{"step": 0, "loss": 4.893901348114014, "lr": 5e-06, "grad_norm": 8.589385986328125, "tokens": 6745, "tok_per_s": 12394.40133290749, "t": 0.9} {"step": 50, "loss": 2.665226697921753, "lr": 0.000255, "grad_norm": 1.4639750719070435, "tokens": 378542, "tok_per_s": 79054.78748977534, "t": 5.14} {"step": 100, "loss": 1.3162341117858887, "lr": 0.000505, "grad_norm": 4.864460468292236, "tokens": 743327, "tok_per_s": 91713.0322759194, "t": 8.46} {"step": 150, "loss": 0.41476961970329285, "lr": 0.000755, "grad_norm": 1.0099022388458252, "tokens": 1114902, "tok_per_s": 88952.81156872514, "t": 12.88} {"step": 200, "loss": 0.32017263770103455, "lr": 0.001, "grad_norm": 1.0685725212097168, "tokens": 1487594, "tok_per_s": 80907.89388267418, "t": 18.74} {"step": 250, "loss": 0.30244582891464233, "lr": 0.0009998349788004777, "grad_norm": 0.7793363928794861, "tokens": 1855845, "tok_per_s": 75702.28466792182, "t": 24.87} {"step": 300, "loss": 0.2866016626358032, "lr": 0.0009993400362330058, "grad_norm": 0.7026446461677551, "tokens": 2224234, "tok_per_s": 72730.97602655923, "t": 30.93} {"step": 350, "loss": 0.30674242973327637, "lr": 0.0009985155353021003, "grad_norm": 0.20337258279323578, "tokens": 2587196, "tok_per_s": 70275.54583591601, "t": 37.17} {"step": 400, "loss": 0.3003799021244049, "lr": 0.0009973620807194618, "grad_norm": 0.32704678177833557, "tokens": 2958062, "tok_per_s": 68707.77097445262, "t": 43.4} {"step": 450, "loss": 0.3215593993663788, "lr": 0.000995880518460463, "grad_norm": 0.19171284139156342, "tokens": 3321063, "tok_per_s": 67416.61621259828, "t": 49.61} {"step": 499, "val_loss_b0": 0.344234447882506, "t": 55.45} {"step": 500, "loss": 0.25862255692481995, "lr": 0.000994071935143687, "grad_norm": 0.3092474937438965, "tokens": 3686492, "tok_per_s": 66780.74482513161, "t": 55.55} {"step": 550, "loss": 0.2762141525745392, "lr": 0.0009919376572339702, "grad_norm": 0.17167170345783234, "tokens": 4053719, "tok_per_s": 67609.1628555525, "t": 60.31} {"step": 600, "loss": 0.2699465751647949, "lr": 0.000989479250069539, "grad_norm": 0.4065549075603485, "tokens": 4423182, "tok_per_s": 67687.50058655214, "t": 65.7} {"step": 650, "loss": 0.24757076799869537, "lr": 0.0009866985167139451, "grad_norm": 0.13648392260074615, "tokens": 4793485, "tok_per_s": 68088.81982719523, "t": 70.75} {"step": 700, "loss": 0.2661091685295105, "lr": 0.0009835974966336503, "grad_norm": 0.20197056233882904, "tokens": 5161053, "tok_per_s": 67531.36719351159, "t": 76.78} {"step": 750, "loss": 0.29451993107795715, "lr": 0.0009801784642022254, "grad_norm": 0.6001314520835876, "tokens": 5526698, "tok_per_s": 66974.31938204053, "t": 82.87} {"step": 800, "loss": 0.27937617897987366, "lr": 0.0009764439270322612, "grad_norm": 0.1711324155330658, "tokens": 5899309, "tok_per_s": 66658.45937654082, "t": 88.85} {"step": 850, "loss": 0.2733612358570099, "lr": 0.0009723966241362178, "grad_norm": 0.3709823787212372, "tokens": 6268601, "tok_per_s": 66430.96526114485, "t": 94.71} {"step": 900, "loss": 0.2699167728424072, "lr": 0.0009680395239175562, "grad_norm": 0.12896230816841125, "tokens": 