{"step": 1, "loss": 3.14205402135849, "grad_norm": 22.113000869750977, "lr": 7.142857142857143e-07, "s_per_step": 6.455075025558472, "peak_gb": 26.618435072, "samples_seen": 32, "time": 1791165515.6419272} {"step": 25, "loss": 1.588310784039398, "grad_norm": 3.3672797679901123, "lr": 1.785714285714286e-05, "s_per_step": 2.4963032404581704, "peak_gb": 37.31657216, "samples_seen": 800, "time": 1791165575.553675} {"step": 50, "loss": 0.7974538557231426, "grad_norm": 2.1865363121032715, "lr": 3.571428571428572e-05, "s_per_step": 2.3631107234954833, "peak_gb": 37.31657216, "samples_seen": 1600, "time": 1791165634.6318743} {"step": 75, "loss": 0.8159684363007546, "grad_norm": 1.9037853479385376, "lr": 5.3571428571428575e-05, "s_per_step": 2.239762897491455, "peak_gb": 37.31657216, "samples_seen": 2400, "time": 1791165690.6263816} {"step": 100, "loss": 0.7896525931358337, "grad_norm": 2.5986344814300537, "lr": 7.142857142857143e-05, "s_per_step": 2.3967845153808596, "peak_gb": 37.31657216, "samples_seen": 3200, "time": 1791165750.546467} {"step": 125, "loss": 0.8200986498594284, "grad_norm": 1.9665552377700806, "lr": 8.92857142857143e-05, "s_per_step": 2.33407000541687, "peak_gb": 37.31657216, "samples_seen": 4000, "time": 1791165808.8986936} {"step": 150, "loss": 0.8343269512057304, "grad_norm": 3.3930838108062744, "lr": 9.999903078446618e-05, "s_per_step": 2.1298329830169678, "peak_gb": 37.31657216, "samples_seen": 4800, "time": 1791165862.14493} {"step": 175, "loss": 0.8642021375894546, "grad_norm": 2.676706552505493, "lr": 9.99861683318768e-05, "s_per_step": 2.233229761123657, "peak_gb": 37.31657216, "samples_seen": 5600, "time": 1791165917.9761162} {"step": 200, "loss": 0.8286110037565231, "grad_norm": 2.648852586746216, "lr": 9.995835331149929e-05, "s_per_step": 2.396289863586426, "peak_gb": 37.31657216, "samples_seen": 6400, "time": 1791165977.8838441} {"step": 225, "loss": 0.9085636857151985, "grad_norm": 2.160125970840454, "lr": 9.99155940437549e-05, "s_per_step": 2.1998683071136473, "peak_gb": 37.31657216, "samples_seen": 7200, "time": 1791166032.881024} {"step": 250, "loss": 0.8117574036121369, "grad_norm": 2.7077982425689697, "lr": 9.9857903319399e-05, "s_per_step": 2.2049441051483156, "peak_gb": 37.31657216, "samples_seen": 8000, "time": 1791166088.0050786} {"step": 275, "loss": 0.7880503736436367, "grad_norm": 1.907461166381836, "lr": 9.978529839569481e-05, "s_per_step": 2.2465640830993654, "peak_gb": 37.31657216, "samples_seen": 8800, "time": 1791166144.169653} {"step": 300, "loss": 0.8249761319160461, "grad_norm": 2.7506635189056396, "lr": 9.969780099125133e-05, "s_per_step": 2.1263711261749267, "peak_gb": 37.31657216, "samples_seen": 9600, "time": 1791166197.3293953} {"step": 325, "loss": 0.8113455653190613, "grad_norm": 1.875877022743225, "lr": 9.959543727952643e-05, "s_per_step": 2.335303964614868, "peak_gb": 37.31657216, "samples_seen": 10400, "time": 1791166255.7124696} {"step": 350, "loss": 0.82724973320961, "grad_norm": 1.6174412965774536, "lr": 9.947823788099753e-05, "s_per_step": 2.136453084945679, "peak_gb": 37.31657216, "samples_seen": 11200, "time": 1791166309.1243026} {"step": 375, "loss": 0.7504141560196876, "grad_norm": 2.193037271499634, "lr": 9.934623785400195e-05, "s_per_step": 2.084479150772095, "peak_gb": 37.31657216, "samples_seen": 12000, "time": 1791166361.2366986} {"step": 400, "loss": 0.824563305824995, "grad_norm": 1.1731573343276978, "lr": 9.919947668424977e-05, "s_per_step": 2.275921335220337, "peak_gb": 37.31657216, "samples_seen": 12800, "time": 1791166418.1351547} {"step": 425, "loss": 0.8523908746242523, "grad_norm": 2.243957996368408, "lr": 9.903799827301237e-05, "s_per_step": 2.191669044494629, "peak_gb": 37.31657216, "samples_seen": 13600, "time": 1791166472.9273403} {"step": 450, "loss": 0.7732072618603706, "grad_norm": 2.2687370777130127, "lr": 9.886185092398996e-05, "s_per_step": 2.1319501781463623, "peak_gb": 37.31657216, "samples_seen": 14400, "time": 1791166526.2265835} {"step": 475, "loss": 0.8263177201151848, "grad_norm": 2.527397632598877, "lr": 9.867108732886235e-05, "s_per_step": 2.2787140560150148, "peak_gb": 37.321700352, "samples_seen": 15200, "time": 1791166583.1949017} {"step": 500, "loss": 0.756193850338459, "grad_norm": 2.1782448291778564, "lr": 9.846576455152708e-05, "s_per_step": 2.24827579498291, "peak_gb": 37.321700352, "samples_seen": 16000, "time": 1791166639.4022188} {"step": 525, "loss": 0.8762797820568085, "grad_norm": 1.765979528427124, "lr": 9.824594401102962e-05, "s_per_step": 2.4363709831237794, "peak_gb": 37.321700352, "samples_seen": 16800, "time": 1791166700.3121493} {"step": 550, "loss": 0.8164837975800038, "grad_norm": 2.792057752609253, "lr": 9.801169146319091e-05, "s_per_step": 2.295490322113037, "peak_gb": 37.325714432, "samples_seen": 17600, "time": 1791166757.6998796} {"step": 575, "loss": 0.7905827209353447, "grad_norm": 2.4493868350982666, "lr": 9.776307698093747e-05, "s_per_step": 2.152802686691284, "peak_gb": 37.325714432, "samples_seen": 18400, "time": 1791166811.5203996} {"step": 