1{"step": 0, "loss": 0.44773048162460327, "lr": 1e-05, "grad_norm": 0.556153416633606, "tokens": 146, "tok_per_s": 292.95913764910637, "t": 1.2}2{"step": 50, "loss": 0.3442081809043884, "lr": 0.00051, "grad_norm": 0.37501290440559387, "tokens": 8382, "tok_per_s": 307.6260095999469, "t": 27.95}3{"step": 100, "loss": 0.45778656005859375, "lr": 0.001, "grad_norm": 0.20229488611221313, "tokens": 16548, "tok_per_s": 288.2230416995394, "t": 58.11}4{"step": 150, "loss": 0.31547975540161133, "lr": 0.0009993400362330058, "grad_norm": 0.057490646839141846, "tokens": 24812, "tok_per_s": 281.8762758384119, "t": 88.72}5{"step": 200, "loss": 0.4259350895881653, "lr": 0.0009973620807194618, "grad_norm": 0.08439421653747559, "tokens": 33400, "tok_per_s": 284.2302435068223, "t": 118.21}6{"step": 250, "loss": 0.4069521129131317, "lr": 0.000994071935143687, "grad_norm": 0.11257767677307129, "tokens": 41583, "tok_per_s": 282.7224436599868, "t": 147.78}7{"step": 300, "loss": 0.3478735387325287, "lr": 0.000989479250069539, "grad_norm": 0.03762270510196686, "tokens": 49989, "tok_per_s": 281.44794099184975, "t": 178.31}8{"step": 350, "loss": 0.45913589000701904, "lr": 0.0009835974966336503, "grad_norm": 0.12336331605911255, "tokens": 58214, "tok_per_s": 280.5834353970054, "t": 208.17}9{"step": 400, "loss": 0.41509032249450684, "lr": 0.0009764439270322612, "grad_norm": 0.07938103377819061, "tokens": 66391, "tok_per_s": 279.2323732206186, "t": 238.47}10{"step": 450, "loss": 0.2963618040084839, "lr": 0.0009680395239175562, "grad_norm": 0.0717848539352417, "tokens": 74699, "tok_per_s": 278.92400552570416, "t": 268.51}11{"step": 499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4616704163379773, "val_loss_b2": 0.46116865392151934, "val_loss_b4": 0.46059843658402144, "val_loss_b8": 0.4601182086882537, "t": 308.96}12{"step": 500, "loss": 0.5758373737335205, "lr": 0.0009584089388519307, "grad_norm": 0.019091954454779625, "tokens": 83038, "tok_per_s": 268.87598847066096, "t": 309.55}13{"step": 550, "loss": 0.4014790654182434, "lr": 0.0009475804200007103, "grad_norm": 0.020043687894940376, "tokens": 91441, "tok_per_s": 271.22329708386246, "t": 337.84}14{"step": 600, "loss": 0.47882869839668274, "lr": 0.0009355857292754152, "grad_norm": 0.06984268128871918, "tokens": 99553, "tok_per_s": 271.1012220025717, "t": 367.92}15{"step": 650, "loss": 0.41903796792030334, "lr": 0.0009224600491706008, "grad_norm": 0.22036805748939514, "tokens": 107666, "tok_per_s": 271.2711839929967, "t": 397.6}16{"step": 700, "loss": 0.4381459653377533, "lr": 0.0009082418795675396, "grad_norm": 0.052618008106946945, "tokens": 115959, "tok_per_s": 271.7214706630748, "t": 427.46}17{"step": 750, "loss": 0.39676451683044434, "lr": 0.0008929729248074364, "grad_norm": 0.0739816278219223, "tokens": 124302, "tok_per_s": 272.69122780391064, "t": 456.53}18{"step": 800, "loss": 0.4894811809062958, "lr": 0.0008766979713654089, "grad_norm": 0.07216119021177292, "tokens": 132734, "tok_per_s": 272.4872088444889, "t": 487.82}19{"step": 850, "loss": 0.5084261894226074, "lr": 0.0008594647564840406, "grad_norm": 0.17283685505390167, "tokens": 141025, "tok_per_s": 272.3845292387025, "t": 518.44}20{"step": 900, "loss": 0.4598939120769501, "lr": 0.0008413238281518224, "grad_norm": 0.162124902009964, "tokens": 149035, "tok_per_s": 272.21858604989944, "t": 548.19}21{"step": 950, "loss": 0.41153138875961304, "lr": 0.0008223283968371944, "grad_norm": 0.08009892702102661, "tokens": 157135, "tok_per_s": 273.393863670134, "t": 575.45}22{"step": 999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.45901697571492656, "val_loss_b2": 0.4572813580222997, "val_loss_b4": 0.45551483733363785, "val_loss_b8": 0.4563300714168483, "t": 613.41}23{"step": 1000, "loss": 0.42753419280052185, "lr": 0.000802534179413072, "grad_norm": 0.1001649722456932, "tokens": 165602, "tok_per_s": 270.0630397464728, "t": 613.9}24{"step": 