6639495, "tok_per_s": 66540.64584280463, "t": 100.13} {"step": 950, "loss": 0.23827987909317017, "lr": 0.0009633758219936298, "grad_norm": 0.21955488622188568, "tokens": 7008173, "tok_per_s": 65975.49436653884, "t": 106.57} {"step": 999, "val_loss_b0": 0.3358626431884068, "t": 113.28} {"step": 1000, "loss": 0.23493222892284393, "lr": 0.0009584089388519307, "grad_norm": 0.16014011204242706, "tokens": 7378163, "tok_per_s": 65260.22913342645, "t": 113.41} {"step": 1050, "loss": 0.28392329812049866, "lr": 0.0009531425173414095, "grad_norm": 0.11941494792699814, "tokens": 7750406, "tok_per_s": 64698.12620002094, "t": 120.14} {"step": 1100, "loss": 0.2538298964500427, "lr": 0.0009475804200007103, "grad_norm": 0.16552582383155823, "tokens": 8114548, "tok_per_s": 64494.73121796913, "t": 126.17} {"step": 1150, "loss": 0.24599699676036835, "lr": 0.0009417267262252774, "grad_norm": 0.1145324856042862, "tokens": 8485043, "tok_per_s": 64249.14619363228, "t": 132.42} {"step": 1200, "loss": 0.23793815076351166, "lr": 0.0009355857292754152, "grad_norm": 0.09503177553415298, "tokens": 8855020, "tok_per_s": 64865.90485113362, "t": 136.86} {"step": 1250, "loss": 0.25888559222221375, "lr": 0.0009291619331274921, "grad_norm": 0.12290304899215698, "tokens": 9229724, "tok_per_s": 66064.18053130695, "t": 140.06} {"step": 1300, "loss": 0.23604851961135864, "lr": 0.0009224600491706008, "grad_norm": 0.12136218696832657, "tokens": 9601501, "tok_per_s": 67174.38824850612, "t": 143.28} {"step": 1350, "loss": 0.21757890284061432, "lr": 0.000915484992751095, "grad_norm": 0.1027582436800003, "tokens": 9969193, "tok_per_s": 68198.7250492196, "t": 146.53} {"step": 1400, "loss": 0.2601683437824249, "lr": 0.0009082418795675396, "grad_norm": 0.17147357761859894, "tokens": 10343983, "tok_per_s": 69225.97694238288, "t": 149.77} {"step": 1450, "loss": 0.25290074944496155, "lr": 0.0009007360219187163, "grad_norm": 0.27584150433540344, "tokens": 10715074, "tok_per_s": 70220.02286578057, "t": 152.94} {"step": 1499, "val_loss_b0": 0.33225616768207233, "t": 156.16} {"step": 1500, "loss": 0.24966830015182495, "lr": 0.0008929729248074364, "grad_norm": 0.1641629934310913, "tokens": 11090019, "tok_per_s": 71146.83666284953, "t": 156.23} {"step": 1550, "loss": 0.238165482878685, "lr": 0.0008849582819030217, "grad_norm": 0.10427166521549225, "tokens": 11466058, "tok_per_s": 72069.09702779935, "t": 159.45} {"step": 1600, "loss": 0.27187713980674744, "lr": 0.0008766979713654089, "grad_norm": 0.1353621929883957, "tokens": 11842461, "tok_per_s": 72952.67948305636, "t": 162.68} {"step": 1650, "loss": 0.2541385591030121, "lr": 0.0008681980515339464, "grad_norm": 0.1683138906955719, "tokens": 12213794, "tok_per_s": 73826.50173045592, "t": 165.79} {"step": 1700, "loss": 0.25042518973350525, "lr": 0.0008594647564840406, "grad_norm": 0.6533067226409912, "tokens": 12581243, "tok_per_s": 74641.24593183695, "t": 168.91} {"step": 1750, "loss": 0.2746562659740448, "lr": 0.0008505044914549131, "grad_norm": 0.13468578457832336, "tokens": 12951154, "tok_per_s": 75382.39274853967, "t": 172.16} {"step": 