600, "loss": 0.8037899886071682, "grad_norm": 1.6931008100509644, "lr": 9.750017493334023e-05, "s_per_step": 2.2320249462127686, "peak_gb": 37.325714432, "samples_seen": 19200, "time": 1791166867.3215806} {"step": 625, "loss": 0.7798363075405359, "grad_norm": 1.994132399559021, "lr": 9.722306396336825e-05, "s_per_step": 2.337219753265381, "peak_gb": 37.325714432, "samples_seen": 20000, "time": 1791166925.7525764} {"step": 650, "loss": 0.7738844112306833, "grad_norm": 2.684321880340576, "lr": 9.693182696436385e-05, "s_per_step": 2.181212863922119, "peak_gb": 37.325714432, "samples_seen": 20800, "time": 1791166980.2833657} {"step": 675, "loss": 0.8178048168122768, "grad_norm": 2.06518816947937, "lr": 9.662655105524643e-05, "s_per_step": 2.1410923194885254, "peak_gb": 37.325714432, "samples_seen": 21600, "time": 1791167033.8111975} {"step": 700, "loss": 0.8055640901625156, "grad_norm": 1.5254127979278564, "lr": 9.630732755445221e-05, "s_per_step": 2.269847593307495, "peak_gb": 37.325714432, "samples_seen": 22400, "time": 1791167090.5579088} {"step": 725, "loss": 0.8045347545295953, "grad_norm": 3.4738898277282715, "lr": 9.597425195261783e-05, "s_per_step": 2.2504861736297608, "peak_gb": 37.325714432, "samples_seen": 23200, "time": 1791167146.8205574} {"step": 750, "loss": 0.817788716852665, "grad_norm": 1.5313327312469482, "lr": 9.562742388401568e-05, "s_per_step": 2.396076259613037, "peak_gb": 37.325714432, "samples_seen": 24000, "time": 1791167206.72293} {"step": 775, "loss": 0.7898177513480187, "grad_norm": 2.4144198894500732, "lr": 9.526694709675015e-05, "s_per_step": 2.249171714782715, "peak_gb": 37.325714432, "samples_seen": 24800, "time": 1791167262.952708} {"step": 800, "loss": 0.7381506878137588, "grad_norm": 1.8181664943695068, "lr": 9.489292942172278e-05, "s_per_step": 2.0362033462524414, "peak_gb": 37.325714432, "samples_seen": 25600, "time": 1791167313.858285} {"step": 825, "loss": 0.7578190127015114, "grad_norm": 2.2866311073303223, "lr": 9.450548274037653e-05, "s_per_step": 1.91242262840271, "peak_gb": 37.325714432, "samples_seen": 26400, "time": 1791167361.6693754} {"step": 850, "loss": 0.817485048621893, "grad_norm": 1.920059323310852, "lr": 9.41047229512281e-05, "s_per_step": 2.3170962715148926, "peak_gb": 37.325714432, "samples_seen": 27200, "time": 1791167419.59729} {"step": 875, "loss": 0.7546365970373153, "grad_norm": 1.885245442390442, "lr": 9.369076993519888e-05, "s_per_step": 2.1289653301239015, "peak_gb": 37.325714432, "samples_seen": 28000, "time": 1791167472.821967} {"step": 900, "loss": 0.7460251280665398, "grad_norm": 2.3024418354034424, "lr": 9.326374751975431e-05, "s_per_step": 2.1195631408691407, "peak_gb": 37.325714432, "samples_seen": 28800, "time": 1791167525.8115594} {"step": 925, "loss": 0.8006729355454445, "grad_norm": 3.084848642349243, "lr": 9.2823783441863e-05, "s_per_step": 2.1862466812133787, "peak_gb": 37.325714432, "samples_seen": 29600, "time": 1791167580.468191} {"step": 950, "loss": 0.7907543142139911, "grad_norm": 1.976046085357666, "lr": 9.237100930978614e-05, "s_per_step": 2.252327461242676, "peak_gb": 37.325714432, "samples_seen": 30400, "time": 1791167636.7768707} {"step": 975, "loss": 0.7727618554607034, "grad_norm": 1.6060981750488281, "lr": 9.190556056370907e-05, "s_per_step": 2.1356379699707033, "peak_gb": 37.325714432, "samples_seen": 31200, "time": 1791167690.168348} {"step": 1000, "loss": 0.7722805575281382, "grad_norm": 2.346635580062866, "lr": 9.142757643522645e-05, "s_per_step": 2.184465847015381, "peak_gb": 37.325714432, "samples_seen": 32000, "time": 1791167744.7805607} {"step": 1025, "loss": 0.790591963082552, "grad_norm": 2.7288553714752197, "lr": 9.093719990569333e-05, "s_per_step": 2.320113706588745, "peak_gb": 37.325714432, "samples_seen": 32800, "time": 1791167802.7838862} {"step": 1050, "loss": 0.8003257100284099, "grad_norm": 1.9871152639389038, "lr": 9.043457766345464e-05, "s_per_step": 2.3094374752044677, "peak_gb": 37.325714432, "samples_seen": 33600, "time": 1791167860.5202947} {"step": 1075, "loss": 0.7964102986454964, "grad_norm": 1.7926714420318604, "lr": 8.991986005996554e-05, "s_per_step": 2.170173463821411, "peak_gb": 37.325714432, "samples_seen": 34400, "time": 1791167914.7752576} {"step": 1100, "loss": 0.769957457780838, "grad_norm": 1.2739399671554565, "lr": 8.93932010648163e-05, "s_per_step": 2.0905527210235597, "peak_gb": 37.325714432, "samples_seen": 35200, "time": 1791167967.0396023} {"step": 1125, "loss": 0.7743674084544182, "grad_norm": 1.7435359954833984, "lr": 8.885475821967478e-05, "s_per_step": 2.130764627456665, "peak_gb": 37.325714432, "samples_seen": 36000, "time": 1791168020.3092685} {"step": 1150, "loss": 0.7376279538124799, "grad_norm": 2.089308261871338, "lr": 8.830469259116016e-05, "s_per_step": 2.06257776260376, "peak_gb": 37.325714432, "samples_seen": 36800, "time": 1791168071.8742328} {"step": 1175, "loss": 0.7563618395477534, "grad_norm": 2.581925630569458, "lr": 8.774316872266266e-05, "s_per_step": 2.104277467727661, "peak_gb": 37.325714432, "samples_seen": 