1050, "loss": 0.37226128578186035, "lr": 0.0007819992357296598, "grad_norm": 0.12398815900087357, "tokens": 173674, "tok_per_s": 269.84787699767276, "t": 644.3}25{"step": 1100, "loss": 0.37368571758270264, "lr": 0.0007607837983149056, "grad_norm": 0.0695347860455513, "tokens": 181834, "tok_per_s": 270.5419575223212, "t": 672.82}26{"step": 1150, "loss": 0.41539129614830017, "lr": 0.0007389500957021191, "grad_norm": 0.08863841742277145, "tokens": 190158, "tok_per_s": 270.57599971464253, "t": 703.49}27{"step": 1200, "loss": 0.40873774886131287, "lr": 0.0007165621699029615, "grad_norm": 0.10569734126329422, "tokens": 198573, "tok_per_s": 270.87731594221987, "t": 733.77}28{"step": 1250, "loss": 0.46784427762031555, "lr": 0.000693685688561191, "grad_norm": 0.11283445358276367, "tokens": 206880, "tok_per_s": 271.07628350194585, "t": 763.88}29{"step": 1300, "loss": 0.31833675503730774, "lr": 0.0006703877523381495, "grad_norm": 0.13993313908576965, "tokens": 215095, "tok_per_s": 271.2641422539619, "t": 793.65}30{"step": 1350, "loss": 0.4010394215583801, "lr": 0.0006467366980949609, "grad_norm": 0.14154480397701263, "tokens": 223349, "tok_per_s": 271.20186132712917, "t": 824.27}31{"step": 1400, "loss": 0.4472590684890747, "lr": 0.0006228018984487442, "grad_norm": 0.17007577419281006, "tokens": 231716, "tok_per_s": 271.3738946486929, "t": 854.56}32{"step": 1450, "loss": 0.5020751357078552, "lr": 0.0005986535582907738, "grad_norm": 0.12949620187282562, "tokens": 239960, "tok_per_s": 271.9305433088727, "t": 883.13}33{"step": 1499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4575820403947449, "val_loss_b2": 0.4551739192114727, "val_loss_b4": 0.45350260144680693, "val_loss_b8": 0.4574959389736877, "t": 921.7}34{"step": 1500, "loss": 0.4547266364097595, "lr": 0.000574362508863438, "grad_norm": 0.14190539717674255, "tokens": 248357, "tok_per_s": 269.4567379287904, "t": 922.4}35{"step": 1550, "loss": 0.5722952485084534, "lr": 0.00055, "grad_norm": 0.21111628413200378, "tokens": 256793, "tok_per_s": 269.57119689433034, "t": 953.3}36{"step": 1600, "loss": 0.4862877130508423, "lr": 0.0005256374911365621, "grad_norm": 0.17942653596401215, "tokens": 265023, "tok_per_s": 270.31872542517766, "t": 981.13}37{"step": 1650, "loss": 0.5156634449958801, "lr": 0.0005013464417092262, "grad_norm": 0.3467433750629425, "tokens": 273283, "tok_per_s": 270.67460624304096, "t": 1010.34}38{"step": 1700, "loss": 0.4826456606388092, "lr": 0.00047719810155125587, "grad_norm": 0.16352055966854095, "tokens": 281671, "tok_per_s": 270.97740402342833, "t": 1040.17}39{"step": 1750, "loss": 0.4109691083431244, "lr": 0.0004532633019050392, "grad_norm": 0.15157116949558258, "tokens": 289799, "tok_per_s": 270.85974879807617, "t": 1070.62}40{"step": 1800, "loss": 0.35956501960754395, "lr": 0.0004296122476618507, "grad_norm": 0.10558658093214035, "tokens": 298140, "tok_per_s": 271.0341557028636, "t": 1100.71}41{"step": 1850, "loss": 0.46247488260269165, "lr": 0.00040631431143880916, "grad_norm": 0.16278192400932312, "tokens": 306518, "tok_per_s": 271.9107306136422, "t": 1127.98}42{"step": 1900, "loss": 0.3558866083621979, "lr": 0.00038343783009703845, "grad_norm": 0.14660103619098663, "tokens": 314885, "tok_per_s": 272.1750561104217, "t": 1157.63}43{"step": 1950, "loss": 0.3170148432254791, "lr": 0.000361049904297881, "grad_norm": 0.16254906356334686, "tokens": 322988, "tok_per_s": 272.070882694565, "t": 1187.84}44{"step": 1999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4556608138970403, "val_loss_b2": 0.45254165307238164, "val_loss_b4": 0.4505236340368129, "val_loss_b8": 0.4535448037679117, "t": 1225.81}45{"step": 2000, "loss": 0.4811217188835144, "lr": 0.0003392162016850945, "grad_norm": 0.17925773561000824, "tokens": 331190, "tok_per_s": 270.2204635161159, "t": 1226.33}46{"step": 2050, "loss": 0.40519949793815613, "lr": 0.0003180007642703402, "grad_norm": 