{"step": 0, "loss": 0.44351446628570557, "lr": 1e-05, "grad_norm": 0.1947793960571289, "tokens": 146, "tok_per_s": 207.96353454379974, "t": 1.39} {"step": 50, "loss": 0.330070436000824, "lr": 0.00051, "grad_norm": 0.11418312788009644, "tokens": 8382, "tok_per_s": 142.33347790030396, "t": 59.58} {"step": 100, "loss": 0.45317208766937256, "lr": 0.001, "grad_norm": 0.09766116738319397, "tokens": 16548, "tok_per_s": 138.63185250616817, "t": 120.07} {"step": 150, "loss": 0.3137042820453644, "lr": 0.0009993400362330058, "grad_norm": 0.07278697937726974, "tokens": 24812, "tok_per_s": 137.91380736535748, "t": 180.6} {"step": 200, "loss": 0.42561978101730347, "lr": 0.0009973620807194618, "grad_norm": 0.07418062537908554, "tokens": 33400, "tok_per_s": 139.56259108196085, "t": 240.02} {"step": 250, "loss": 0.4048921465873718, "lr": 0.000994071935143687, "grad_norm": 0.11941985785961151, "tokens": 41583, "tok_per_s": 138.69695686530457, "t": 300.51} {"step": 300, "loss": 0.34847313165664673, "lr": 0.000989479250069539, "grad_norm": 0.05667081102728844, "tokens": 49989, "tok_per_s": 138.2921495208583, "t": 362.18} {"step": 350, "loss": 0.45757293701171875, "lr": 0.0009835974966336503, "grad_norm": 0.10435967147350311, "tokens": 58214, "tok_per_s": 137.521112596292, "t": 424.01} {"step": 400, "loss": 0.41054046154022217, "lr": 0.0009764439270322612, "grad_norm": 0.11928416043519974, "tokens": 66391, "tok_per_s": 136.96283576870843, "t": 485.43} {"step": 450, "loss": 0.298988401889801, "lr": 0.0009680395239175562, "grad_norm": 0.03191227838397026, "tokens": 74699, "tok_per_s": 137.03700252404883, "t": 545.81} {"step": 499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.460529974142632, "val_loss_b2": 0.45888712842103707, "val_loss_b4": 0.45692866021274287, "val_loss_b8": 0.4558107207830814, "t": 620.68} {"step": 500, "loss": 0.5794364809989929, "lr": 0.0009584089388519307, "grad_norm": 0.052696529775857925, "tokens": 83038, "tok_per_s": 133.66519926380704, "t": 621.93} {"step": 550, "loss": 0.3943813145160675, "lr": 0.0009475804200007103, "grad_norm": 0.036708977073431015, "tokens": 91441, "tok_per_s": 134.06986578016725, "t": 682.73} {"step": 600, "loss": 0.4744678735733032, "lr": 0.0009355857292754152, "grad_norm": 0.09452898055315018, "tokens": 99553, "tok_per_s": 134.3747243048147, "t": 741.56} {"step": 650, "loss": 0.41545602679252625, "lr": 0.0009224600491706008, "grad_norm": 0.17442570626735687, "tokens": 107666, "tok_per_s": 135.2310807736479, "t": 796.86} {"step": 700, "loss": 0.4370920956134796, "lr": 0.0009082418795675396, "grad_norm": 0.07144679129123688, "tokens": 115959, "tok_per_s": 136.11728558284474, "t": 852.62} {"step": 750, "loss": 0.4014780521392822, "lr": 0.0008929729248074364, "grad_norm": 0.08195694535970688, "tokens": 124302, "tok_per_s": 136.77512368625912, "t": 909.5} {"step": 800, "loss": 0.4891710877418518, "lr": 0.0008766979713654089, "grad_norm": 0.09693891555070877, "tokens": 132734, "tok_per_s": 140.07179485560997, "t": 948.3} {"step": 850, "loss": 0.49942106008529663, "lr": 0.0008594647564840406, "grad_norm": 0.06404875218868256, "tokens": 141025, "tok_per_s": 143.31703115046477, "t": 984.7} {"step": 900, "loss": 0.4629952609539032, "lr": 0.0008413238281518224, "grad_norm": 0.1538352072238922, "tokens": 149035, "tok_per_s": 146.1458498640726, "t": 1020.47} {"step": 950, "loss": 0.4050980806350708, "lr": 0.0008223283968371944, "grad_norm": 0.08137238025665283, "tokens": 157135, "tok_per_s": 149.31219145743253, "t": 1053.08} {"step": 999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.457395156890433, "val_loss_b2": 0.45449976030390155, "val_loss_b4": 0.4514617919921875, "val_loss_b8": 0.45137302366720156, "t": 1084.71} {"step": 1000, "loss": 0.4228428304195404, "lr": 0.000802534179413072, "grad_norm": 0.10694779455661774, "tokens": 165602, "tok_per_s": 152.69321146308198, "t": 