1{"step": 0, "loss": 0.2580532431602478, "lr": 1e-05, "grad_norm": 0.23523882031440735, "tokens": 146, "tok_per_s": 612.4290144724328, "t": 0.68}2{"step": 50, "loss": 0.2984015941619873, "lr": 0.00051, "grad_norm": 0.15599730610847473, "tokens": 8382, "tok_per_s": 728.1660891908106, "t": 11.95}3{"step": 100, "loss": 0.2955377399921417, "lr": 0.001, "grad_norm": 0.09142272919416428, "tokens": 16548, "tok_per_s": 728.537435719802, "t": 23.16}4{"step": 150, "loss": 0.2785259485244751, "lr": 0.0009984630218530014, "grad_norm": 0.04951321333646774, "tokens": 24812, "tok_per_s": 734.603057487999, "t": 34.22}5{"step": 200, "loss": 0.29046913981437683, "lr": 0.0009938625865312252, "grad_norm": 0.0388338677585125, "tokens": 33400, "tok_per_s": 741.6563361894432, "t": 45.48}6{"step": 250, "loss": 0.26837068796157837, "lr": 0.0009862301196726987, "grad_norm": 0.027337750419974327, "tokens": 41583, "tok_per_s": 739.9594056582931, "t": 56.64}7{"step": 300, "loss": 0.2509698271751404, "lr": 0.0009756177587652855, "grad_norm": 0.023025518283247948, "tokens": 49989, "tok_per_s": 740.2985167140023, "t": 67.97}8{"step": 350, "loss": 0.38487178087234497, "lr": 0.0009620979969947759, "grad_norm": 0.1557064801454544, "tokens": 58214, "tok_per_s": 740.3920662747522, "t": 79.07}9{"step": 400, "loss": 0.28965502977371216, "lr": 0.0009457631880429201, "grad_norm": 0.02757183648645878, "tokens": 66391, "tok_per_s": 738.8809295625225, "t": 90.3}10{"step": 450, "loss": 0.20280273258686066, "lr": 0.0009267249152181378, "grad_norm": 0.07334977388381958, "tokens": 74699, "tok_per_s": 739.2581441097116, "t": 101.49}11{"step": 499, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.4129690521716363, "val_loss_b2": 0.4127616287163427, "val_loss_b4": 0.4151448494966459, "val_loss_b8": 0.4207350474410036, "t": 114.16}12{"step": 500, "loss": 0.3544820547103882, "lr": 0.0009051132292283771, "grad_norm": 0.07510331273078918, "tokens": 83038, "tok_per_s": 728.8281414661615, "t": 114.38}13{"step": 550, "loss": 0.30062878131866455, "lr": 0.0008810757598029093, "grad_norm": 0.10836857557296753, "tokens": 91441, "tok_per_s": 731.9181828850625, "t": 125.38}14{"step": 600, "loss": 0.36118224263191223, "lr": 0.0008547767072315835, "grad_norm": 0.07137104123830795, "tokens": 99553, "tok_per_s": 731.0711095658081, "t": 136.62}15{"step": 650, "loss": 0.294386625289917, "lr": 0.0008263957207103506, "grad_norm": 0.07298284769058228, "tokens": 107666, "tok_per_s": 730.5660116324807, "t": 147.82}16{"step": 700, "loss": 0.3116520047187805, "lr": 0.0007961266711550921, "grad_norm": 0.05143333971500397, "tokens": 115959, "tok_per_s": 731.3087261743568, "t": 159.01}17{"step": 750, "loss": 0.2591821849346161, "lr": 0.0007641763268666831, "grad_norm": 0.04235551506280899, "tokens": 124302, "tok_per_s": 731.4750818386264, "t": 170.38}18{"step": 800, "loss": 0.33459532260894775, "lr": 0.0007307629410938364, "grad_norm": 0.08239558339118958, "tokens": 132734, "tok_per_s": 733.0145098590112, "t": 181.52}19{"step": 850, "loss": 0.34336617588996887, "lr": 0.0006961147611421076, "grad_norm": 0.07290179282426834, "tokens": 141025, "tok_per_s": 733.8649183056879, "t": 192.61}20{"step": 900, "loss": 0.3378755450248718, "lr": 0.0006604684692133597, "grad_norm": 0.1295628398656845, "tokens": 149035, "tok_per_s": 733.4884209107172, "t": 203.63}21{"step": 950, "loss": 0.31969067454338074, "lr": 0.0006240675656263302, "grad_norm": 0.08445288985967636, "tokens": 157135, "tok_per_s": 733.2837633929447, "t": 214.73}22{"step": 999, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.4114615127200712, "val_loss_b2": 0.4107440534707873, "val_loss_b4": 0.411278999578014, "val_loss_b8": 0.41611300464193673, "t": 227.2}23{"step": 1000, "loss": 0.2974494695663452, "lr": 0.0005871607054625496, "grad_norm": 0.06395639479160309, "tokens": 165602, "tok_per_s": 729.6745772577765, "t": 227.4}24{"step": 1050, "loss": 0.27726855874061584, "lr": 0.00055, "grad_norm": 