37600, "time": 1791168124.4817083} {"step": 1200, "loss": 0.7164853295683861, "grad_norm": 1.9859364032745361, "lr": 8.717035458512277e-05, "s_per_step": 2.175741729736328, "peak_gb": 37.325714432, "samples_seen": 38400, "time": 1791168178.8757303} {"step": 1225, "loss": 0.7512343572080136, "grad_norm": 1.4672244787216187, "lr": 8.658642152678558e-05, "s_per_step": 2.196865644454956, "peak_gb": 37.325714432, "samples_seen": 39200, "time": 1791168233.7978122} {"step": 1250, "loss": 0.7883425006270408, "grad_norm": 0.9867988228797913, "lr": 8.599154422194459e-05, "s_per_step": 2.1413458442687987, "peak_gb": 37.325714432, "samples_seen": 40000, "time": 1791168287.3319008} {"step": 1275, "loss": 0.7481986878812313, "grad_norm": 1.657426118850708, "lr": 8.53859006186907e-05, "s_per_step": 2.2622928619384766, "peak_gb": 37.325714432, "samples_seen": 40800, "time": 1791168343.8896875} {"step": 1300, "loss": 0.7483823847025632, "grad_norm": 2.765939235687256, "lr": 8.476967188568188e-05, "s_per_step": 2.1760437870025635, "peak_gb": 37.325714432, "samples_seen": 41600, "time": 1791168398.291302} {"step": 1325, "loss": 0.7789613246917725, "grad_norm": 1.4214611053466797, "lr": 8.414304235794941e-05, "s_per_step": 2.260581455230713, "peak_gb": 37.325714432, "samples_seen": 42400, "time": 1791168454.8063686} {"step": 1350, "loss": 0.6945078286528588, "grad_norm": 0.8304738402366638, "lr": 8.3506199481757e-05, "s_per_step": 2.104763975143433, "peak_gb": 37.325714432, "samples_seen": 43200, "time": 1791168507.4259417} {"step": 1375, "loss": 0.7696672566235065, "grad_norm": 1.0556106567382812, "lr": 8.285933375852925e-05, "s_per_step": 2.2171495151519776, "peak_gb": 37.325714432, "samples_seen": 44000, "time": 1791168562.8552532} {"step": 1400, "loss": 0.7444813340902329, "grad_norm": 1.4957417249679565, "lr": 8.220263868786613e-05, "s_per_step": 2.1510196685791017, "peak_gb": 37.325714432, "samples_seen": 44800, "time": 1791168616.631196} {"step": 1425, "loss": 0.7628245377540588, "grad_norm": 1.9097741842269897, "lr": 8.153631070966065e-05, "s_per_step": 2.2037828826904295, "peak_gb": 37.325714432, "samples_seen": 45600, "time": 1791168671.7262833} {"step": 1450, "loss": 0.7726829506456852, "grad_norm": 4.09751558303833, "lr": 8.086054914533705e-05, "s_per_step": 2.278927917480469, "peak_gb": 37.325714432, "samples_seen": 46400, "time": 1791168728.7000833} {"step": 1475, "loss": 0.7285840643197298, "grad_norm": 2.5535264015197754, "lr": 8.017555613822691e-05, "s_per_step": 2.2388983535766602, "peak_gb": 37.325714432, "samples_seen": 47200, "time": 1791168784.6731944} {"step": 1500, "loss": 0.7646115978434682, "grad_norm": 1.643479347229004, "lr": 7.948153659310116e-05, "s_per_step": 2.2301154708862305, "peak_gb": 37.325714432, "samples_seen": 48000, "time": 1791168840.426597} {"step": 1525, "loss": 0.8089976158738136, "grad_norm": 1.9452074766159058, "lr": 7.87786981148762e-05, "s_per_step": 2.326566572189331, "peak_gb": 37.325714432, "samples_seen": 48800, "time": 1791168898.5912657} {"step": 1550, "loss": 0.7462999747693538, "grad_norm": 1.458425760269165, "lr": 7.806725094651197e-05, "s_per_step": 2.1147663688659666, "peak_gb": 37.325714432, "samples_seen": 49600, "time": 1791168951.4609642} {"step": 1575, "loss": 0.7764386893808841, "grad_norm": 1.451231837272644, "lr": 7.734740790612136e-05, "s_per_step": 2.115509796142578, "peak_gb": 37.325714432, "samples_seen": 50400, "time": 1791169004.349144} {"step": 1600, "loss": 0.7370309364795685, "grad_norm": 1.2360936403274536, "lr": 7.661938432330886e-05, "s_per_step": 2.2563931560516357, "peak_gb": 37.325714432, "samples_seen": 51200, "time": 1791169060.7593937} {"step": 1625, "loss": 0.7613919779658318, "grad_norm": 1.3745328187942505, "lr": 7.588339797475826e-05, "s_per_step": 2.2605470848083495, "peak_gb": 37.325714432, "samples_seen": 52000, "time": 1791169117.27354} {"step": 1650, "loss": 0.7241708636283875, "grad_norm": 1.1827912330627441, "lr": 7.513966901908811e-05, "s_per_step": 2.072138557434082, "peak_gb": 37.325714432, "samples_seen": 52800, "time": 1791169169.0774484} {"step": 1675, "loss": 0.8018289273977279, "grad_norm": 1.4603354930877686, "lr": 7.438841993099486e-05, "s_per_step": 2.274630489349365, "peak_gb": 37.325714432, "samples_seen": 53600, "time": 1791169225.9437313} {"step": 1700, "loss": 0.7257322013378144, "grad_norm": 1.382242202758789, "lr": 7.362987543470305e-05, "s_per_step": 2.2222759437561037, "peak_gb": 37.325714432, "samples_seen": 54400, "time": 1791169281.5011303} {"step": 1725, "loss": 0.7535443095862866, "grad_norm": 1.816344141960144, "lr": 7.286426243674262e-05, "s_per_step": 2.216677312850952, "peak_gb": 37.325714432, "samples_seen": 55200, "time": 1791169336.9185019} {"step": 1750, "loss": 0.6980357927083969, "grad_norm": 1.857561469078064, "lr": 7.209180995807341e-05, "s_per_step": 2.2018299293518067, "peak_gb": 37.325714432, "samples_seen": 56000, "time": 1791169391.9646761} {"step": 1775, "loss": 0.7253469225764274, "grad_norm": 2.774467706680298, "lr": 