{"step": 0, "loss": 0.41289830207824707, "lr": 1e-05, "grad_norm": 0.19947576522827148, "tokens": 157, "tok_per_s": 103.98306598785344, "t": 2.09} {"step": 50, "loss": 0.38818633556365967, "lr": 0.00051, "grad_norm": 0.12373296916484833, "tokens": 8616, "tok_per_s": 210.50877483594448, "t": 41.51} {"step": 100, "loss": 0.40296533703804016, "lr": 0.001, "grad_norm": 0.10322540253400803, "tokens": 16635, "tok_per_s": 207.34427215615867, "t": 80.81} {"step": 150, "loss": 0.5339024066925049, "lr": 0.0009993400362330058, "grad_norm": 0.04654471576213837, "tokens": 25042, "tok_per_s": 210.48447697193697, "t": 119.55} {"step": 200, "loss": 0.4560130834579468, "lr": 0.0009973620807194618, "grad_norm": 0.05597564950585365, "tokens": 33661, "tok_per_s": 213.79851018681325, "t": 158.02} {"step": 250, "loss": 0.43810510635375977, "lr": 0.000994071935143687, "grad_norm": 0.08368786424398422, "tokens": 42410, "tok_per_s": 216.42884760342238, "t": 196.53} {"step": 300, "loss": 0.39362531900405884, "lr": 0.000989479250069539, "grad_norm": 0.07594774663448334, "tokens": 50771, "tok_per_s": 216.42588239331687, "t": 235.17} {"step": 350, "loss": 0.4323241114616394, "lr": 0.0009835974966336503, "grad_norm": 0.38913479447364807, "tokens": 59133, "tok_per_s": 216.67913069323032, "t": 273.48} {"step": 400, "loss": 0.5905739068984985, "lr": 0.0009764439270322612, "grad_norm": 0.07163003832101822, "tokens": 67299, "tok_per_s": 215.99829129373754, "t": 312.15} {"step": 450, "loss": 0.46402379870414734, "lr": 0.0009680395239175562, "grad_norm": 0.02075173147022724, "tokens": 75575, "tok_per_s": 215.50317368831892, "t": 351.27} {"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4599296049040018, "val_loss_b2": 0.459329121920086, "val_loss_b4": 0.45875651687163327, "val_loss_b8": 0.45905304613108705, "t": 400.69} {"step": 500, "loss": 0.4088743329048157, "lr": 0.0009584089388519307, "grad_norm": 0.07065055519342422, "tokens": 84036, "tok_per_s": 209.60270815006396, "t": 401.51} {"step": 550, "loss": 0.2894475758075714, "lr": 0.0009475804200007103, "grad_norm": 0.1305769383907318, "tokens": 92359, "tok_per_s": 209.82826323986959, "t": 440.74} {"step": 600, "loss": 0.31267547607421875, "lr": 0.0009355857292754152, "grad_norm": 0.037300556898117065, "tokens": 100627, "tok_per_s": 209.99614181083223, "t": 479.76} {"step": 650, "loss": 0.5138199329376221, "lr": 0.0009224600491706008, "grad_norm": 0.05305271968245506, "tokens": 108981, "tok_per_s": 210.34535545351588, "t": 518.69} {"step": 700, "loss": 0.3874957263469696, "lr": 0.0009082418795675396, "grad_norm": 0.06754928827285767, "tokens": 117352, "tok_per_s": 211.07379998945905, "t": 556.55} {"step": 750, "loss": 0.5038999915122986, "lr": 0.0008929729248074364, "grad_norm": 0.06872856616973877, "tokens": 125499, "tok_per_s": 211.08505274721273, "t": 595.13} {"step": 800, "loss": 0.3794027268886566, "lr": 0.0008766979713654089, "grad_norm": 0.06263452023267746, "tokens": 133880, "tok_per_s": 211.32467965074878, "t": 634.11} {"step": 850, "loss": 0.47108355164527893, "lr": 0.0008594647564840406, "grad_norm": 0.09413265436887741, "tokens": 142063, "tok_per_s": 211.29734867103713, "t": 672.92} {"step": 900, "loss": 0.3490629196166992, "lr": 0.0008413238281518224, "grad_norm": 0.06246592476963997, "tokens": 150436, "tok_per_s": 211.45278787108913, "t": 712.02} {"step": 950, "loss": 0.40948736667633057, "lr": 0.0008223283968371944, "grad_norm": 0.10729923099279404, "tokens": 158527, "tok_per_s": 211.3841915804981, "t": 750.53} {"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4589796729014976, "val_loss_b2": 0.4571161359445751, "val_loss_b4": 0.45688086651181165, "val_loss_b8": 0.4644446112123718, "t": 799.53} {"step": 1000, "loss": 0.39746469259262085, "lr": 0.000802534179413072, "grad_norm": 0.08773847669363022, "tokens": 166917, "tok_per_s": 208.70119180642672, "t": 