1085.23} {"step": 1050, "loss": 0.3771308958530426, "lr": 0.0007819992357296598, "grad_norm": 0.10716952383518219, "tokens": 173674, "tok_per_s": 155.90404578200764, "t": 1114.67} {"step": 1100, "loss": 0.37311506271362305, "lr": 0.0007607837983149056, "grad_norm": 0.042935341596603394, "tokens": 181834, "tok_per_s": 159.3325308554698, "t": 1141.91} {"step": 1150, "loss": 0.4193495512008667, "lr": 0.0007389500957021191, "grad_norm": 0.07456079125404358, "tokens": 190158, "tok_per_s": 162.8401082498871, "t": 1168.45} {"step": 1200, "loss": 0.3960014283657074, "lr": 0.0007165621699029615, "grad_norm": 0.0967603474855423, "tokens": 198573, "tok_per_s": 166.22311887568608, "t": 1195.31} {"step": 1250, "loss": 0.4707754850387573, "lr": 0.000693685688561191, "grad_norm": 0.0919080600142479, "tokens": 206880, "tok_per_s": 169.39705354820487, "t": 1221.96} {"step": 1300, "loss": 0.31079643964767456, "lr": 0.0006703877523381495, "grad_norm": 0.14708662033081055, "tokens": 215095, "tok_per_s": 172.36805353002407, "t": 1248.57} {"step": 1350, "loss": 0.4025787115097046, "lr": 0.0006467366980949609, "grad_norm": 0.12627997994422913, "tokens": 223349, "tok_per_s": 175.2527589970368, "t": 1275.13} {"step": 1400, "loss": 0.4380834102630615, "lr": 0.0006228018984487442, "grad_norm": 0.09957712143659592, "tokens": 231716, "tok_per_s": 178.0608917265224, "t": 1302.02} {"step": 1450, "loss": 0.5104676485061646, "lr": 0.0005986535582907738, "grad_norm": 0.14716589450836182, "tokens": 239960, "tok_per_s": 180.74074319898767, "t": 1328.34} {"step": 1499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.45723540116672506, "val_loss_b2": 0.45459638927416474, "val_loss_b4": 0.45460108855253606, "val_loss_b8": 0.4637742406808431, "t": 1356.88} {"step": 1500, "loss": 0.43768787384033203, "lr": 0.000574362508863438, "grad_norm": 0.10279540717601776, "tokens": 248357, "tok_per_s": 183.0519502344204, "t": 1357.45} {"step": 1550, "loss": 0.5726707577705383, "lr": 0.00055, "grad_norm": 0.30702072381973267, "tokens": 256793, "tok_per_s": 185.65716894362282, "t": 1383.85} {"step": 1600, "loss": 0.4804554581642151, "lr": 0.0005256374911365621, "grad_norm": 0.12820062041282654, "tokens": 265023, "tok_per_s": 188.00911646818113, "t": 1410.32} {"step": 1650, "loss": 0.5249490141868591, "lr": 0.0005013464417092262, "grad_norm": 0.2085103988647461, "tokens": 273283, "tok_per_s": 190.30819445141864, "t": 1436.69} {"step": 1700, "loss": 0.4736141562461853, "lr": 0.00047719810155125587, "grad_norm": 0.23362912237644196, "tokens": 281671, "tok_per_s": 192.59669082106024, "t": 1463.18} {"step": 1750, "loss": 0.4066462516784668, "lr": 0.0004532633019050392, "grad_norm": 0.07103698700666428, "tokens": 289799, "tok_per_s": 194.6200517985393, "t": 1489.74} {"step": 1800, "loss": 0.3650647699832916, "lr": 0.0004296122476618507, "grad_norm": 0.10220512002706528, "tokens": 298140, "tok_per_s": 196.723828626759, "t": 1516.22} {"step": 1850, "loss": 0.4692266881465912, "lr": 0.00040631431143880916, "grad_norm": 0.13829396665096283, "tokens": 306518, "tok_per_s": 198.80955586773788, "t": 1542.46} {"step": 1900, "loss": 0.34885820746421814, "lr": 0.00038343783009703845, "grad_norm": 0.10494671761989594, "tokens": 314885, "tok_per_s": 200.78090710333277, "t": 1568.99} {"step": 1950, "loss": 0.3201918303966522, "lr": 0.000361049904297881, "grad_norm": 0.11540502309799194, "tokens": 322988, "tok_per_s": 202.5182046316439, "t": 1595.55} {"step": 1999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.45547910533320324, "val_loss_b2": 0.45226012408997757, "val_loss_b4": 0.45134724108910784, "val_loss_b8": 0.45782278934213666, "t": 1624.5} {"step": 2000, "loss": 0.48728716373443604, "lr": 0.0003392162016850945, "grad_norm": 0.1404743492603302, "tokens": 331190, "tok_per_s": 203.8874672373223, "t": 1625.07} {"step": 2050, "loss": 0.39781516790390015, "lr": 0.0003180007642703402, "grad_norm": 