1{"step": 0, "loss": 0.44360893964767456, "lr": 1e-05, "grad_norm": 0.10068731755018234, "tokens": 146, "tok_per_s": 379.1904967131824, "t": 0.87}2{"step": 50, "loss": 0.3289877772331238, "lr": 0.00051, "grad_norm": 0.06031933054327965, "tokens": 8382, "tok_per_s": 543.4168467640391, "t": 15.92}3{"step": 100, "loss": 0.45103463530540466, "lr": 0.001, "grad_norm": 0.06353510916233063, "tokens": 16548, "tok_per_s": 518.345902528987, "t": 32.41}4{"step": 150, "loss": 0.315324991941452, "lr": 0.0009993400362330058, "grad_norm": 0.058041591197252274, "tokens": 24812, "tok_per_s": 516.2149916193804, "t": 48.56}5{"step": 200, "loss": 0.4251997172832489, "lr": 0.0009973620807194618, "grad_norm": 0.0693533718585968, "tokens": 33400, "tok_per_s": 518.5699588492599, "t": 64.9}6{"step": 250, "loss": 0.40569043159484863, "lr": 0.000994071935143687, "grad_norm": 0.10658703744411469, "tokens": 41583, "tok_per_s": 516.8403863368313, "t": 80.95}7{"step": 300, "loss": 0.3475882112979889, "lr": 0.000989479250069539, "grad_norm": 0.047659363597631454, "tokens": 49989, "tok_per_s": 516.2080872242972, "t": 97.33}8{"step": 350, "loss": 0.45864933729171753, "lr": 0.0009835974966336503, "grad_norm": 0.07695730030536652, "tokens": 58214, "tok_per_s": 515.867795669087, "t": 113.34}9{"step": 400, "loss": 0.41047054529190063, "lr": 0.0009764439270322612, "grad_norm": 0.07615884393453598, "tokens": 66391, "tok_per_s": 514.2148216264576, "t": 129.6}10{"step": 450, "loss": 0.30148714780807495, "lr": 0.0009680395239175562, "grad_norm": 0.032057397067546844, "tokens": 74699, "tok_per_s": 514.4093252966711, "t": 145.7}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4601564026630941, "val_loss_b2": 0.4584391186424169, "val_loss_b4": 0.45638808903287587, "val_loss_b8": 0.45659693947797225, "t": 166.76}12{"step": 500, "loss": 0.582899808883667, "lr": 0.0009584089388519307, "grad_norm": 0.06949158757925034, "tokens": 83038, "tok_per_s": 498.40069841629077, "t": 167.1}13{"step": 550, "loss": 0.39293789863586426, "lr": 0.0009475804200007103, "grad_norm": 0.037267740815877914, "tokens": 91441, "tok_per_s": 501.49387790950794, "t": 182.83}14{"step": 600, "loss": 0.4768736660480499, "lr": 0.0009355857292754152, "grad_norm": 0.09590467065572739, "tokens": 99553, "tok_per_s": 501.47207765677956, "t": 199.01}15{"step": 650, "loss": 0.41578325629234314, "lr": 0.0009224600491706008, "grad_norm": 0.1587521731853485, "tokens": 107666, "tok_per_s": 501.7602767418817, "t": 215.07}16{"step": 700, "loss": 0.43583041429519653, "lr": 0.0009082418795675396, "grad_norm": 0.06457367539405823, "tokens": 115959, "tok_per_s": 502.680202581547, "t": 231.17}17{"step": 750, "loss": 0.39333441853523254, "lr": 0.0008929729248074364, "grad_norm": 0.0720522478222847, "tokens": 124302, "tok_per_s": 502.8900218820664, "t": 247.66}18{"step": 800, "loss": 0.49071377515792847, "lr": 0.0008766979713654089, "grad_norm": 0.09458129853010178, "tokens": 132734, "tok_per_s": 504.2102724225809, "t": 263.74}19{"step": 850, "loss": 0.5044121146202087, "lr": 0.0008594647564840406, "grad_norm": 0.10087167471647263, "tokens": 141025, "tok_per_s": 504.6666324540942, "t": 279.93}20{"step": 900, "loss": 0.4620496332645416, "lr": 0.0008413238281518224, "grad_norm": 0.12511363625526428, "tokens": 149035, "tok_per_s": 504.3487684772498, "t": 295.99}21{"step": 950, "loss": 0.4082881808280945, "lr": 0.0008223283968371944, "grad_norm": 0.08660915493965149, "tokens": 157135, "tok_per_s": 503.8126272753373, "t": 312.38}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4563248391337087, "val_loss_b2": 0.4529612171291541, "val_loss_b4": 0.4500673443534328, "val_loss_b8": 0.4523222891787345, "t": 333.18}23{"step": 1000, "loss": 0.4236169755458832, "lr": 0.000802534179413072, "grad_norm": 0.09051677584648132, "tokens": 165602, "tok_per_s": 497.3366906946961, "t": 