{"step": 0, "loss": 0.6644763946533203, "lr": 1e-05, "grad_norm": 5.680084228515625, "tokens": 146, "tok_per_s": 141.46135553956987, "t": 1.49} {"step": 50, "loss": 0.35510000586509705, "lr": 0.00051, "grad_norm": 0.7261158227920532, "tokens": 8382, "tok_per_s": 209.86136561195113, "t": 40.4} {"step": 100, "loss": 0.4570963680744171, "lr": 0.001, "grad_norm": 0.24637189507484436, "tokens": 16548, "tok_per_s": 211.39769274934773, "t": 78.74} {"step": 150, "loss": 0.31619879603385925, "lr": 0.0009993400362330058, "grad_norm": 0.08306342363357544, "tokens": 24812, "tok_per_s": 213.88393776640754, "t": 116.47} {"step": 200, "loss": 0.4250110387802124, "lr": 0.0009973620807194618, "grad_norm": 0.09148009121417999, "tokens": 33400, "tok_per_s": 216.15619745557277, "t": 154.98} {"step": 250, "loss": 0.4082123935222626, "lr": 0.000994071935143687, "grad_norm": 0.1515781730413437, "tokens": 41583, "tok_per_s": 215.90921335729468, "t": 193.06} {"step": 300, "loss": 0.3465111255645752, "lr": 0.000989479250069539, "grad_norm": 0.008793611079454422, "tokens": 49989, "tok_per_s": 216.0462052223742, "t": 231.84} {"step": 350, "loss": 0.47030675411224365, "lr": 0.0009835974966336503, "grad_norm": 0.10443144291639328, "tokens": 58214, "tok_per_s": 216.1910390978099, "t": 269.73} {"step": 400, "loss": 0.4296374022960663, "lr": 0.0009764439270322612, "grad_norm": 0.052171774208545685, "tokens": 66391, "tok_per_s": 215.76153491352085, "t": 308.17} {"step": 450, "loss": 0.29752418398857117, "lr": 0.0009680395239175562, "grad_norm": 0.05620457977056503, "tokens": 74699, "tok_per_s": 215.88717470713576, "t": 346.47} {"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4614060591335306, "val_loss_b2": 0.4608306790761257, "val_loss_b4": 0.4599862782575627, "val_loss_b8": 0.45909975596165176, "t": 392.92} {"step": 500, "loss": 0.5755393505096436, "lr": 0.0009584089388519307, "grad_norm": 0.02727334573864937, "tokens": 83038, "tok_per_s": 211.1920504077883, "t": 393.65} {"step": 550, "loss": 0.4017924666404724, "lr": 0.0009475804200007103, "grad_norm": 0.004908864852041006, "tokens": 91441, "tok_per_s": 212.34346139088245, "t": 431.09} {"step": 600, "loss": 0.4867638051509857, "lr": 0.0009355857292754152, "grad_norm": 0.10723856836557388, "tokens": 99553, "tok_per_s": 212.25113424371096, "t": 469.5} {"step": 650, "loss": 0.4368710219860077, "lr": 0.0009224600491706008, "grad_norm": 0.13653473556041718, "tokens": 107666, "tok_per_s": 212.22950970710252, "t": 507.77} {"step": 700, "loss": 0.4439235031604767, "lr": 0.0009082418795675396, "grad_norm": 0.07129785418510437, "tokens": 115959, "tok_per_s": 212.57056517521025, "t": 545.97} {"step": 750, "loss": 0.4081542193889618, "lr": 0.0008929729248074364, "grad_norm": 0.06531000882387161, "tokens": 124302, "tok_per_s": 212.68022223242926, "t": 584.92} {"step": 800, "loss": 0.4864971935749054, "lr": 0.0008766979713654089, "grad_norm": 0.04692531004548073, "tokens": 132734, "tok_per_s": 213.21285974990184, "t": 623.0} {"step": 850, "loss": 0.4979650378227234, "lr": 0.0008594647564840406, "grad_norm": 0.08015435934066772, "tokens": 141025, "tok_per_s": 213.54012851058073, "t": 660.88} {"step": 900, "loss": 0.45703357458114624, "lr": 0.0008413238281518224, "grad_norm": 0.11793000251054764, "tokens": 149035, "tok_per_s": 213.53019098318674, "t": 698.42} {"step": 950, "loss": 0.4070718586444855, "lr": 0.0008223283968371944, "grad_norm": 0.10662169009447098, "tokens": 157135, "tok_per_s": 213.55339011319845, "t": 736.27} {"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4595901917917732, "val_loss_b2": 0.45844550435915554, "val_loss_b4": 0.457498853109105, "val_loss_b8": 0.4579453108756045, "t": 782.06} {"step": 1000, "loss": 0.4328213930130005, "lr": 0.000802534179413072, "grad_norm": 0.08575072139501572, "tokens": 165602, "tok_per_s": 211.6963637863752, "t": 