45576051849048 
Step 4919 | loss:1.9695789813995361 lr:2.994428559306539e-07 tokens_per_second_per_gpu:888.8099692047875 mfu:13.060809254993126 
Step 4920 | loss:1.9886640310287476 lr:2.9459604138291076e-07 tokens_per_second_per_gpu:888.0100444668495 mfu:13.049054588886145 
Step 4921 | loss:2.017700433731079 lr:2.8978871521134764e-07 tokens_per_second_per_gpu:886.3290305678906 mfu:13.024352568600598 
Step 4922 | loss:1.9659844636917114 lr:2.850208793198861e-07 tokens_per_second_per_gpu:892.395978807519 mfu:13.113504644368376 
Step 4923 | loss:1.9568344354629517 lr:2.8029253559683775e-07 tokens_per_second_per_gpu:888.0424767969531 mfu:13.049531172736298 
Step 4924 | loss:1.9791858196258545 lr:2.756036859148603e-07 tokens_per_second_per_gpu:864.3152485475691 mfu:12.70086631404648 
Step 4925 | loss:1.9856529235839844 lr:2.709543321309793e-07 tokens_per_second_per_gpu:857.3593281364891 mfu:12.598651045507907 
Step 4926 | loss:1.971391201019287 lr:2.6634447608657743e-07 tokens_per_second_per_gpu:884.0187372353331 mfu:12.99040346633455 
Step 4927 | loss:1.9738606214523315 lr:2.6177411960737197e-07 tokens_per_second_per_gpu:881.1967900555818 mfu:12.948935756565978 
Step 4928 | loss:1.9736223220825195 lr:2.572432645034817e-07 tokens_per_second_per_gpu:863.655584221277 mfu:12.691172734725207 
Step 4929 | loss:1.9969308376312256 lr:2.5275191256933784e-07 tokens_per_second_per_gpu:896.7240706260814 mfu:13.177104720468911 
Step 4930 | loss:1.977583885192871 lr:2.4830006558373973e-07 tokens_per_second_per_gpu:876.5965768796304 mfu:12.881336934652264 
Step 4931 | loss:1.9367398023605347 lr:2.438877253098548e-07 tokens_per_second_per_gpu:883.0223669324254 mfu:12.975762088622213 
Step 4932 | loss:1.977508783340454 lr:2.3951489349518517e-07 tokens_per_second_per_gpu:874.382225751211 mfu:12.848797675739876 
Step 4933 | loss:2.021160125732422 lr:2.3518157187160106e-07 tokens_per_second_per_gpu:874.506115640876 mfu:12.850618202369416 
Step 4934 | loss:2.001491069793701 lr:2.3088776215531848e-07 tokens_per_second_per_gpu:888.9441665398627 mfu:13.06278124659614 
Step 4935 | loss:2.026644229888916 lr:2.266334660468772e-07 tokens_per_second_per_gpu:859.0840118254706 mfu:12.623994780915305 
Step 4936 | loss:1.9696907997131348 lr:2.2241868523121823e-07 tokens_per_second_per_gpu:874.2992409660332 mfu:12.847578237965969 
Step 4937 | loss:1.9356706142425537 lr:2.1824342137760633e-07 tokens_per_second_per_gpu:889.4784039017939 mfu:13.070631712413165 
Step 4938 | loss:1.9991261959075928 lr:2.141076761396521e-07 tokens_per_second_per_gpu:871.9075587563215 mfu:12.81243314933971 
Step 4939 | loss:2.030883312225342 lr:2.1001145115531194e-07 tokens_per_second_per_gpu:886.7332994256888 mfu:13.030293184280413 
Step 4940 | loss:1.9214725494384766 lr:2.0595474804691038e-07 tokens_per_second_per_gpu:864.6273220604675 mfu:12.705452145401576 
Step 4941 | loss:2.037709951400757 lr:2.0193756842110668e-07 tokens_per_second_per_gpu:864.9144344186194 mfu:12.709671179699683 
Step 4942 | loss:1.9582576751708984 lr:1.979599138688948e-07 tokens_per_second_per_gpu:853.7958555484157 mfu:12.546286831141742 
Step 4943 | loss:2.0395593643188477 lr:1.940217859656257e-07 tokens_per_second_per_gpu:878.9375334160285 mfu:12.915736623962095 