7.131274906557725e-05, "s_per_step": 2.397851753234863, "peak_gb": 37.325714432, "samples_seen": 56800, "time": 1791169451.9115198} {"step": 1800, "loss": 0.743451382741332, "grad_norm": 2.1614222526550293, "lr": 7.052731280293791e-05, "s_per_step": 2.1326423931121825, "peak_gb": 37.325714432, "samples_seen": 57600, "time": 1791169505.2281344} {"step": 1825, "loss": 0.7323271352052688, "grad_norm": 1.8209247589111328, "lr": 6.973573612092985e-05, "s_per_step": 2.3023265171051026, "peak_gb": 37.328663552, "samples_seen": 58400, "time": 1791169562.786706} {"step": 1850, "loss": 0.7592687951028347, "grad_norm": 1.0971518754959106, "lr": 6.893825580713633e-05, "s_per_step": 2.175807409286499, "peak_gb": 37.328663552, "samples_seen": 59200, "time": 1791169617.1823072} {"step": 1875, "loss": 0.7327933664619922, "grad_norm": 1.8120750188827515, "lr": 6.813511041511828e-05, "s_per_step": 2.188905382156372, "peak_gb": 37.328663552, "samples_seen": 60000, "time": 1791169671.9053829} {"step": 1900, "loss": 0.7617114392668008, "grad_norm": 1.5995821952819824, "lr": 6.732654019305469e-05, "s_per_step": 2.2518668460845945, "peak_gb": 37.328663552, "samples_seen": 60800, "time": 1791169728.2025328} {"step": 1925, "loss": 0.7184512709081173, "grad_norm": 3.1466126441955566, "lr": 6.651278701187629e-05, "s_per_step": 2.1966624069213867, "peak_gb": 37.328663552, "samples_seen": 61600, "time": 1791169783.119614} {"step": 1950, "loss": 0.7223995580524206, "grad_norm": 2.8622689247131348, "lr": 6.569409429291362e-05, "s_per_step": 2.0271696281433105, "peak_gb": 37.328663552, "samples_seen": 62400, "time": 1791169833.799278} {"step": 1975, "loss": 0.7936395730078221, "grad_norm": 1.976616382598877, "lr": 6.487070693508147e-05, "s_per_step": 2.2634132957458495, "peak_gb": 37.328663552, "samples_seen": 63200, "time": 1791169890.385065} {"step": 2000, "loss": 0.7677774439752102, "grad_norm": 1.5000005960464478, "lr": 6.404287124162117e-05, "s_per_step": 2.219316129684448, "peak_gb": 37.328663552, "samples_seen": 64000, "time": 1791169945.8683996} {"step": 2025, "loss": 0.8423459057509899, "grad_norm": 2.1223344802856445, "lr": 6.321083484642303e-05, "s_per_step": 2.251362638473511, "peak_gb": 37.328663552, "samples_seen": 64800, "time": 1791170002.1529393} {"step": 2050, "loss": 0.7075329820811749, "grad_norm": 2.1938531398773193, "lr": 6.237484663995047e-05, "s_per_step": 2.1452943515777587, "peak_gb": 37.328663552, "samples_seen": 65600, "time": 1791170055.7858298} {"step": 2075, "loss": 0.8434611645340919, "grad_norm": 1.8508089780807495, "lr": 6.153515669478846e-05, "s_per_step": 2.182622308731079, "peak_gb": 37.328663552, "samples_seen": 66400, "time": 1791170110.3518124} {"step": 2100, "loss": 0.7706048192456365, "grad_norm": 2.157609462738037, "lr": 6.069201619083826e-05, "s_per_step": 2.2786025047302245, "peak_gb": 37.328663552, "samples_seen": 67200, "time": 1791170167.3173573} {"step": 2125, "loss": 0.7334290408343077, "grad_norm": 1.6534168720245361, "lr": 5.984567734018094e-05, "s_per_step": 2.185659351348877, "peak_gb": 37.328663552, "samples_seen": 68000, "time": 1791170221.9593232} {"step": 2150, "loss": 0.763808610253036, "grad_norm": 2.686551809310913, "lr": 5.899639331163218e-05, "s_per_step": 2.268961925506592, "peak_gb": 37.328663552, "samples_seen": 68800, "time": 1791170278.6838627} {"step": 2175, "loss": 0.74334836833179, "grad_norm": 1.4271022081375122, "lr": 5.814441815501079e-05, "s_per_step": 2.15900297164917, "peak_gb": 37.328663552, "samples_seen": 69600, "time": 1791170332.6593788} {"step": 2200, "loss": 0.7046704458445311, "grad_norm": 1.7289416790008545, "lr": 5.729000672514379e-05, "s_per_step": 2.078843479156494, "peak_gb": 37.328663552, "samples_seen": 70400, "time": 1791170384.6309428} {"step": 2225, "loss": 0.7402220770716668, "grad_norm": 1.6976007223129272, "lr": 5.643341460563063e-05, "s_per_step": 2.128084936141968, "peak_gb": 37.328663552, "samples_seen": 71200, "time": 1791170437.8334522} {"step": 2250, "loss": 0.6715993209183216, "grad_norm": 2.1607041358947754, "lr": 5.557489803238933e-05, "s_per_step": 2.159433355331421, "peak_gb": 37.328663552, "samples_seen": 72000, "time": 1791170491.8197389} {"step": 2275, "loss": 0.6767104347795247, "grad_norm": 1.7123639583587646, "lr": 5.471471381700778e-05, "s_per_step": 2.1726886463165282, "peak_gb": 37.328663552, "samples_seen": 72800, "time": 1791170546.1373775} {"step": 2300, "loss": 0.747688923329115, "grad_norm": 2.3197970390319824, "lr": 5.385311926992242e-05, "s_per_step": 2.1769580173492433, "peak_gb": 37.328663552, "samples_seen": 73600, "time": 1791170600.5618634} {"step": 2325, "loss": 0.7415474114567041, "grad_norm": 2.262953996658325, "lr": 5.2990372123447995e-05, "s_per_step": 2.1750038051605225, "peak_gb": 37.328663552, "samples_seen": 74400, "time": 1791170654.9374063} {"step": 2350, "loss": 0.7086691360920667, "grad_norm": 2.3506317138671875, "lr": 5.212673045468114e-05, "s_per_step": 2.1435218715667723, "peak_gb": 37.328663552, "samples_seen": 75200, "time": 1791170708.5259638} {"step": 