782.72} {"step": 1050, "loss": 0.3772578835487366, "lr": 0.0007819992357296598, "grad_norm": 0.06752017140388489, "tokens": 173674, "tok_per_s": 211.54234465658703, "t": 821.45} {"step": 1100, "loss": 0.37643927335739136, "lr": 0.0007607837983149056, "grad_norm": 0.04086579382419586, "tokens": 181834, "tok_per_s": 211.65393615709414, "t": 859.57} {"step": 1150, "loss": 0.42132800817489624, "lr": 0.0007389500957021191, "grad_norm": 0.1692216843366623, "tokens": 190158, "tok_per_s": 211.90884918622064, "t": 897.82} {"step": 1200, "loss": 0.41987988352775574, "lr": 0.0007165621699029615, "grad_norm": 0.2133738398551941, "tokens": 198573, "tok_per_s": 212.09794777784748, "t": 936.69} {"step": 1250, "loss": 0.4763341248035431, "lr": 0.000693685688561191, "grad_norm": 0.1505996435880661, "tokens": 206880, "tok_per_s": 212.24676773072733, "t": 975.18} {"step": 1300, "loss": 0.3152061700820923, "lr": 0.0006703877523381495, "grad_norm": 0.1286003440618515, "tokens": 215095, "tok_per_s": 212.31254158388407, "t": 1013.57} {"step": 1350, "loss": 0.39434534311294556, "lr": 0.0006467366980949609, "grad_norm": 0.11008001118898392, "tokens": 223349, "tok_per_s": 212.4382110346171, "t": 1051.82} {"step": 1400, "loss": 0.4491351246833801, "lr": 0.0006228018984487442, "grad_norm": 0.20237210392951965, "tokens": 231716, "tok_per_s": 212.54766353509004, "t": 1090.65} {"step": 1450, "loss": 0.49844831228256226, "lr": 0.0005986535582907738, "grad_norm": 0.11668998748064041, "tokens": 239960, "tok_per_s": 212.72679147560876, "t": 1128.48} {"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45658283600259614, "val_loss_b2": 0.45435874811118904, "val_loss_b4": 0.454458028944682, "val_loss_b8": 0.4627116171816642, "t": 1173.91} {"step": 1500, "loss": 0.45087289810180664, "lr": 0.000574362508863438, "grad_norm": 0.15090641379356384, "tokens": 248357, "tok_per_s": 211.49611133523828, "t": 1174.75} {"step": 1550, "loss": 0.565893828868866, "lr": 0.00055, "grad_norm": 0.23161718249320984, "tokens": 256793, "tok_per_s": 211.83030459336086, "t": 1212.72} {"step": 1600, "loss": 0.4820862412452698, "lr": 0.0005256374911365621, "grad_norm": 0.13227154314517975, "tokens": 265023, "tok_per_s": 211.94676181016726, "t": 1250.88} {"step": 1650, "loss": 0.5263903737068176, "lr": 0.0005013464417092262, "grad_norm": 0.2619132697582245, "tokens": 273283, "tok_per_s": 212.10948456279985, "t": 1288.87} {"step": 1700, "loss": 0.475395530462265, "lr": 0.00047719810155125587, "grad_norm": 0.14985093474388123, "tokens": 281671, "tok_per_s": 212.32108070859078, "t": 1327.09} {"step": 1750, "loss": 0.41160255670547485, "lr": 0.0004532633019050392, "grad_norm": 0.16373006999492645, "tokens": 289799, "tok_per_s": 212.3303519922363, "t": 1365.31} {"step": 1800, "loss": 0.36834022402763367, "lr": 0.0004296122476618507, "grad_norm": 0.13301368057727814, "tokens": 298140, "tok_per_s": 212.49980910929432, "t": 1403.48} {"step": 1850, "loss": 0.4615144729614258, "lr": 0.00040631431143880916, "grad_norm": 0.14588533341884613, "tokens": 306518, "tok_per_s": 212.74793585293529, "t": 1441.22} {"step": 1900, "loss": 0.3502458930015564, "lr": 0.00038343783009703845, "grad_norm": 0.10745350271463394, "tokens": 314885, "tok_per_s": 212.9020996743239, "t": 1479.48} {"step": 1950, "loss": 0.3214513957500458, "lr": 0.000361049904297881, "grad_norm": 0.12961970269680023, "tokens": 322988, "tok_per_s": 212.86503738551986, "t": 1517.8} {"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45508726504472985, "val_loss_b2": 0.45239103269318515, "val_loss_b4": 0.45146719818340847, "val_loss_b8": 0.455602312158516, "t": 1564.14} {"step": 2000, "loss": 0.4833122491836548, "lr": 0.0003392162016850945, "grad_norm": 0.22385811805725098, "tokens": 331190, "tok_per_s": 211.69215280381673, "t": 1564.95} {"step": 2050, "loss": 0.4087717831134796, "lr": 