Step 4944 | loss:2.018773078918457 lr:1.9012318627101844e-07 tokens_per_second_per_gpu:896.08023814186 mfu:13.167643785556011 
Step 4945 | loss:2.057999610900879 lr:1.8626411632909345e-07 tokens_per_second_per_gpu:856.6931157592902 mfu:12.588861244444248 
Step 4946 | loss:1.9995200634002686 lr:1.824445776682504e-07 tokens_per_second_per_gpu:865.4976238115878 mfu:12.718240981665238 
Step 4947 | loss:1.9830703735351562 lr:1.7866457180121254e-07 tokens_per_second_per_gpu:876.0738001591793 mfu:12.873654879696387 
Step 4948 | loss:2.0001888275146484 lr:1.7492410022506013e-07 tokens_per_second_per_gpu:871.681607551251 mfu:12.809112860759912 
Step 4949 | loss:1.9665825366973877 lr:1.712231644212081e-07 tokens_per_second_per_gpu:859.9809708034196 mfu:12.637175337531955 
Step 4950 | loss:1.970294713973999 lr:1.675617658554063e-07 tokens_per_second_per_gpu:854.5507756846681 mfu:12.557380167449804 
Step 4951 | loss:2.0063345432281494 lr:1.6393990597775022e-07 tokens_per_second_per_gpu:877.237055651269 mfu:12.890748587714311 
Step 4952 | loss:1.9677157402038574 lr:1.6035758622269247e-07 tokens_per_second_per_gpu:892.7038121653593 mfu:13.11802816785301 
Step 4953 | loss:1.9998977184295654 lr:1.5681480800900926e-07 tokens_per_second_per_gpu:883.3210747093389 mfu:12.980151514295217 
Step 4954 | loss:2.0592548847198486 lr:1.5331157273981157e-07 tokens_per_second_per_gpu:854.8021246599928 mfu:12.561073669027078 
Step 4955 | loss:1.9976158142089844 lr:1.4984788180256726e-07 tokens_per_second_per_gpu:850.044348580909 mfu:12.491159505145138 
Step 4956 | loss:1.9977667331695557 lr:1.4642373656906793e-07 tokens_per_second_per_gpu:872.4416706278137 mfu:12.82028177111049 
Step 4957 | loss:1.9863015413284302 lr:1.4303913839545103e-07 tokens_per_second_per_gpu:896.3025273836115 mfu:13.170910262628215 
Step 4958 | loss:1.9679269790649414 lr:1.3969408862217758e-07 tokens_per_second_per_gpu:853.0045028756232 mfu:12.534658129089694 
Step 4959 | loss:1.9241931438446045 lr:1.3638858857406568e-07 tokens_per_second_per_gpu:899.0769831791562 mfu:13.211680100037261 
Step 4960 | loss:1.9939799308776855 lr:1.3312263956026804e-07 tokens_per_second_per_gpu:886.1382148472159 mfu:13.021548585953083 
Step 4961 | loss:2.023094654083252 lr:1.2989624287425007e-07 tokens_per_second_per_gpu:855.2576334968556 mfu:12.567767241599796 
Step 4962 | loss:1.972769021987915 lr:1.2670939979384512e-07 tokens_per_second_per_gpu:896.0361075405708 mfu:13.166995298943892 
Step 4963 | loss:1.9907664060592651 lr:1.2356211158117692e-07 tokens_per_second_per_gpu:879.0491372803331 mfu:12.917376610949534 
Step 4964 | loss:1.9821041822433472 lr:1.204543794827595e-07 tokens_per_second_per_gpu:825.2356215943361 mfu:12.126602330656278 
Step 4965 | loss:2.0370635986328125 lr:1.1738620472939721e-07 tokens_per_second_per_gpu:865.4547518008084 mfu:12.717610989682058 
Step 4966 | loss:1.9849779605865479 lr:1.1435758853624024e-07 tokens_per_second_per_gpu:867.4448898299544 mfu:12.746855500984108 
Step 4967 | loss:1.9509875774383545 lr:1.1136853210278463e-07 tokens_per_second_per_gpu:878.6665613818514 mfu:12.911754767126048 