2375, "loss": 0.6722931536287069, "grad_norm": 2.5476269721984863, "lr": 5.1262452608300514e-05, "s_per_step": 2.0527558517456055, "peak_gb": 37.328663552, "samples_seen": 76000, "time": 1791170759.8453696} {"step": 2400, "loss": 0.6826995080709457, "grad_norm": 2.1311166286468506, "lr": 5.0397797119287236e-05, "s_per_step": 2.0880999755859375, "peak_gb": 37.328663552, "samples_seen": 76800, "time": 1791170812.048361} {"step": 2425, "loss": 0.7050965564697981, "grad_norm": 3.221079111099243, "lr": 4.9533022635588216e-05, "s_per_step": 2.119127044677734, "peak_gb": 37.328663552, "samples_seen": 77600, "time": 1791170865.0271327} {"step": 2450, "loss": 0.7206440759450197, "grad_norm": 2.5294783115386963, "lr": 4.8668387840745734e-05, "s_per_step": 2.2606944370269777, "peak_gb": 37.328663552, "samples_seen": 78400, "time": 1791170921.5450323} {"step": 2475, "loss": 0.6436616685986519, "grad_norm": 2.3800606727600098, "lr": 4.7804151376516375e-05, "s_per_step": 2.2651154708862307, "peak_gb": 37.328663552, "samples_seen": 79200, "time": 1791170978.1734085} {"step": 2500, "loss": 0.7039403146505356, "grad_norm": 1.7854039669036865, "lr": 4.694057176550241e-05, "s_per_step": 2.0506904697418213, "peak_gb": 37.328663552, "samples_seen": 80000, "time": 1791171029.4411094} {"step": 2525, "loss": 0.7302389190718531, "grad_norm": 2.1441829204559326, "lr": 4.607790733381898e-05, "s_per_step": 2.298251438140869, "peak_gb": 37.328663552, "samples_seen": 80800, "time": 1791171086.8978634} {"step": 2550, "loss": 0.655513388440013, "grad_norm": 2.3894569873809814, "lr": 4.521641613381981e-05, "s_per_step": 2.033922777175903, "peak_gb": 37.328663552, "samples_seen": 81600, "time": 1791171137.7463996} {"step": 2575, "loss": 0.7391077170521021, "grad_norm": 2.9977188110351562, "lr": 4.435635586690507e-05, "s_per_step": 2.149828996658325, "peak_gb": 37.328663552, "samples_seen": 82400, "time": 1791171191.4925926} {"step": 2600, "loss": 0.7200800219923258, "grad_norm": 2.7793188095092773, "lr": 4.349798380643398e-05, "s_per_step": 2.1879476928710937, "peak_gb": 37.328663552, "samples_seen": 83200, "time": 1791171246.1917589} {"step": 2625, "loss": 0.7436163403838872, "grad_norm": 1.5204609632492065, "lr": 4.264155672076572e-05, "s_per_step": 2.4061502170562745, "peak_gb": 37.328663552, "samples_seen": 84000, "time": 1791171306.346018} {"step": 2650, "loss": 0.660215564146638, "grad_norm": 1.1763237714767456, "lr": 4.178733079645106e-05, "s_per_step": 2.2049616050720213, "peak_gb": 37.328663552, "samples_seen": 84800, "time": 1791171361.4704888} {"step": 2675, "loss": 0.6927475852519274, "grad_norm": 2.5386247634887695, "lr": 4.093556156159842e-05, "s_per_step": 2.145371465682983, "peak_gb": 37.328663552, "samples_seen": 85600, "time": 1791171415.1052473} {"step": 2700, "loss": 0.7659448549896478, "grad_norm": 1.650169014930725, "lr": 4.008650380943658e-05, "s_per_step": 2.305666389465332, "peak_gb": 37.328663552, "samples_seen": 86400, "time": 1791171472.7473748} {"step": 2725, "loss": 0.6683748767152429, "grad_norm": 2.2317709922790527, "lr": 3.924041152209739e-05, "s_per_step": 2.1367229557037355, "peak_gb": 37.328663552, "samples_seen": 87200, "time": 1791171526.165955} {"step": 2750, "loss": 0.6803565273061395, "grad_norm": 2.578368902206421, "lr": 3.8397537794641006e-05, "s_per_step": 2.1723069763183593, "peak_gb": 37.328663552, "samples_seen": 88000, "time": 1791171580.4741504} {"step": 2775, "loss": 0.6919519574567675, "grad_norm": 2.4252359867095947, "lr": 3.755813475934657e-05, "s_per_step": 2.2460842609405516, "peak_gb": 37.328663552, "samples_seen": 88800, "time": 1791171636.626775} {"step": 2800, "loss": 0.7549696940928697, "grad_norm": 1.3772821426391602, "lr": 3.672245351029079e-05, "s_per_step": 2.140784168243408, "peak_gb": 37.328663552, "samples_seen": 89600, "time": 1791171690.1468506} {"step": 2825, "loss": 0.6725568605586887, "grad_norm": 2.269684314727783, "lr": 3.5890744028237224e-05, "s_per_step": 2.1861842250823975, "peak_gb": 37.328663552, "samples_seen": 90400, "time": 1791171744.8019009} {"step": 2850, "loss": 0.7570831072703004, "grad_norm": 1.3243885040283203, "lr": 3.506325510585843e-05, "s_per_step": 2.1999145126342774, "peak_gb": 37.328663552, "samples_seen": 91200, "time": 1791171799.8001847} {"step": 2875, "loss": 0.7394591322168708, "grad_norm": 0.9553370475769043, "lr": 3.424023427331364e-05, "s_per_step": 2.3712642765045167, "peak_gb": 37.328663552, "samples_seen": 92000, "time": 1791171859.0828495} {"step": 2900, "loss": 0.6674072152376175, "grad_norm": 1.9110374450683594, "lr": 3.342192772420396e-05, "s_per_step": 1.943366403579712, "peak_gb": 37.328663552, "samples_seen": 92800, "time": 1791171907.6675425} {"step": 2925, "loss": 0.728705649226904, "grad_norm": 1.81485116481781, "lr": 3.260858024192766e-05, "s_per_step": 2.3112503147125243, "peak_gb": 37.328663552, "samples_seen": 93600, "time": 1791171965.4493177} {"step": 2950, "loss": 0.6727638635039329, "grad_norm": 1.9227899312973022, "lr": 3.180043512645685e-05, "s_per_step": 2.1781687355041504, "peak_gb": 