1800, "loss": 0.23507453501224518, "lr": 0.0008413238281518224, "grad_norm": 0.09708059579133987, "tokens": 13321567, "tok_per_s": 76093.4231191147, "t": 175.42} {"step": 1850, "loss": 0.23296044766902924, "lr": 0.000831929499926194, "grad_norm": 0.10002591460943222, "tokens": 13693429, "tok_per_s": 76841.09323855596, "t": 178.56} {"step": 1900, "loss": 0.2855033278465271, "lr": 0.0008223283968371944, "grad_norm": 0.24509881436824799, "tokens": 14065036, "tok_per_s": 77578.80269448782, "t": 181.65} {"step": 1950, "loss": 0.25528639554977417, "lr": 0.0008125275605983724, "grad_norm": 0.11180505156517029, "tokens": 14433016, "tok_per_s": 78260.62550088504, "t": 184.77} {"step": 1999, "val_loss_b0": 0.33023983609296975, "t": 187.81} {"step": 1999, "checkpoint_sha256": "2794bfcd69fab5976f2dede9aba94223c674c919ef41171beec2e5dec06a43b4", "t": 187.83} {"step": 2000, "loss": 0.2521602213382721, "lr": 0.000802534179413072, "grad_norm": 0.11580369621515274, "tokens": 14797545, "tok_per_s": 78905.05490663534, "t": 187.89} {"step": 2050, "loss": 0.23580710589885712, "lr": 0.000792355582702407, "grad_norm": 0.1044440045952797, "tokens": 15172670, "tok_per_s": 79579.05311074022, "t": 191.01} {"step": 2100, "loss": 0.2425411492586136, "lr": 0.0007819992357296598, "grad_norm": 0.09370554238557816, "tokens": 15540833, "tok_per_s": 80203.53454219426, "t": 194.12} {"step": 2150, "loss": 0.24246105551719666, "lr": 0.0007714727341250532, "grad_norm": 0.1083199679851532, "tokens": 15909883, "tok_per_s": 80823.76775577223, "t": 197.2} {"step": 2200, "loss": 0.25080206990242004, "lr": 0.0007607837983149056, "grad_norm": 0.12443375587463379, "tokens": 16275558, "tok_per_s": 81403.56922794781, "t": 200.29} {"step": 2250, "loss": 0.249131977558136, "lr": 0.0007499402678592567, "grad_norm": 0.1120896115899086, "tokens": 16647673, "tok_per_s": 82000.29014793769, "t": 203.37} {"step": 2300, "loss": 0.2338966280221939, "lr": 0.0007389500957021191, "grad_norm": 0.18210990726947784, "tokens": 17022061, "tok_per_s": 82582.72635782651, "t": 206.47} {"step": 2350, "loss": 0.25850415229797363, "lr": 0.00072782134233857, "grad_norm": 0.10739555209875107, "tokens": 17389657, "tok_per_s": 83132.15770932083, "t": 209.53} {"step": 2400, "loss": 0.2410065084695816, "lr": 0.0007165621699029615, "grad_norm": 0.09528127312660217, "tokens": 17763312, "tok_per_s": 83672.23846673075, "t": 212.65} {"step": 2450, "loss": 0.24681909382343292, "lr": 0.0007051808361825866, "grad_norm": 0.11120103299617767, "tokens": 18129854, "tok_per_s": 83979.51757730836, "t": 216.24} {"step": 2499, "val_loss_b0": 0.3201226467126787, "t": 222.24} {"step": 2500, "loss": 0.20318791270256042, "lr": 0.000693685688561191, "grad_norm": 0.07409936934709549, "tokens": 18498245, "tok_per_s": 83325.88879354074, "t": 222.35} {"step": 2550, "loss": 0.25038501620292664, "lr": 0.0006820851578967708, "grad_norm": 0.09720011055469513, "tokens": 18868723, "tok_per_s": 83088.94373431515, "t": 227.44} {"step": 2600, "loss": 0.27927419543266296, "lr": 0.0006703877523381495, "grad_norm": 0.3294103145599365, "tokens": 