Step 4968 | loss:1.9529694318771362 lr:1.0841903661283903e-07 tokens_per_second_per_gpu:883.0638703360262 mfu:12.976371969312849 
Step 4969 | loss:2.01114559173584 lr:1.0550910323455787e-07 tokens_per_second_per_gpu:898.0600569622436 mfu:13.196736659025479 
Step 4970 | loss:1.9812052249908447 lr:1.0263873312040818e-07 tokens_per_second_per_gpu:884.8702912079776 mfu:13.002916809335183 
Step 4971 | loss:1.9869275093078613 lr:9.98079274072139e-08 tokens_per_second_per_gpu:893.0446475212176 mfu:13.12303664629549 
Step 4972 | loss:1.9991635084152222 lr:9.701668721612267e-08 tokens_per_second_per_gpu:879.6113547119511 mfu:12.925638235918441 
Step 4973 | loss:1.9165856838226318 lr:9.426501365259465e-08 tokens_per_second_per_gpu:877.7251564005719 mfu:12.89792108915415 
Step 4974 | loss:2.0163302421569824 lr:9.155290780643588e-08 tokens_per_second_per_gpu:882.7314142644427 mfu:12.971486622065337 
Step 4975 | loss:1.9806843996047974 lr:8.888037075177602e-08 tokens_per_second_per_gpu:878.9861658684708 mfu:12.916451263994228 
Step 4976 | loss:2.027698516845703 lr:8.624740354707949e-08 tokens_per_second_per_gpu:846.4887007886373 mfu:12.438910273923815 
Step 4977 | loss:1.9759981632232666 lr:8.365400723512328e-08 tokens_per_second_per_gpu:903.5234078521999 mfu:13.277019043718639 
Step 4978 | loss:2.0208380222320557 lr:8.110018284304133e-08 tokens_per_second_per_gpu:868.3917783157524 mfu:12.760769757492529 
Step 4979 | loss:1.9558753967285156 lr:7.85859313822579e-08 tokens_per_second_per_gpu:882.3414119007075 mfu:12.965755648450921 
Step 4980 | loss:1.9838063716888428 lr:7.611125384855422e-08 tokens_per_second_per_gpu:875.8282809032029 mfu:12.870047044183915 
Step 4981 | loss:2.0166006088256836 lr:7.367615122202409e-08 tokens_per_second_per_gpu:838.2564396973863 mfu:12.317939542749043 
Step 4982 | loss:2.0162100791931152 lr:7.128062446709604e-08 tokens_per_second_per_gpu:859.3384648387719 mfu:12.627733895446232 
Step 4983 | loss:2.0155861377716064 lr:6.892467453251116e-08 tokens_per_second_per_gpu:899.7952522595981 mfu:13.22223485952292 
Step 4984 | loss:1.977239727973938 lr:6.66083023513564e-08 tokens_per_second_per_gpu:884.0299692184723 mfu:12.99056851712653 
Step 4985 | loss:1.999682903289795 lr:6.433150884102012e-08 tokens_per_second_per_gpu:882.2232788105842 mfu:12.964019716350403 
Step 4986 | loss:1.9222980737686157 lr:6.20942949032366e-08 tokens_per_second_per_gpu:907.1687917818341 mfu:13.330586921910609 
Step 4987 | loss:1.9765530824661255 lr:5.989666142404149e-08 tokens_per_second_per_gpu:843.6910389186453 mfu:12.397799429862712 
Step 4988 | loss:1.9426547288894653 lr:5.773860927383856e-08 tokens_per_second_per_gpu:867.1964494418563 mfu:12.743204740267407 
Step 4989 | loss:1.985858678817749 lr:5.56201393072886e-08 tokens_per_second_per_gpu:875.8086953851656 mfu:12.869759240576723 
Step 4990 | loss:1.9504258632659912 lr:5.354125236343155e-08 tokens_per_second_per_gpu:904.3370801720997 mfu:13.288975726625546 
Step 4991 | loss:2.0068349838256836 lr:5.150194926561991e-08 tokens_per_second_per_gpu:887.5225962972518 mfu:13.041891676919139 
Step 4992 | loss:2.0089120864868164 lr:4.9502230821507625e-08 tokens_per_second_per_gpu:835.4680495667733 mfu:12.27696494425638 