37.328663552, "samples_seen": 94400, "time": 1791172019.9040134} {"step": 2975, "loss": 0.7250781350582838, "grad_norm": 1.9956176280975342, "lr": 3.099773412155837e-05, "s_per_step": 2.1951618003845215, "peak_gb": 37.328663552, "samples_seen": 95200, "time": 1791172074.7835524} {"step": 3000, "loss": 0.650225435718894, "grad_norm": 1.4397475719451904, "lr": 3.0200717342479927e-05, "s_per_step": 2.1171874523162844, "peak_gb": 37.328663552, "samples_seen": 96000, "time": 1791172127.713813} {"step": 3025, "loss": 0.6574885688722134, "grad_norm": 2.6953608989715576, "lr": 2.9409623204123326e-05, "s_per_step": 2.1706494808197023, "peak_gb": 37.328663552, "samples_seen": 96800, "time": 1791172181.9805422} {"step": 3050, "loss": 0.7310007732175291, "grad_norm": 2.1912403106689453, "lr": 2.8624688349726657e-05, "s_per_step": 2.2939053535461427, "peak_gb": 37.328663552, "samples_seen": 97600, "time": 1791172239.3286743} {"step": 3075, "loss": 0.6456812293455004, "grad_norm": 1.7668237686157227, "lr": 2.7846147580076e-05, "s_per_step": 2.030617341995239, "peak_gb": 37.328663552, "samples_seen": 98400, "time": 1791172290.0945995} {"step": 3100, "loss": 0.7004510406404734, "grad_norm": 0.9194343090057373, "lr": 2.7074233783268676e-05, "s_per_step": 2.0785311794281007, "peak_gb": 37.328663552, "samples_seen": 99200, "time": 1791172342.0582764} {"step": 3125, "loss": 0.7067461168020963, "grad_norm": 0.9615018367767334, "lr": 2.630917786504836e-05, "s_per_step": 2.172322187423706, "peak_gb": 37.328663552, "samples_seen": 100000, "time": 1791172396.3667948} {"step": 3150, "loss": 0.6149680116400122, "grad_norm": 1.5655421018600464, "lr": 2.5551208679733385e-05, "s_per_step": 2.068291358947754, "peak_gb": 37.328663552, "samples_seen": 100800, "time": 1791172448.0745811} {"step": 3175, "loss": 0.7133472035825252, "grad_norm": 2.5095202922821045, "lr": 2.4800552961758572e-05, "s_per_step": 2.2229059314727784, "peak_gb": 37.328663552, "samples_seen": 101600, "time": 1791172503.6477566} {"step": 3200, "loss": 0.7128471711371094, "grad_norm": 5.073495388031006, "lr": 2.4057435257851175e-05, "s_per_step": 2.1217748641967775, "peak_gb": 37.328663552, "samples_seen": 102400, "time": 1791172556.6926906} {"step": 3225, "loss": 0.681353373080492, "grad_norm": 0.7074483633041382, "lr": 2.3322077859861412e-05, "s_per_step": 2.2286937618255616, "peak_gb": 37.328663552, "samples_seen": 103200, "time": 1791172612.4104753} {"step": 3250, "loss": 0.6933992094546556, "grad_norm": 1.5983896255493164, "lr": 2.2594700738267265e-05, "s_per_step": 2.2323473739624022, "peak_gb": 37.328663552, "samples_seen": 104000, "time": 1791172668.2196336} {"step": 3275, "loss": 0.6521770719438791, "grad_norm": 1.4988881349563599, "lr": 2.1875521476373913e-05, "s_per_step": 2.350031909942627, "peak_gb": 37.328663552, "samples_seen": 104800, "time": 1791172726.9709315} {"step": 3300, "loss": 0.6772003842145204, "grad_norm": 1.3674873113632202, "lr": 2.11647552052271e-05, "s_per_step": 2.1167491817474366, "peak_gb": 37.328663552, "samples_seen": 105600, "time": 1791172779.890159} {"step": 3325, "loss": 0.6974349667225033, "grad_norm": 1.8985122442245483, "lr": 2.046261453926006e-05, "s_per_step": 2.188663167953491, "peak_gb": 37.328663552, "samples_seen": 106400, "time": 1791172834.6072176} {"step": 3350, "loss": 0.6722285900078714, "grad_norm": 3.2266275882720947, "lr": 1.9769309512693395e-05, "s_per_step": 2.0479675102233887, "peak_gb": 37.328663552, "samples_seen": 107200, "time": 1791172885.8069012} {"step": 3375, "loss": 0.6281475232355297, "grad_norm": 3.8666343688964844, "lr": 1.9085047516706533e-05, "s_per_step": 2.2480383014678953, "peak_gb": 37.328663552, "samples_seen": 108000, "time": 1791172942.0083659} {"step": 3400, "loss": 0.6186308555305005, "grad_norm": 1.4103232622146606, "lr": 1.8410033237400098e-05, "s_per_step": 2.2519297409057617, "peak_gb": 37.328663552, "samples_seen": 108800, "time": 1791172998.3070562} {"step": 3425, "loss": 0.6535533627495169, "grad_norm": 1.9440644979476929, "lr": 1.7744468594567244e-05, "s_per_step": 2.151489324569702, "peak_gb": 37.328663552, "samples_seen": 109600, "time": 1791173052.0947604} {"step": 3450, "loss": 0.6736921292543411, "grad_norm": 4.172308921813965, "lr": 1.7088552681292513e-05, "s_per_step": 2.1378032398223876, "peak_gb": 37.328663552, "samples_seen": 110400, "time": 1791173105.5402908} {"step": 3475, "loss": 0.7076615856215358, "grad_norm": 2.3574821949005127, "lr": 1.6442481704396416e-05, "s_per_step": 2.167111291885376, "peak_gb": 37.328663552, "samples_seen": 111200, "time": 1791173159.7185235} {"step": 3500, "loss": 0.754842204619199, "grad_norm": 1.3139305114746094, "lr": 1.5806448925743172e-05, "s_per_step": 2.2147708892822267, "peak_gb": 37.328663552, "samples_seen": 112000, "time": 1791173215.0882668} {"step": 3525, "loss": 0.6143901840061881, "grad_norm": 1.189170002937317, "lr": 1.5180644604429567e-05, "s_per_step": 2.2504481792449953, "peak_gb": 37.328663552, "samples_seen": 112800, "time": 1791173271.3500268} {"step": 