19238526, "tok_per_s": 83565.12658303416, "t": 230.57} {"step": 2650, "loss": 0.22914384305477142, "lr": 0.0006586020510848676, "grad_norm": 0.0957266315817833, "tokens": 19604815, "tok_per_s": 84032.82760514115, "t": 233.65} {"step": 2700, "loss": 0.22442744672298431, "lr": 0.0006467366980949609, "grad_norm": 0.0896112397313118, "tokens": 19973518, "tok_per_s": 84492.71076218144, "t": 236.74} {"step": 2750, "loss": 0.2508562207221985, "lr": 0.0006348003957452433, "grad_norm": 0.0941975936293602, "tokens": 20339691, "tok_per_s": 84932.57199798962, "t": 239.83} {"step": 2800, "loss": 0.2486131638288498, "lr": 0.0006228018984487442, "grad_norm": 0.14808215200901031, "tokens": 20706938, "tok_per_s": 85375.4066639954, "t": 242.89} {"step": 2850, "loss": 0.2505967617034912, "lr": 0.0006107500062339806, "grad_norm": 0.11593659222126007, "tokens": 21078412, "tok_per_s": 85805.61329699597, "t": 246.0} {"step": 2900, "loss": 0.2540470361709595, "lr": 0.0005986535582907738, "grad_norm": 0.09411244839429855, "tokens": 21455185, "tok_per_s": 86241.65298335986, "t": 249.13} {"step": 2950, "loss": 0.23919716477394104, "lr": 0.000586521426487344, "grad_norm": 0.13543732464313507, "tokens": 21829052, "tok_per_s": 86666.46080476069, "t": 252.23} {"step": 2999, "val_loss_b0": 0.32096910975426074, "t": 255.31} {"step": 3000, "loss": 0.2272709757089615, "lr": 0.000574362508863438, "grad_norm": 0.09472932666540146, "tokens": 22195465, "tok_per_s": 87033.65458155649, "t": 255.37} {"step": 3050, "loss": 0.2506798207759857, "lr": 0.0005621857231042606, "grad_norm": 0.10756011307239532, "tokens": 22560169, "tok_per_s": 87406.40001090434, "t": 258.46} {"step": 3100, "loss": 0.23246736824512482, "lr": 0.00055, "grad_norm": 0.09280041605234146, "tokens": 22927890, "tok_per_s": 87799.81240636474, "t": 261.49} {"step": 3150, "loss": 0.25815412402153015, "lr": 0.0005378142768957396, "grad_norm": 0.10131771117448807, "tokens": 23296870, "tok_per_s": 88178.08409857047, "t": 264.55} {"step": 3200, "loss": 0.2587609887123108, "lr": 0.0005256374911365621, "grad_norm": 0.09417936205863953, "tokens": 23665276, "tok_per_s": 88541.01773038412, "t": 267.63} {"step": 3250, "loss": 0.22540967166423798, "lr": 0.000513478573512656, "grad_norm": 0.10079510509967804, "tokens": 24037925, "tok_per_s": 88864.42204427028, "t": 270.85} {"step": 3300, "loss": 0.2503198981285095, "lr": 0.0005013464417092262, "grad_norm": 0.0953252986073494, "tokens": 24408498, "tok_per_s": 89178.28853856685, "t": 274.06} {"step": 3350, "loss": 0.2291378378868103, "lr": 0.0004892499937660194, "grad_norm": 0.1113397404551506, "tokens": 24777747, "tok_per_s": 89500.35726034621, "t": 277.2} {"step": 3400, "loss": 0.2388450801372528, "lr": 0.00047719810155125587, "grad_norm": 0.1162654459476471, "tokens": 25152353, "tok_per_s": 89839.86977678102, "t": 280.32} {"step": 3450, "loss": 0.24066077172756195, "lr": 0.0004651996042547569, "grad_norm": 0.09526378661394119, "tokens": 25518244, "tok_per_s": 90131.51533352527, "t": 283.47} {"step": 3499, "val_loss_b0": 0.31135624020307723, "t": 286.63} {"step": 3500, "loss": 