800.37} {"step": 1050, "loss": 0.44673895835876465, "lr": 0.0007819992357296598, "grad_norm": 0.09891089051961899, "tokens": 175091, "tok_per_s": 208.71522044260522, "t": 839.48} {"step": 1100, "loss": 0.35710445046424866, "lr": 0.0007607837983149056, "grad_norm": 0.10515832155942917, "tokens": 183159, "tok_per_s": 208.60137045464964, "t": 878.61} {"step": 1150, "loss": 0.2942264676094055, "lr": 0.0007389500957021191, "grad_norm": 0.09344721585512161, "tokens": 191581, "tok_per_s": 208.93283078990837, "t": 917.53} {"step": 1200, "loss": 0.5104178786277771, "lr": 0.0007165621699029615, "grad_norm": 0.11859089136123657, "tokens": 200185, "tok_per_s": 209.32541174037874, "t": 956.91} {"step": 1250, "loss": 0.5970321893692017, "lr": 0.000693685688561191, "grad_norm": 0.11485891789197922, "tokens": 208401, "tok_per_s": 209.27875190991335, "t": 996.38} {"step": 1300, "loss": 0.4301040768623352, "lr": 0.0006703877523381495, "grad_norm": 0.11925120651721954, "tokens": 216624, "tok_per_s": 209.34368777183772, "t": 1035.35} {"step": 1350, "loss": 0.529863715171814, "lr": 0.0006467366980949609, "grad_norm": 0.14746329188346863, "tokens": 225093, "tok_per_s": 209.72430945508543, "t": 1073.86} {"step": 1400, "loss": 0.39886265993118286, "lr": 0.0006228018984487442, "grad_norm": 0.129085972905159, "tokens": 233304, "tok_per_s": 209.80397186226116, "t": 1112.59} {"step": 1450, "loss": 0.4157991409301758, "lr": 0.0005986535582907738, "grad_norm": 0.2618933320045471, "tokens": 241497, "tok_per_s": 209.92406282482975, "t": 1150.98} {"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45837607179268525, "val_loss_b2": 0.45549386495907007, "val_loss_b4": 0.45259049774215043, "val_loss_b8": 0.45275256879344955, "t": 1199.35} {"step": 1500, "loss": 0.44786298274993896, "lr": 0.000574362508863438, "grad_norm": 0.09288837760686874, "tokens": 249582, "tok_per_s": 208.0652361415438, "t": 1200.11} {"step": 1550, "loss": 0.3230152428150177, "lr": 0.00055, "grad_norm": 0.07352703809738159, "tokens": 257750, "tok_per_s": 208.13389756541514, "t": 1238.96} {"step": 1600, "loss": 0.4365949332714081, "lr": 0.0005256374911365621, "grad_norm": 0.1760379672050476, "tokens": 266068, "tok_per_s": 208.31106972512077, "t": 1277.85} {"step": 1650, "loss": 0.4660661518573761, "lr": 0.0005013464417092262, "grad_norm": 0.19410660862922668, "tokens": 274463, "tok_per_s": 208.33783586385576, "t": 1317.97} {"step": 1700, "loss": 0.31113412976264954, "lr": 0.00047719810155125587, "grad_norm": 0.11362376809120178, "tokens": 282527, "tok_per_s": 208.34637368300113, "t": 1356.62} {"step": 1750, "loss": 0.4590863883495331, "lr": 0.0004532633019050392, "grad_norm": 0.14404942095279694, "tokens": 290793, "tok_per_s": 208.36739970902372, "t": 1396.16} {"step": 1800, "loss": 0.4144552946090698, "lr": 0.0004296122476618507, "grad_norm": 0.09978672862052917, "tokens": 299230, "tok_per_s": 208.6164584628805, "t": 1434.93} {"step": 1850, "loss": 0.3896350562572479, "lr": 0.00040631431143880916, "grad_norm": 0.1311625987291336, "tokens": 307566, "tok_per_s": 208.8799724454702, "t": 1473.03} {"step": 1900, "loss": 0.3976743221282959, "lr": 0.00038343783009703845, "grad_norm": 0.12976668775081635, "tokens": 315780, "tok_per_s": 208.85684960660643, "t": 1512.52} {"step": 1950, "loss": 0.41538894176483154, "lr": 0.000361049904297881, "grad_norm": 0.11471240222454071, "tokens": 324229, "tok_per_s": 208.94571576611787, "t": 1552.32} {"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45595270122078735, "val_loss_b2": 0.4533633612364369, "val_loss_b4": 0.4510320106006244, "val_loss_b8": 0.4581389260327305, "t": 1600.87} {"step": 2000, "loss": 0.4623417556285858, "lr": 0.0003392162016850945, "grad_norm": 0.13485188782215118, "tokens": 332550, "tok_per_s": 207.69639782085156, "t": 1601.71} {"step": 2050, "loss": 0.5143191814422607, "lr": 