333.47}24{"step": 1050, "loss": 0.3729163110256195, "lr": 0.0007819992357296598, "grad_norm": 0.08617589622735977, "tokens": 173674, "tok_per_s": 496.77389192877376, "t": 350.1}25{"step": 1100, "loss": 0.3675701320171356, "lr": 0.0007607837983149056, "grad_norm": 0.06448420882225037, "tokens": 181834, "tok_per_s": 496.83024354378847, "t": 366.48}26{"step": 1150, "loss": 0.4148028790950775, "lr": 0.0007389500957021191, "grad_norm": 0.08021393418312073, "tokens": 190158, "tok_per_s": 497.170269836169, "t": 382.97}27{"step": 1200, "loss": 0.3938710391521454, "lr": 0.0007165621699029615, "grad_norm": 0.10902020335197449, "tokens": 198573, "tok_per_s": 497.6256647443422, "t": 399.53}28{"step": 1250, "loss": 0.470177561044693, "lr": 0.000693685688561191, "grad_norm": 0.1066279485821724, "tokens": 206880, "tok_per_s": 497.6743936082616, "t": 416.19}29{"step": 1300, "loss": 0.31399017572402954, "lr": 0.0006703877523381495, "grad_norm": 0.10055562108755112, "tokens": 215095, "tok_per_s": 497.59382597314664, "t": 432.76}30{"step": 1350, "loss": 0.401774138212204, "lr": 0.0006467366980949609, "grad_norm": 0.1030733734369278, "tokens": 223349, "tok_per_s": 497.7851526471807, "t": 449.18}31{"step": 1400, "loss": 0.43696075677871704, "lr": 0.0006228018984487442, "grad_norm": 0.08759450167417526, "tokens": 231716, "tok_per_s": 497.84412816808106, "t": 465.93}32{"step": 1450, "loss": 0.5046469569206238, "lr": 0.0005986535582907738, "grad_norm": 0.11722283810377121, "tokens": 239960, "tok_per_s": 498.0352410802012, "t": 482.3}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4569978239267198, "val_loss_b2": 0.45549401912623405, "val_loss_b4": 0.45732240408967434, "val_loss_b8": 0.46872922597464933, "t": 502.93}34{"step": 1500, "loss": 0.43458813428878784, "lr": 0.000574362508863438, "grad_norm": 0.09314879775047302, "tokens": 248357, "tok_per_s": 493.99446876206827, "t": 503.24}35{"step": 1550, "loss": 0.557553768157959, "lr": 0.00055, "grad_norm": 0.18644362688064575, "tokens": 256793, "tok_per_s": 495.53306558957496, "t": 518.71}36{"step": 1600, "loss": 0.4801119267940521, "lr": 0.0005256374911365621, "grad_norm": 0.17901791632175446, "tokens": 265023, "tok_per_s": 495.74873639526794, "t": 535.08}37{"step": 1650, "loss": 0.5164927244186401, "lr": 0.0005013464417092262, "grad_norm": 0.16601528227329254, "tokens": 273283, "tok_per_s": 495.8345349059787, "t": 551.65}38{"step": 1700, "loss": 0.46620485186576843, "lr": 0.00047719810155125587, "grad_norm": 0.19031429290771484, "tokens": 281671, "tok_per_s": 496.34214230213536, "t": 567.98}39{"step": 1750, "loss": 0.4105158746242523, "lr": 0.0004532633019050392, "grad_norm": 0.11179789155721664, "tokens": 289799, "tok_per_s": 496.28246853057607, "t": 584.43}40{"step": 1800, "loss": 0.3618490695953369, "lr": 0.0004296122476618507, "grad_norm": 0.09445618838071823, "tokens": 298140, "tok_per_s": 496.5675588554315, "t": 600.89}41{"step": 1850, "loss": 0.47131380438804626, "lr": 0.00040631431143880916, "grad_norm": 0.13251905143260956, "tokens": 306518, "tok_per_s": 496.9921844564051, "t": 617.24}42{"step": 1900, "loss": 0.3506874740123749, "lr": 0.00038343783009703845, "grad_norm": 0.09645937383174896, "tokens": 314885, "tok_per_s": 497.3114315372648, "t": 633.67}43{"step": 1950, "loss": 0.32076308131217957, "lr": 0.000361049904297881, "grad_norm": 0.11470590531826019, "tokens": 322988, "tok_per_s": 497.32646143910836, "t": 649.94}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4546232143607029, "val_loss_b2": 0.45132841953448677, "val_loss_b4": 0.4502221657878487, "val_loss_b8": 0.45583135098174854, "t": 670.84}45{"step": 2000, "loss": 0.48702937364578247, "lr": 0.0003392162016850945, "grad_norm": 0.12954342365264893, "tokens": 331190, "tok_per_s": 493.80322002234493, "t": 671.18}46{"step": 2050, "loss": 0.4005405008792877, "lr": 0.0003180007642703402, "grad_norm": 