0.0003180007642703402, "grad_norm": 0.22454775869846344, "tokens": 339365, "tok_per_s": 211.76487069521113, "t": 1603.02} {"step": 2100, "loss": 0.3631439208984375, "lr": 0.000297465820586928, "grad_norm": 0.14241984486579895, "tokens": 347821, "tok_per_s": 212.02027540529693, "t": 1640.97} {"step": 2150, "loss": 0.4852296710014343, "lr": 0.0002776716031628058, "grad_norm": 0.174610897898674, "tokens": 355802, "tok_per_s": 211.99723302582936, "t": 1678.8} {"step": 2200, "loss": 0.34208327531814575, "lr": 0.00025867617184817756, "grad_norm": 0.2635476291179657, "tokens": 363932, "tok_per_s": 212.0038602027029, "t": 1717.09} {"step": 2250, "loss": 0.3052659034729004, "lr": 0.00024053524351595949, "grad_norm": 0.12927033007144928, "tokens": 372235, "tok_per_s": 212.06965109356784, "t": 1755.71} {"step": 2300, "loss": 0.3800409436225891, "lr": 0.0002233020286345913, "grad_norm": 0.16911424696445465, "tokens": 380617, "tok_per_s": 212.10838747153025, "t": 1794.91} {"step": 2350, "loss": 0.352823406457901, "lr": 0.00020702707519256364, "grad_norm": 0.2780165374279022, "tokens": 388820, "tok_per_s": 212.1557830929417, "t": 1833.17} {"step": 2400, "loss": 0.3765140771865845, "lr": 0.00019175812043246033, "grad_norm": 0.3892991840839386, "tokens": 397013, "tok_per_s": 212.21076019893343, "t": 1871.3} {"step": 2450, "loss": 0.40282729268074036, "lr": 0.00017753995082939931, "grad_norm": 0.1660112589597702, "tokens": 405444, "tok_per_s": 212.3219306808007, "t": 1910.03} {"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4528964208581284, "val_loss_b2": 0.45029942233789255, "val_loss_b4": 0.4513187427248139, "val_loss_b8": 0.4594480336858111, "t": 1956.03} {"step": 2500, "loss": 0.4626985788345337, "lr": 0.00016441427072458494, "grad_norm": 0.18089695274829865, "tokens": 413920, "tok_per_s": 211.580500996187, "t": 1956.79} {"step": 2550, "loss": 0.3277227282524109, "lr": 0.0001524195799992897, "grad_norm": 0.1283731609582901, "tokens": 422230, "tok_per_s": 211.6263484947166, "t": 1995.63} {"step": 2600, "loss": 0.414442777633667, "lr": 0.0001415910611480694, "grad_norm": 0.18218661844730377, "tokens": 430404, "tok_per_s": 211.7161500907616, "t": 2033.39} {"step": 2650, "loss": 0.3827161192893982, "lr": 0.00013196047608244387, "grad_norm": 0.20599478483200073, "tokens": 438498, "tok_per_s": 211.6515476626135, "t": 2072.25} {"step": 2700, "loss": 0.34525230526924133, "lr": 0.00012355607296773896, "grad_norm": 0.26840877532958984, "tokens": 446658, "tok_per_s": 211.73083088408677, "t": 2110.02} {"step": 2750, "loss": 0.35430482029914856, "lr": 0.00011640250336634969, "grad_norm": 0.2299339473247528, "tokens": 455155, "tok_per_s": 211.84797442668358, "t": 2148.96} {"step": 2800, "loss": 0.4402179718017578, "lr": 0.00011052074993046101, "grad_norm": 0.23972682654857635, "tokens": 463083, "tok_per_s": 211.73843986510133, "t": 2187.51} {"step": 2850, "loss": 0.38545069098472595, "lr": 0.00010592806485631325, "grad_norm": 0.22342637181282043, "tokens": 471665, "tok_per_s": 211.98485423636959, "t": 2225.46} {"step": 2900, "loss": 0.43328121304512024, "lr": 0.00010263791928053818, "grad_norm": 0.2505686283111572, "tokens": 480193, "tok_per_s": 212.16858203565639, "t": 2263.72} {"step": 2950, "loss": 0.3182322680950165, "lr": 0.0001006599637669943, "grad_norm": 0.1792982816696167, "tokens": 488284, "tok_per_s": 212.09540269726858, "t": 2302.65} {"step": 2999, "loss": 0.43810218572616577, "lr": 0.0001000002640500325, "grad_norm": 0.22313541173934937, "tokens": 496298, "tok_per_s": 212.05506071039483, "t": 2340.88} {"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4521168153705475, "val_loss_b2": 0.44932703645197614, "val_loss_b4": 0.45028291235068796, "val_loss_b8": 0.4582403163242481, "t": 2349.77} {"step": 2999, "checkpoint_sha256": "a31c97935f20348d4763244744bc1606292a50f1bcd8fddfc0df68b7550c29aa", "t": 2349.8}