0.25604546070098877, "lr": 0.0004532633019050392, "grad_norm": 0.10658708959817886, "tokens": 25888139, "tok_per_s": 90410.89233923804, "t": 286.69} {"step": 3550, "loss": 0.24742013216018677, "lr": 0.0004413979489151325, "grad_norm": 0.0955493301153183, "tokens": 26258139, "tok_per_s": 90716.17455831761, "t": 289.8} {"step": 3600, "loss": 0.2317628115415573, "lr": 0.0004296122476618507, "grad_norm": 0.09340193122625351, "tokens": 26630664, "tok_per_s": 91032.64519866496, "t": 292.89} {"step": 3650, "loss": 0.2472177892923355, "lr": 0.0004179148421032294, "grad_norm": 0.13555389642715454, "tokens": 26998760, "tok_per_s": 91299.05688190578, "t": 296.07} {"step": 3700, "loss": 0.24989689886569977, "lr": 0.00040631431143880916, "grad_norm": 0.11238809674978256, "tokens": 27369665, "tok_per_s": 91573.8900969576, "t": 299.23} {"step": 3750, "loss": 0.23724427819252014, "lr": 0.00039481916381741344, "grad_norm": 0.1086030900478363, "tokens": 27744624, "tok_per_s": 91853.97516141774, "t": 302.4} {"step": 3800, "loss": 0.24095052480697632, "lr": 0.00038343783009703845, "grad_norm": 0.09491030871868134, "tokens": 28115168, "tok_per_s": 92143.34421747255, "t": 305.48} {"step": 3850, "loss": 0.2248423993587494, "lr": 0.0003721786576614301, "grad_norm": 0.10163564234972, "tokens": 28481621, "tok_per_s": 92416.0546594893, "t": 308.54} {"step": 3900, "loss": 0.22799572348594666, "lr": 0.000361049904297881, "grad_norm": 0.13770447671413422, "tokens": 28852349, "tok_per_s": 92679.5826859226, "t": 311.66} {"step": 3950, "loss": 0.2195623517036438, "lr": 0.0003500597321407435, "grad_norm": 0.10534518957138062, "tokens": 29226577, "tok_per_s": 92948.68329587222, "t": 314.79} {"step": 3999, "val_loss_b0": 0.30858088971925773, "t": 317.86} {"step": 3999, "checkpoint_sha256": "e5a48976c0c78d79ea706c398db66a2e5105b01ad15184477b1b85a4bb7f0d4e", "t": 317.87} {"step": 4000, "loss": 0.24589629471302032, "lr": 0.0003392162016850945, "grad_norm": 0.11850559711456299, "tokens": 29598638, "tok_per_s": 93198.95894995796, "t": 317.94} {"step": 4050, "loss": 0.25206413865089417, "lr": 0.0003285272658749467, "grad_norm": 0.1947087049484253, "tokens": 29971194, "tok_per_s": 93460.35374127164, "t": 321.03} {"step": 4100, "loss": 0.23549585044384003, "lr": 0.0003180007642703402, "grad_norm": 0.10763320326805115, "tokens": 30340887, "tok_per_s": 93709.11362194331, "t": 324.13} {"step": 4150, "loss": 0.23217222094535828, "lr": 0.00030764441729759317, "grad_norm": 0.11357047408819199, "tokens": 30707441, "tok_per_s": 93953.10179375118, "t": 327.19} {"step": 4200, "loss": 0.255111962556839, "lr": 0.000297465820586928, "grad_norm": 0.13270950317382812, "tokens": 31075053, "tok_per_s": 94203.0608547411, "t": 330.22} {"step": 4250, "loss": 0.23274120688438416, "lr": 0.0002874724394016277, "grad_norm": 0.1090550646185875, "tokens": 31437289, "tok_per_s": 94437.80719240375, "t": 333.24} {"step": 4300, "loss": 0.22975695133209229, "lr": 0.0002776716031628058, "grad_norm": 0.09239999949932098, "tokens": 31805156, "tok_per_s": 94654.75668019964, "t": 336.36} {"step": 4350, "loss": 