0.18191149830818176, "tokens": 339365, "tok_per_s": 270.13895368591096, "t": 1256.96}47{"step": 2100, "loss": 0.35611963272094727, "lr": 0.000297465820586928, "grad_norm": 0.18636132776737213, "tokens": 347821, "tok_per_s": 270.2457919723909, "t": 1287.75}48{"step": 2150, "loss": 0.4867813289165497, "lr": 0.0002776716031628058, "grad_norm": 0.1425459384918213, "tokens": 355802, "tok_per_s": 270.52649013522006, "t": 1315.92}49{"step": 2200, "loss": 0.343868613243103, "lr": 0.00025867617184817756, "grad_norm": 0.18803671002388, "tokens": 363932, "tok_per_s": 270.8194181721469, "t": 1344.52}50{"step": 2250, "loss": 0.2998804748058319, "lr": 0.00024053524351595949, "grad_norm": 0.11654919385910034, "tokens": 372235, "tok_per_s": 270.8395676294311, "t": 1375.08}51{"step": 2300, "loss": 0.3792121410369873, "lr": 0.0002233020286345913, "grad_norm": 0.12893208861351013, "tokens": 380617, "tok_per_s": 270.95953211522976, "t": 1405.4}52{"step": 2350, "loss": 0.3563537299633026, "lr": 0.00020702707519256364, "grad_norm": 0.16867871582508087, "tokens": 388820, "tok_per_s": 270.8099031898963, "t": 1436.48}53{"step": 2400, "loss": 0.36468949913978577, "lr": 0.00019175812043246033, "grad_norm": 0.36536863446235657, "tokens": 397013, "tok_per_s": 270.84830160665524, "t": 1466.51}54{"step": 2450, "loss": 0.405938059091568, "lr": 0.00017753995082939931, "grad_norm": 0.22472795844078064, "tokens": 405444, "tok_per_s": 271.1740019579975, "t": 1495.84}55{"step": 2499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4543059279966848, "val_loss_b2": 0.4520588193755246, "val_loss_b4": 0.4533251240195871, "val_loss_b8": 0.46210163975655005, "t": 1535.85}56{"step": 2500, "loss": 0.4719253480434418, "lr": 0.00016441427072458494, "grad_norm": 0.19475767016410828, "tokens": 413920, "tok_per_s": 269.5231647286812, "t": 1536.45}57{"step": 2550, "loss": 0.3289445638656616, "lr": 0.0001524195799992897, "grad_norm": 0.14256161451339722, "tokens": 422230, "tok_per_s": 269.71534122511554, "t": 1566.16}58{"step": 2600, "loss": 0.4111308157444, "lr": 0.0001415910611480694, "grad_norm": 0.1471184492111206, "tokens": 430404, "tok_per_s": 269.86916876315263, "t": 1595.56}59{"step": 2650, "loss": 0.38169416785240173, "lr": 0.00013196047608244387, "grad_norm": 0.18448062241077423, "tokens": 438498, "tok_per_s": 269.9677879484833, "t": 1624.97}60{"step": 2700, "loss": 0.34222716093063354, "lr": 0.00012355607296773896, "grad_norm": 0.23438702523708344, "tokens": 446658, "tok_per_s": 270.39960498407885, "t": 1652.54}61{"step": 2750, "loss": 0.35380586981773376, "lr": 0.00011640250336634969, "grad_norm": 0.22147689759731293, "tokens": 455155, "tok_per_s": 270.93550934897615, "t": 1680.64}62{"step": 2800, "loss": 0.4269869327545166, "lr": 0.00011052074993046101, "grad_norm": 0.21119914948940277, "tokens": 463083, "tok_per_s": 270.7836484065161, "t": 1710.86}63{"step": 2850, "loss": 0.38265764713287354, "lr": 0.00010592806485631325, "grad_norm": 0.19624683260917664, "tokens": 471665, "tok_per_s": 271.1092725440419, "t": 1740.46}64{"step": 2900, "loss": 0.42009401321411133, "lr": 0.00010263791928053818, "grad_norm": 0.20755545794963837, "tokens": 480193, "tok_per_s": 271.5355787012204, "t": 1769.13}65{"step": 2950, "loss": 0.3174911439418793, "lr": 0.0001006599637669943, "grad_norm": 0.20931555330753326, "tokens": 488284, "tok_per_s": 271.5518620579893, "t": 1798.83}66{"step": 2999, "loss": 0.448149710893631, "lr": 0.0001000002640500325, "grad_norm": 0.2065098136663437, "tokens": 496298, "tok_per_s": 271.46892202681545, "t": 1828.89}67{"step": 2999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.45304519311144414, "val_loss_b2": 0.4499895801798001, "val_loss_b4": 0.45009866002864474, "val_loss_b8": 0.4581950372401689, "t": 1838.78}68{"step": 2999, "checkpoint_sha256": "d404e47b38d702b141ee92bd1d6909aa954fbb2c4a1c831bf1adb2bfde86a6fd", "t": 1839.11}69