0.1462763249874115, "tokens": 339365, "tok_per_s": 205.5735552594785, "t": 1651.51} {"step": 2100, "loss": 0.35300207138061523, "lr": 0.000297465820586928, "grad_norm": 0.14225618541240692, "tokens": 347821, "tok_per_s": 207.38744754608223, "t": 1677.85} {"step": 2150, "loss": 0.48658332228660583, "lr": 0.0002776716031628058, "grad_norm": 0.09956580400466919, "tokens": 355802, "tok_per_s": 208.87035021779732, "t": 1704.15} {"step": 2200, "loss": 0.33726561069488525, "lr": 0.00025867617184817756, "grad_norm": 0.1209631860256195, "tokens": 363932, "tok_per_s": 210.3634572140177, "t": 1730.71} {"step": 2250, "loss": 0.2975793480873108, "lr": 0.00024053524351595949, "grad_norm": 0.0979456827044487, "tokens": 372235, "tok_per_s": 211.88890217928684, "t": 1757.44} {"step": 2300, "loss": 0.3735887110233307, "lr": 0.0002233020286345913, "grad_norm": 0.1212862879037857, "tokens": 380617, "tok_per_s": 213.37337132401115, "t": 1784.5} {"step": 2350, "loss": 0.35255488753318787, "lr": 0.00020702707519256364, "grad_norm": 0.18635345995426178, "tokens": 388820, "tok_per_s": 214.7755041548517, "t": 1811.05} {"step": 2400, "loss": 0.36102214455604553, "lr": 0.00019175812043246033, "grad_norm": 0.23337861895561218, "tokens": 397013, "tok_per_s": 216.13858238104135, "t": 1837.53} {"step": 2450, "loss": 0.40519991517066956, "lr": 0.00017753995082939931, "grad_norm": 0.17053379118442535, "tokens": 405444, "tok_per_s": 217.55464616573175, "t": 1864.33} {"step": 2499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4524969727961285, "val_loss_b2": 0.4488434300392117, "val_loss_b4": 0.4486513744145558, "val_loss_b8": 0.4592763234265865, "t": 1893.13} {"step": 2500, "loss": 0.47165316343307495, "lr": 0.00016441427072458494, "grad_norm": 0.21392056345939636, "tokens": 413920, "tok_per_s": 218.66279980651166, "t": 1893.65} {"step": 2550, "loss": 0.3332514464855194, "lr": 0.0001524195799992897, "grad_norm": 0.14337772130966187, "tokens": 422230, "tok_per_s": 219.93237902721214, "t": 1920.51} {"step": 2600, "loss": 0.40951499342918396, "lr": 0.0001415910611480694, "grad_norm": 0.14815109968185425, "tokens": 430404, "tok_per_s": 221.16569107878897, "t": 1946.76} {"step": 2650, "loss": 0.38410139083862305, "lr": 0.00013196047608244387, "grad_norm": 0.1480327844619751, "tokens": 438498, "tok_per_s": 222.25542060800845, "t": 1973.64} {"step": 2700, "loss": 0.33331114053726196, "lr": 0.00012355607296773896, "grad_norm": 0.13606895506381989, "tokens": 446658, "tok_per_s": 223.42105169733355, "t": 1999.87} {"step": 2750, "loss": 0.3506133556365967, "lr": 0.00011640250336634969, "grad_norm": 0.12089331448078156, "tokens": 455155, "tok_per_s": 224.64921135609262, "t": 2026.76} {"step": 2800, "loss": 0.4300166964530945, "lr": 0.00011052074993046101, "grad_norm": 0.21027590334415436, "tokens": 463083, "tok_per_s": 225.58926671890882, "t": 2053.46} {"step": 2850, "loss": 0.37648335099220276, "lr": 0.00010592806485631325, "grad_norm": 0.16461865603923798, "tokens": 471665, "tok_per_s": 226.85787473467119, "t": 2079.81} {"step": 2900, "loss": 0.4316491186618805, "lr": 0.00010263791928053818, "grad_norm": 0.16477756202220917, "tokens": 480193, "tok_per_s": 228.04873862953426, "t": 2106.35} {"step": 2950, "loss": 0.32055434584617615, "lr": 0.0001006599637669943, "grad_norm": 0.18149171769618988, "tokens": 488284, "tok_per_s": 228.96673797319664, "t": 2133.24} {"step": 2999, "loss": 0.4402756989002228, "lr": 0.0001000002640500325, "grad_norm": 0.173695370554924, "tokens": 496298, "tok_per_s": 229.87381599356277, "t": 2159.69} {"step": 2999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4520384241877782, "val_loss_b2": 0.44838604990515935, "val_loss_b4": 0.44821149131357524, "val_loss_b8": 0.4584367309314621, "t": 2162.68} {"step": 2999, "checkpoint_sha256": "63501504cc2f44e41c51c3c2ec941160a997e2e5035167f0cf79e8de7dc00d37", "t": 2162.73}