0.22192060947418213, "lr": 0.00026807050007380607, "grad_norm": 0.08665385842323303, "tokens": 32177315, "tok_per_s": 94891.32985915107, "t": 339.45} {"step": 4400, "loss": 0.21348054707050323, "lr": 0.00025867617184817756, "grad_norm": 0.10297154635190964, "tokens": 32546876, "tok_per_s": 95111.3544781959, "t": 342.55} {"step": 4450, "loss": 0.2402956187725067, "lr": 0.00024949550854508714, "grad_norm": 0.14627201855182648, "tokens": 32914772, "tok_per_s": 95322.8427840503, "t": 345.65} {"step": 4499, "val_loss_b0": 0.307113040536357, "t": 348.79} {"step": 4500, "loss": 0.23403209447860718, "lr": 0.00024053524351595949, "grad_norm": 0.14701786637306213, "tokens": 33283782, "tok_per_s": 95505.02032013224, "t": 348.85} {"step": 4550, "loss": 0.22132393717765808, "lr": 0.00023180194846605365, "grad_norm": 0.09536434710025787, "tokens": 33657244, "tok_per_s": 95712.80981289134, "t": 352.0} {"step": 4600, "loss": 0.24084043502807617, "lr": 0.0002233020286345913, "grad_norm": 0.16624119877815247, "tokens": 34028571, "tok_per_s": 95918.22131897401, "t": 355.12} {"step": 4650, "loss": 0.24391821026802063, "lr": 0.00021504171809697835, "grad_norm": 0.12853600084781647, "tokens": 34397737, "tok_per_s": 96123.20422021119, "t": 358.2} {"step": 4700, "loss": 0.22518156468868256, "lr": 0.00020702707519256364, "grad_norm": 0.1037769764661789, "tokens": 34766082, "tok_per_s": 96307.34794115594, "t": 361.34} {"step": 4750, "loss": 0.2516454756259918, "lr": 0.00019926397808128378, "grad_norm": 0.12616997957229614, "tokens": 35135394, "tok_per_s": 96505.79144985274, "t": 364.43} {"step": 4800, "loss": 0.22693447768688202, "lr": 0.00019175812043246033, "grad_norm": 0.10747947543859482, "tokens": 35503604, "tok_per_s": 96688.70550060159, "t": 367.55} {"step": 4850, "loss": 0.24022401869297028, "lr": 0.00018451500724890507, "grad_norm": 0.11923696100711823, "tokens": 35876686, "tok_per_s": 96890.09531448482, "t": 370.63} {"step": 4900, "loss": 0.21510519087314606, "lr": 0.00017753995082939931, "grad_norm": 0.10345502942800522, "tokens": 36246522, "tok_per_s": 97081.32484585806, "t": 373.71} {"step": 4950, "loss": 0.24551476538181305, "lr": 0.00017083806687250794, "grad_norm": 0.11034710705280304, "tokens": 36620964, "tok_per_s": 97279.33745013516, "t": 376.8} {"step": 4999, "val_loss_b0": 0.30144658339476427, "t": 379.91} {"step": 5000, "loss": 0.2237081527709961, "lr": 0.00016441427072458494, "grad_norm": 0.111484095454216, "tokens": 36994918, "tok_per_s": 97451.53305834711, "t": 379.97} {"step": 5050, "loss": 0.23500335216522217, "lr": 0.00015827327377472263, "grad_norm": 0.14874327182769775, "tokens": 37363224, "tok_per_s": 97629.85665147858, "t": 383.05} {"step": 5100, "loss": 0.2314451038837433, "lr": 0.0001524195799992897, "grad_norm": 0.12479910999536514, "tokens": 37736785, "tok_per_s": 97827.48587283603, "t": 386.1} {"step": 5150, "loss": 0.23686784505844116, "lr": 0.00014685748265859042, "grad_norm": 0.1780228316783905, "tokens": 38106235, "tok_per_s": 97991.12133427126, "t": 389.23} {"step": 5200, "loss": 0.23971110582351685, "lr": 0.0001415910611480694, "grad_norm": 