0.0003180007642703402, "grad_norm": 0.1475761979818344, "tokens": 340880, "tok_per_s": 208.52352609741254, "t": 1635.31} {"step": 2100, "loss": 0.31296083331108093, "lr": 0.000297465820586928, "grad_norm": 0.19896818697452545, "tokens": 349421, "tok_per_s": 209.7169249290748, "t": 1666.73} {"step": 2150, "loss": 0.4111775755882263, "lr": 0.0002776716031628058, "grad_norm": 0.1659286767244339, "tokens": 357735, "tok_per_s": 210.59695896190357, "t": 1699.25} {"step": 2200, "loss": 0.4609731137752533, "lr": 0.00025867617184817756, "grad_norm": 0.16592730581760406, "tokens": 366168, "tok_per_s": 211.53052773606458, "t": 1731.62} {"step": 2250, "loss": 0.37529799342155457, "lr": 0.00024053524351595949, "grad_norm": 0.1267513930797577, "tokens": 374489, "tok_per_s": 212.41580916607825, "t": 1763.58} {"step": 2300, "loss": 0.3170437514781952, "lr": 0.0002233020286345913, "grad_norm": 0.09567230939865112, "tokens": 382832, "tok_per_s": 213.2854288634787, "t": 1795.51} {"step": 2350, "loss": 0.5384082198143005, "lr": 0.00020702707519256364, "grad_norm": 0.13156796991825104, "tokens": 391097, "tok_per_s": 214.06841281592753, "t": 1827.55} {"step": 2400, "loss": 0.27971306443214417, "lr": 0.00019175812043246033, "grad_norm": 0.17224574089050293, "tokens": 399648, "tok_per_s": 214.9981639312062, "t": 1859.43} {"step": 2450, "loss": 0.3607747256755829, "lr": 0.00017753995082939931, "grad_norm": 0.11695021390914917, "tokens": 407914, "tok_per_s": 215.6760700376368, "t": 1891.9} {"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45440590070232845, "val_loss_b2": 0.45106324637212325, "val_loss_b4": 0.4471693607666858, "val_loss_b8": 0.45074574943832013, "t": 1931.46} {"step": 2500, "loss": 0.25153791904449463, "lr": 0.00016441427072458494, "grad_norm": 0.12982884049415588, "tokens": 416524, "tok_per_s": 215.64210841889684, "t": 1932.13} {"step": 2550, "loss": 0.3206387758255005, "lr": 0.0001524195799992897, "grad_norm": 0.08452094346284866, "tokens": 424563, "tok_per_s": 216.21832596732958, "t": 1964.16} {"step": 2600, "loss": 0.2879783511161804, "lr": 0.0001415910611480694, "grad_norm": 0.159508615732193, "tokens": 432991, "tok_per_s": 217.005241712018, "t": 1995.88} {"step": 2650, "loss": 0.39170753955841064, "lr": 0.00013196047608244387, "grad_norm": 0.16003650426864624, "tokens": 441165, "tok_per_s": 217.5838003058662, "t": 2028.14} {"step": 2700, "loss": 0.3488978147506714, "lr": 0.00012355607296773896, "grad_norm": 0.066033273935318, "tokens": 449578, "tok_per_s": 218.28637737387328, "t": 2060.16} {"step": 2750, "loss": 0.3758210241794586, "lr": 0.00011640250336634969, "grad_norm": 0.19757522642612457, "tokens": 457759, "tok_per_s": 218.9065109648847, "t": 2091.69} {"step": 2800, "loss": 0.3674268126487732, "lr": 0.00011052074993046101, "grad_norm": 0.10825106501579285, "tokens": 465905, "tok_per_s": 219.54103300193725, "t": 2122.76} {"step": 2850, "loss": 0.4037761688232422, "lr": 0.00010592806485631325, "grad_norm": 0.21395525336265564, "tokens": 474059, "tok_per_s": 220.25687313316106, "t": 2152.88} {"step": 2900, "loss": 0.5387614369392395, "lr": 0.00010263791928053818, "grad_norm": 0.11183827370405197, "tokens": 482466, "tok_per_s": 221.07856595930105, "t": 2182.91} {"step": 2950, "loss": 0.3719007968902588, "lr": 0.0001006599637669943, "grad_norm": 0.21202754974365234, "tokens": 490971, "tok_per_s": 221.90540782470214, "t": 2213.1} {"step": 2999, "loss": 0.3620559573173523, "lr": 0.0001000002640500325, "grad_norm": 0.18273140490055084, "tokens": 499017, "tok_per_s": 222.55213214208075, "t": 2242.82} {"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45272684731819524, "val_loss_b2": 0.44940244863631396, "val_loss_b4": 0.44720984562798166, "val_loss_b8": 0.45561350525864946, "t": 2250.53} {"step": 2999, "checkpoint_sha256": "7f296e6183179b136531dcc61a7a332ccacdbcc5c97fcaa53ee84e11defa252d", "t": 2250.67}