0.1311776340007782, "tokens": 339365, "tok_per_s": 493.8670162265375, "t": 687.65}47{"step": 2100, "loss": 0.34949859976768494, "lr": 0.000297465820586928, "grad_norm": 0.13563375174999237, "tokens": 347821, "tok_per_s": 494.47115402657846, "t": 703.91}48{"step": 2150, "loss": 0.49024274945259094, "lr": 0.0002776716031628058, "grad_norm": 0.09416386485099792, "tokens": 355802, "tok_per_s": 494.23084584573087, "t": 720.4}49{"step": 2200, "loss": 0.3431936204433441, "lr": 0.00025867617184817756, "grad_norm": 0.19345928728580475, "tokens": 363932, "tok_per_s": 494.1925330161135, "t": 736.91}50{"step": 2250, "loss": 0.29876285791397095, "lr": 0.00024053524351595949, "grad_norm": 0.11998790502548218, "tokens": 372235, "tok_per_s": 494.411295612509, "t": 753.38}51{"step": 2300, "loss": 0.3751833438873291, "lr": 0.0002233020286345913, "grad_norm": 0.1754246950149536, "tokens": 380617, "tok_per_s": 494.5507791858257, "t": 770.12}52{"step": 2350, "loss": 0.35470983386039734, "lr": 0.00020702707519256364, "grad_norm": 0.1456558108329773, "tokens": 388820, "tok_per_s": 494.58336141042287, "t": 786.65}53{"step": 2400, "loss": 0.3595636188983917, "lr": 0.00019175812043246033, "grad_norm": 0.2724345624446869, "tokens": 397013, "tok_per_s": 494.721383753257, "t": 802.99}54{"step": 2450, "loss": 0.4080161452293396, "lr": 0.00017753995082939931, "grad_norm": 0.15844008326530457, "tokens": 405444, "tok_per_s": 495.02234104412975, "t": 819.53}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4521611675715552, "val_loss_b2": 0.44901452550986765, "val_loss_b4": 0.4487142088144151, "val_loss_b8": 0.45882957612663255, "t": 840.33}56{"step": 2500, "loss": 0.47043484449386597, "lr": 0.00016441427072458494, "grad_norm": 0.19158314168453217, "tokens": 413920, "tok_per_s": 492.67101244640804, "t": 840.65}57{"step": 2550, "loss": 0.3300534188747406, "lr": 0.0001524195799992897, "grad_norm": 0.11555640399456024, "tokens": 422230, "tok_per_s": 492.8542870417488, "t": 857.19}58{"step": 2600, "loss": 0.4100675880908966, "lr": 0.0001415910611480694, "grad_norm": 0.16078338027000427, "tokens": 430404, "tok_per_s": 493.08253352623973, "t": 873.38}59{"step": 2650, "loss": 0.38008034229278564, "lr": 0.00013196047608244387, "grad_norm": 0.14391842484474182, "tokens": 438498, "tok_per_s": 492.8610681486069, "t": 890.19}60{"step": 2700, "loss": 0.33231571316719055, "lr": 0.00012355607296773896, "grad_norm": 0.14003606140613556, "tokens": 446658, "tok_per_s": 493.02237052823165, "t": 906.45}61{"step": 2750, "loss": 0.35383865237236023, "lr": 0.00011640250336634969, "grad_norm": 0.21345694363117218, "tokens": 455155, "tok_per_s": 493.42940149852456, "t": 922.92}62{"step": 2800, "loss": 0.4214420020580292, "lr": 0.00011052074993046101, "grad_norm": 0.19586677849292755, "tokens": 463083, "tok_per_s": 493.21629309097875, "t": 939.4}63{"step": 2850, "loss": 0.37628963589668274, "lr": 0.00010592806485631325, "grad_norm": 0.19460980594158173, "tokens": 471665, "tok_per_s": 493.7000271129356, "t": 955.86}64{"step": 2900, "loss": 0.43250590562820435, "lr": 0.00010263791928053818, "grad_norm": 0.19755420088768005, "tokens": 480193, "tok_per_s": 494.11576629449, "t": 972.31}65{"step": 2950, "loss": 0.31748321652412415, "lr": 0.0001006599637669943, "grad_norm": 0.18879081308841705, "tokens": 488284, "tok_per_s": 494.0902872316477, "t": 988.74}66{"step": 2999, "loss": 0.4398652911186218, "lr": 0.0001000002640500325, "grad_norm": 0.1778552383184433, "tokens": 496298, "tok_per_s": 494.0841113727118, "t": 1004.97}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45039344362697914, "val_loss_b2": 0.4469778701082834, "val_loss_b4": 0.44693895229980707, "val_loss_b8": 0.45735521631442955, "t": 1009.87}68{"step": 2999, "checkpoint_sha256": "34855465d1f63b1af7cf00389f6c9e5fff15e0d4b32e54ab22e8180ee44dc18e", "t": 1009.94}69