0.13304054737091064, "tokens": 173674, "tok_per_s": 728.9295376907252, "t": 238.7}25{"step": 1100, "loss": 0.23081760108470917, "lr": 0.0005128392945374505, "grad_norm": 0.09567917138338089, "tokens": 181834, "tok_per_s": 729.0928487383845, "t": 249.84}26{"step": 1150, "loss": 0.34129706025123596, "lr": 0.0004759324343736697, "grad_norm": 0.08240954577922821, "tokens": 190158, "tok_per_s": 729.7390719001983, "t": 261.03}27{"step": 1200, "loss": 0.3132610321044922, "lr": 0.00043953153078664045, "grad_norm": 0.1229400485754013, "tokens": 198573, "tok_per_s": 730.2571147345977, "t": 272.36}28{"step": 1250, "loss": 0.3715328574180603, "lr": 0.00040388523885789254, "grad_norm": 0.15301461517810822, "tokens": 206880, "tok_per_s": 730.6283857069637, "t": 283.6}29{"step": 1300, "loss": 0.2495521605014801, "lr": 0.00036923705890616387, "grad_norm": 0.04287685081362724, "tokens": 215095, "tok_per_s": 730.7486552068776, "t": 294.79}30{"step": 1350, "loss": 0.2587812542915344, "lr": 0.0003358236731333169, "grad_norm": 0.11645929515361786, "tokens": 223349, "tok_per_s": 731.0613859104535, "t": 305.96}31{"step": 1400, "loss": 0.2501791715621948, "lr": 0.00030387332884490803, "grad_norm": 0.1007695347070694, "tokens": 231716, "tok_per_s": 731.3535606308608, "t": 317.27}32{"step": 1450, "loss": 0.35891661047935486, "lr": 0.0002736042792896495, "grad_norm": 0.17963343858718872, "tokens": 239960, "tok_per_s": 731.8156869909545, "t": 328.34}33{"step": 1499, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.40851796080772096, "val_loss_b2": 0.40876816782164893, "val_loss_b4": 0.4131663564764196, "val_loss_b8": 0.42335924882591214, "t": 340.73}34{"step": 1499, "checkpoint_sha256": "d4325f11d7f68754631fd07924bd4768d19b957cf8d4daed88b17c746bad1f64", "t": 340.75}35{"step": 1500, "loss": 0.26295551657676697, "lr": 0.0002452232927684166, "grad_norm": 0.15522685647010803, "tokens": 248357, "tok_per_s": 729.2761631646307, "t": 340.99}36{"step": 1550, "loss": 0.3109534978866577, "lr": 0.0002189242401970908, "grad_norm": 0.16692478954792023, "tokens": 256793, "tok_per_s": 730.2609578959001, "t": 352.09}37{"step": 1600, "loss": 0.283221572637558, "lr": 0.00019488677077162295, "grad_norm": 0.1639794409275055, "tokens": 265023, "tok_per_s": 729.8172581207525, "t": 363.58}38{"step": 1650, "loss": 0.35360851883888245, "lr": 0.00017327508478186216, "grad_norm": 0.2212497889995575, "tokens": 273283, "tok_per_s": 714.4591261343934, "t": 382.95}39{"step": 1700, "loss": 0.35748106241226196, "lr": 0.00015423681195707997, "grad_norm": 0.12465238571166992, "tokens": 281671, "tok_per_s": 699.6272868796068, "t": 403.04}40{"step": 1750, "loss": 0.2656850516796112, "lr": 0.00013790200300522413, "grad_norm": 0.07715098559856415, "tokens": 289799, "tok_per_s": 685.71970277419, "t": 423.06}41{"step": 1800, "loss": 0.24114304780960083, "lr": 0.00012438224123471442, "grad_norm": 0.07585620880126953, "tokens": 298140, "tok_per_s": 673.4204134982532, "t": 443.17}42{"step": 1850, "loss": 0.2697941064834595, "lr": 0.00011376988032730135, "grad_norm": 0.07818277925252914, "tokens": 306518, "tok_per_s": 662.754582787904, "t": 462.93}43{"step": 1900, "loss": 0.27652421593666077, "lr": 0.00010613741346877497, "grad_norm": 0.10166487842798233, "tokens": 314885, "tok_per_s": 652.3479962923444, "t": 483.14}44{"step": 1950, "loss": 0.20917129516601562, "lr": 0.00010153697814699858, "grad_norm": 0.10033971816301346, "tokens": 322988, "tok_per_s": 642.2730058727624, "t": 503.32}45{"step": 1999, "loss": 0.2973034679889679, "lr": 0.00010000061514140841, "grad_norm": 0.09640076756477356, "tokens": 331026, "tok_per_s": 633.4933472510902, "t": 522.98}46{"step": 1999, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.4078555936090659, "val_loss_b2": 0.408420847571091, "val_loss_b4": 0.41316756238554775, "val_loss_b8": 0.4216234737129835, "t": 526.21}47{"step": 1999, "checkpoint_sha256": "aabf646812efd9f1fdedbcccbf73004a44516484ad036798fdf3a7b80e5cefb0", "t": 526.23}48