0.12234541028738022, "tokens": 38482669, "tok_per_s": 98173.7536879953, "t": 392.34} {"step": 5250, "loss": 0.22917263209819794, "lr": 0.00013662417800637024, "grad_norm": 0.12000050395727158, "tokens": 38851644, "tok_per_s": 98347.65238310881, "t": 395.39} {"step": 5300, "loss": 0.23561249673366547, "lr": 0.00013196047608244387, "grad_norm": 0.14291389286518097, "tokens": 39217877, "tok_per_s": 98513.82837106055, "t": 398.45} {"step": 5350, "loss": 0.22554700076580048, "lr": 0.0001276033758637823, "grad_norm": 0.14456899464130402, "tokens": 39591009, "tok_per_s": 98693.59156944367, "t": 401.5} {"step": 5400, "loss": 0.22340495884418488, "lr": 0.00012355607296773896, "grad_norm": 0.14683744311332703, "tokens": 39961932, "tok_per_s": 98866.55391351503, "t": 404.55} {"step": 5450, "loss": 0.2575177848339081, "lr": 0.00011982153579777482, "grad_norm": 0.1387782096862793, "tokens": 40326134, "tok_per_s": 99009.38255709155, "t": 407.65} {"step": 5499, "val_loss_b0": 0.29920892184016, "t": 410.7} {"step": 5500, "loss": 0.2172803431749344, "lr": 0.00011640250336634969, "grad_norm": 0.12045646458864212, "tokens": 40689343, "tok_per_s": 99144.45307280343, "t": 410.76} {"step": 5550, "loss": 0.20771841704845428, "lr": 0.00011330148328605484, "grad_norm": 0.10797061771154404, "tokens": 41053233, "tok_per_s": 99298.19791515301, "t": 413.78} {"step": 5600, "loss": 0.22944067418575287, "lr": 0.00011052074993046101, "grad_norm": 0.11586741358041763, "tokens": 41419954, "tok_per_s": 99448.04495757262, "t": 416.85} {"step": 5650, "loss": 0.22497913241386414, "lr": 0.00010806234276602983, "grad_norm": 0.14512304961681366, "tokens": 41788487, "tok_per_s": 99597.22461299476, "t": 419.93} {"step": 5700, "loss": 0.2533671259880066, "lr": 0.00010592806485631325, "grad_norm": 0.1459806263446808, "tokens": 42153008, "tok_per_s": 99725.95129162961, "t": 423.04} {"step": 5750, "loss": 0.2329426258802414, "lr": 0.00010411948153953696, "grad_norm": 0.14114364981651306, "tokens": 42518941, "tok_per_s": 99488.23303918292, "t": 427.73} {"step": 5800, "loss": 0.22550031542778015, "lr": 0.00010263791928053818, "grad_norm": 0.1401529461145401, "tokens": 42891344, "tok_per_s": 98967.90964824292, "t": 433.74} {"step": 5850, "loss": 0.2264426052570343, "lr": 0.0001014844646978998, "grad_norm": 0.13447849452495575, "tokens": 43261765, "tok_per_s": 99015.61526641472, "t": 437.27} {"step": 5900, "loss": 0.22152191400527954, "lr": 0.0001006599637669943, "grad_norm": 0.14213977754116058, "tokens": 43636103, "tok_per_s": 99153.8144850969, "t": 440.44} {"step": 5950, "loss": 0.2278166264295578, "lr": 0.00010016502119952223, "grad_norm": 0.1376131772994995, "tokens": 44006823, "tok_per_s": 99301.60362599298, "t": 443.51} {"step": 5999, "loss": 0.21452510356903076, "lr": 0.00010000006601251297, "grad_norm": 0.12236664444208145, "tokens": 44367329, "tok_per_s": 99434.74745327698, "t": 446.55} {"step": 5999, "val_loss_b0": 0.29915615541529633, "t": 446.6} {"step": 5999, "checkpoint_sha256": "6e2adb2e666c92af82ee6d3ac90f59766eaff0b406cfdf725162806131ef9ce2", "t": 446.61}