Step 4993 | loss:1.9843260049819946 lr:4.7542097823083386e-08 tokens_per_second_per_gpu:881.8811328670921 mfu:12.95899197919606 
Step 4994 | loss:1.9846417903900146 lr:4.562155104665955e-08 tokens_per_second_per_gpu:872.515559382583 mfu:12.821367545309215 
Step 4995 | loss:2.0099613666534424 lr:4.3740591252883215e-08 tokens_per_second_per_gpu:825.247964167395 mfu:12.126783701250696 
Step 4996 | loss:1.970369577407837 lr:4.1899219186691816e-08 tokens_per_second_per_gpu:874.899339279661 mfu:12.856396511702874 
Step 4997 | loss:1.9385912418365479 lr:4.009743557736867e-08 tokens_per_second_per_gpu:894.0091535429011 mfu:13.137209787474108 
Step 4998 | loss:2.0031611919403076 lr:3.833524113852072e-08 tokens_per_second_per_gpu:863.7032344964815 mfu:12.691872941942675 
Step 4999 | loss:1.9861881732940674 lr:3.661263656804526e-08 tokens_per_second_per_gpu:857.305666610339 mfu:12.597862504670537 
Step 5000 | loss:1.9997456073760986 lr:3.492962254819654e-08 tokens_per_second_per_gpu:892.818595672211 mfu:13.119714878781728 
Step 5001 | loss:2.018458843231201 lr:3.328619974553027e-08 tokens_per_second_per_gpu:899.0527326045079 mfu:13.211323744752354 
Step 5002 | loss:1.9909923076629639 lr:3.168236881092579e-08 tokens_per_second_per_gpu:867.0666357452845 mfu:12.741297164983202 
Step 5003 | loss:1.98439621925354 lr:3.0118130379575005e-08 tokens_per_second_per_gpu:872.0714205011426 mfu:12.814841050991866 
Step 5004 | loss:1.9305052757263184 lr:2.8593485071004567e-08 tokens_per_second_per_gpu:888.9079000605559 mfu:13.062248321015883 
Step 5005 | loss:1.9840573072433472 lr:2.7108433489042574e-08 tokens_per_second_per_gpu:910.2842112518242 mfu:13.376367123367213 
Step 5006 | loss:1.955034852027893 lr:2.5662976221840773e-08 tokens_per_second_per_gpu:870.5027633141633 mfu:12.791790080575836 
Step 5007 | loss:1.991391897201538 lr:2.425711384188567e-08 tokens_per_second_per_gpu:870.2603983546607 mfu:12.788228596551313 
Step 5008 | loss:2.0280518531799316 lr:2.2890846905965212e-08 tokens_per_second_per_gpu:847.1040323651961 mfu:12.447952396119181 
Step 5009 | loss:1.9590355157852173 lr:2.1564175955191e-08 tokens_per_second_per_gpu:884.9335936088306 mfu:13.003847020079402 
Step 5010 | loss:1.9828861951828003 lr:2.0277101514987184e-08 tokens_per_second_per_gpu:881.125510109513 mfu:12.947888318067799 
Step 5011 | loss:2.0103278160095215 lr:1.9029624095101562e-08 tokens_per_second_per_gpu:890.3981064766512 mfu:13.084146479706206 
Step 5012 | loss:1.9826120138168335 lr:1.7821744189605582e-08 tokens_per_second_per_gpu:847.3602832963834 mfu:12.451717930541175 
Step 5013 | loss:2.0128209590911865 lr:1.6653462276872146e-08 tokens_per_second_per_gpu:885.0648638402234 mfu:13.0057759987278 
Step 5014 | loss:2.0178303718566895 lr:1.5524778819597795e-08 tokens_per_second_per_gpu:863.0030472056455 mfu:12.681583889203358 
Step 5015 | loss:1.9677495956420898 lr:1.4435694264802735e-08 tokens_per_second_per_gpu:884.6490808263428 mfu:12.999666185805001 
Step 5016 | loss:1.9880377054214478 lr:1.3386209043819708e-08 tokens_per_second_per_gpu:881.5387314683452 mfu:12.953960488199534 
Step 5017 | loss:1.9630825519561768 lr:1.2376323572305115e-08 tokens_per_second_per_gpu:861.2123212666631 mfu:12.655269681749155 