3550, "loss": 0.7468885008245707, "grad_norm": 1.0117112398147583, "lr": 1.456525593987194e-05, "s_per_step": 2.2883919048309327, "peak_gb": 37.328663552, "samples_seen": 113600, "time": 1791173328.5602643} {"step": 3575, "loss": 0.6123304791096598, "grad_norm": 1.6147323846817017, "lr": 1.3960467015808465e-05, "s_per_step": 2.1810163593292238, "peak_gb": 37.328663552, "samples_seen": 114400, "time": 1791173383.0861204} {"step": 3600, "loss": 0.6615970143675804, "grad_norm": 2.9963948726654053, "lr": 1.3366458745233385e-05, "s_per_step": 2.190250720977783, "peak_gb": 37.328663552, "samples_seen": 115200, "time": 1791173437.8429022} {"step": 3625, "loss": 0.6804951827973127, "grad_norm": 1.5510998964309692, "lr": 1.2783408816279802e-05, "s_per_step": 2.1283248138427733, "peak_gb": 37.328663552, "samples_seen": 116000, "time": 1791173491.051459} {"step": 3650, "loss": 0.6892811707407236, "grad_norm": 1.4326013326644897, "lr": 1.2211491639067125e-05, "s_per_step": 2.369460802078247, "peak_gb": 37.328663552, "samples_seen": 116800, "time": 1791173550.289685} {"step": 3675, "loss": 0.6716245946101844, "grad_norm": 2.649146795272827, "lr": 1.1650878293528994e-05, "s_per_step": 2.1898504161834715, "peak_gb": 37.328663552, "samples_seen": 117600, "time": 1791173605.0363798} {"step": 3700, "loss": 0.6472007501125335, "grad_norm": 2.400968074798584, "lr": 1.110173647823749e-05, "s_per_step": 2.089416027069092, "peak_gb": 37.328663552, "samples_seen": 118400, "time": 1791173657.2722385} {"step": 3725, "loss": 0.6779031552001834, "grad_norm": 1.842848300933838, "lr": 1.0564230460238694e-05, "s_per_step": 2.1233923053741455, "peak_gb": 37.328663552, "samples_seen": 119200, "time": 1791173710.357557} {"step": 3750, "loss": 0.6172893346473575, "grad_norm": 3.009672164916992, "lr": 1.0038521025914932e-05, "s_per_step": 2.111167163848877, "peak_gb": 37.328663552, "samples_seen": 120000, "time": 1791173763.137248} {"step": 3775, "loss": 0.6523078301548958, "grad_norm": 0.9374409317970276, "lr": 9.524765432887944e-06, "s_per_step": 2.3036874389648436, "peak_gb": 37.328663552, "samples_seen": 120800, "time": 1791173820.7299206} {"step": 3800, "loss": 0.6383235438168049, "grad_norm": 1.7281076908111572, "lr": 9.02311736297789e-06, "s_per_step": 2.1478301906585693, "peak_gb": 37.328663552, "samples_seen": 121600, "time": 1791173874.4261167} {"step": 3825, "loss": 0.6730420371307991, "grad_norm": 1.6016979217529297, "lr": 8.533726876231828e-06, "s_per_step": 2.2305167865753175, "peak_gb": 37.328663552, "samples_seen": 122400, "time": 1791173930.1895103} {"step": 3850, "loss": 0.6855003063753248, "grad_norm": 1.8208370208740234, "lr": 8.056740366035576e-06, "s_per_step": 2.341342372894287, "peak_gb": 37.328663552, "samples_seen": 123200, "time": 1791173988.7235923} {"step": 3875, "loss": 0.6778232954442501, "grad_norm": 1.5814423561096191, "lr": 7.592300515322576e-06, "s_per_step": 2.280441083908081, "peak_gb": 37.328663552, "samples_seen": 124000, "time": 1791174045.7350547} {"step": 3900, "loss": 0.7005690622329712, "grad_norm": 1.7448139190673828, "lr": 7.140546253892439e-06, "s_per_step": 2.2497168445587157, "peak_gb": 37.328663552, "samples_seen": 124800, "time": 1791174101.9784636} {"step": 3925, "loss": 0.680451717376709, "grad_norm": 3.5512075424194336, "lr": 6.70161271685244e-06, "s_per_step": 2.2352783203125, "peak_gb": 37.328663552, "samples_seen": 125600, "time": 1791174157.8608978} {"step": 3950, "loss": 0.6795122207701206, "grad_norm": 3.0180165767669678, "lr": 6.27563120419386e-06, "s_per_step": 2.179275674819946, "peak_gb": 37.328663552, "samples_seen": 126400, "time": 1791174212.3432853} {"step": 3975, "loss": 0.6303972934558988, "grad_norm": 1.2422635555267334, "lr": 5.8627291415157435e-06, "s_per_step": 2.078404426574707, "peak_gb": 37.328663552, "samples_seen": 127200, "time": 1791174264.3039021} {"step": 4000, "loss": 0.6791560095734894, "grad_norm": 1.8804198503494263, "lr": 5.463030041907597e-06, "s_per_step": 2.176313486099243, "peak_gb": 37.328663552, "samples_seen": 128000, "time": 1791174318.7121499} {"step": 4025, "loss": 0.6513661769777537, "grad_norm": 2.495976448059082, "lr": 5.076653469002313e-06, "s_per_step": 2.1938330554962158, "peak_gb": 37.328663552, "samples_seen": 128800, "time": 1791174373.5584402} {"step": 4050, "loss": 0.6535539354383946, "grad_norm": 1.9437261819839478, "lr": 4.70371500121074e-06, "s_per_step": 2.1953781414031983, "peak_gb": 37.328663552, "samples_seen": 129600, "time": 1791174428.4433782} {"step": 4075, "loss": 0.7009203843027353, "grad_norm": 1.0737240314483643, "lr": 4.344326197148107e-06, "s_per_step": 2.248444013595581, "peak_gb": 37.328663552, "samples_seen": 130400, "time": 1791174484.654927} {"step": 4100, "loss": 0.64098393403925, "grad_norm": 1.6634223461151123, "lr": 3.9985945622630915e-06, "s_per_step": 2.09239275932312, "peak_gb": 37.328663552, "samples_seen": 131200, "time": 1791174536.9651742} {"step": 4125, "loss": 0.7195338121801614, "grad_norm": 1.6115185022354126, "lr": 3.6666235166793127e-06, "s_per_step": 2.3179955768585203, "peak_gb": 37.328663552, "samples_seen": 132000, "time": 1791174594.9155335} {"step": 4150, "loss": 0.6215781589318067, "grad_norm": 1.4749220609664917, "lr": 3.3485123642587658e-06, "s_per_step": 2.1519798469543456, "peak_gb": 37.328663552, "samples_seen": 132800, "time": 1791174648.7154896} {"step": 4175, "loss": 0.6063127079233527, "grad_norm": 2.4063498973846436, "lr": 3.0443562628967415e-06, "s_per_step": 2.164182243347168, "peak_gb": 37.328663552, "samples_seen": 133600, "time": 1791174702.8204815} {"step": 4200, "loss": 0.6975668650865555, "grad_norm": 1.5435162782669067, "lr": 2.754246196056759e-06, "s_per_step": 2.2063780212402344, "peak_gb": 37.328663552, "samples_seen": 134400, "time": 1791174757.9804275} {"step": 4225, "loss": 0.6374323242623359, "grad_norm": 1.643761396408081, "lr": 2.4782689455543796e-06, "s_per_step": 2.173592166900635, "peak_gb": 37.328663552, "samples_seen": 135200, "time": 1791174812.3206897} {"step": 4250, "loss": 0.6485517076496035, "grad_norm": 2.015836238861084, "lr": 2.2165070655977727e-06, "s_per_step": 2.0835715389251708, "peak_gb": 37.328663552, "samples_seen": 136000, "time": 1791174864.4104404} {"step": 4275, "loss": 0.6164555564941838, "grad_norm": 1.3733229637145996, "lr": 1.9690388580929363e-06, "s_per_step": 2.3116278553009035, "peak_gb": 37.328663552, "samples_seen": 136800, "time": 1791174922.2016754} {"step": 4300, "loss": 0.6570157048292458, "grad_norm": 1.1992275714874268, "lr": 1.7359383492209613e-06, "s_per_step": 2.2723003482818602, "peak_gb": 37.328663552, "samples_seen": 137600, "time": 1791174979.0097623} {"step": 4325, "loss": 0.6460098330676556, "grad_norm": 1.471946358680725, "lr": 1.5172752672942159e-06, "s_per_step": 2.1469297885894774, "peak_gb": 37.328663552, "samples_seen": 138400, "time": 1791175032.6836147} {"step": 4350, "loss": 0.6363432590290904, "grad_norm": 1.199631690979004, "lr": 1.3131150218982923e-06, "s_per_step": 2.2307802295684813, "peak_gb": 37.328663552, "samples_seen": 139200, "time": 1791175088.4536717} {"step": 4375, "loss": 0.6324924950860441, "grad_norm": 1.9240083694458008, "lr": 1.123518684325714e-06, "s_per_step": 2.1913782024383544, "peak_gb": 37.328663552, "samples_seen": 140000, "time": 1791175143.2387235} {"step": 4400, "loss": 0.6856773376883939, "grad_norm": 2.5178141593933105, "lr": 9.485429693074754e-07, "s_per_step": 2.324142723083496, "peak_gb": 37.328663552, "samples_seen": 140800, "time": 1791175201.3428428} {"step": 4425, "loss": 0.6213866775110364, "grad_norm": 0.6766404509544373, "lr": 7.882402180477033e-07, "s_per_step": 2.1214879989624023, "peak_gb": 37.328663552, "samples_seen": 141600, "time": 1791175254.3807} {"step": 4450, "loss": 0.7287836332805455, "grad_norm": 0.6748529672622681, "lr": 6.426583825666133e-07, "s_per_step": 2.485296297073364, "peak_gb": 37.328663552, "samples_seen": 142400, "time": 1791175316.5137088} {"step": 4475, "loss": 0.6739577786624431, "grad_norm": 1.455942153930664, "lr": 5.118410113564565e-07, "s_per_step": 2.2427228450775147, "peak_gb": 37.328663552, "samples_seen": 143200, "time": 1791175372.5823774} {"step": 4500, "loss": 0.5849272518604994, "grad_norm": 1.208377718925476, "lr": 3.9582723635464004e-07, "s_per_step": 2.0806651401519773, "peak_gb": 37.328663552, "samples_seen": 144000, "time": 1791175424.5995016} {"step": 4525, "loss": 0.6931665486842394, "grad_norm": 2.3075685501098633, "lr": 2.9465176123806284e-07, "s_per_step": 2.244974718093872, "peak_gb": 37.328663552, "samples_seen": 144800, "time": 1791175480.7244606} {"step": 4550, "loss": 0.675754471779801, "grad_norm": 1.8862049579620361, "lr": 2.083448510420527e-07, "s_per_step": 2.2479200553894043, "peak_gb": 37.328663552, "samples_seen": 145600, "time": 1791175536.9230142} {"step": 4575, "loss": 0.6882729256153106, "grad_norm": 1.836661458015442, "lr": 1.3693232310705295e-07, "s_per_step": 2.2444938945770265, "peak_gb": 37.328663552, "samples_seen": 146400, "time": 1791175593.0358894} {"step": 4600, "loss": 0.6727710048668086, "grad_norm": 2.4301044940948486, "lr": 8.043553935577208e-08, "s_per_step": 2.264568119049072, "peak_gb": 37.328663552, "samples_seen": 147200, "time": 1791175649.6505373} {"step": 4625, "loss": 0.6940591262280941, "grad_norm": 1.7329171895980835, "lr": 3.8871399903134265e-08, "s_per_step": 2.141450147628784, "peak_gb": 37.328663552, "samples_seen": 148000, "time": 1791175703.1872365} {"step": 4650, "loss": 0.6567035659402609, "grad_norm": 1.8683308362960815, "lr": 1.2252338000839914e-08, "s_per_step": 2.156028919219971, "peak_gb": 37.328663552, "samples_seen": 148800, "time": 1791175757.0884378} {"step": 4675, "loss": 0.6862510319799184, "grad_norm": 2.6522982120513916, "lr": 5.863163181796249e-10, "s_per_step": 2.03354868888855, "peak_gb": 37.328663552, "samples_seen": 149600, "time": 1791175807.9276795} {"step": 4681, "loss": 0.5528123727999628, "grad_norm": 2.920032024383545, "lr": 1.1965662055635207e-11, "s_per_step": 1.9081807533899944, "peak_gb": 37.328663552, "samples_seen": 149792, "time": 1791175819.3772266}