Step 5018 | loss:2.0800020694732666 lr:1.1406038250205698e-08 tokens_per_second_per_gpu:877.7701149318283 mfu:12.89858174196124 
Step 5019 | loss:1.9859404563903809 lr:1.0475353461825155e-08 tokens_per_second_per_gpu:884.903221121186 mfu:13.003400705027287 
Step 5020 | loss:1.983710765838623 lr:9.584269575746429e-09 tokens_per_second_per_gpu:879.3911709763651 mfu:12.92240269865943 
Step 5021 | loss:1.9305976629257202 lr:8.732786944887217e-09 tokens_per_second_per_gpu:855.0641027211881 mfu:12.564923361992745 
Step 5022 | loss:2.072139263153076 lr:7.920905906488863e-09 tokens_per_second_per_gpu:850.6719076474467 mfu:12.500381306821849 
Step 5023 | loss:1.9629366397857666 lr:7.148626782071955e-09 tokens_per_second_per_gpu:834.563877881071 mfu:12.263678398954363 
Step 5024 | loss:2.0033352375030518 lr:6.41594987752514e-09 tokens_per_second_per_gpu:854.889554505383 mfu:12.562358425694304 
Step 5025 | loss:1.9773470163345337 lr:5.72287548301631e-09 tokens_per_second_per_gpu:840.6681482617144 mfu:12.353378912950419 
Step 5026 | loss:1.9888814687728882 lr:5.069403873025902e-09 tokens_per_second_per_gpu:852.7500336576891 mfu:12.530918776436305 
Step 5027 | loss:1.9869904518127441 lr:4.45553530638021e-09 tokens_per_second_per_gpu:864.1275930879514 mfu:12.69810877053477 
Step 5028 | loss:2.0062718391418457 lr:3.881270026184769e-09 tokens_per_second_per_gpu:886.9834369833542 mfu:13.033968884420345 
Step 5029 | loss:1.9492871761322021 lr:3.346608259890971e-09 tokens_per_second_per_gpu:865.4627017507364 mfu:12.717727811931127 
Step 5030 | loss:1.9760193824768066 lr:2.851550219240551e-09 tokens_per_second_per_gpu:875.8432166468654 mfu:12.870266520681497 
Step 5031 | loss:1.9875032901763916 lr:2.396096100321099e-09 tokens_per_second_per_gpu:873.3072501673221 mfu:12.83300121581998 
Step 5032 | loss:1.9760127067565918 lr:1.9802460834883463e-09 tokens_per_second_per_gpu:882.0268595512083 mfu:12.961133391298253 
Step 5033 | loss:2.0183489322662354 lr:1.6040003334660825e-09 tokens_per_second_per_gpu:847.9439292096646 mfu:12.460294440942652 
Step 5034 | loss:1.950516700744629 lr:1.2673589992462376e-09 tokens_per_second_per_gpu:853.8101404469088 mfu:12.546496743655 
Step 5035 | loss:1.9770711660385132 lr:9.703222141665968e-10 tokens_per_second_per_gpu:901.8684699240764 mfu:13.252700202394871 
Step 5036 | loss:1.9309866428375244 lr:7.128900958774942e-10 tokens_per_second_per_gpu:870.3523622574742 mfu:12.789579979900521 
Step 5037 | loss:1.9802812337875366 lr:4.950627463085056e-10 tokens_per_second_per_gpu:860.0840689306239 mfu:12.638690335136186 
Step 5038 | loss:1.9409985542297363 lr:3.168402517461644e-10 tokens_per_second_per_gpu:898.5037737928626 mfu:13.20325695142626 
Step 5039 | loss:2.023380994796753 lr:1.7822268278955278e-10 tokens_per_second_per_gpu:888.7582686913961 mfu:13.06004953067951 
Step 5040 | loss:1.9932010173797607 lr:7.921009430589266e-11 tokens_per_second_per_gpu:868.7970981134167 mfu:12.766725816434242 
Step 5041 | loss:1.9672313928604126 lr:1.980252554156792e-11 tokens_per_second_per_gpu:886.4246187061347 mfu:13.025757209056827 
Step 5042 | loss:1.994719386100769 lr:0.0 tokens_per_second_per_gpu:721.5585053959696 mfu:10.603096648124236