{"step": 0, "loss": 0.4617134928703308, "lr": 1e-05, "grad_norm": 1.5623806715011597, "tokens": 139, "tok_per_s": 315.97102863101395, "t": 0.97} {"step": 50, "loss": 0.3293335437774658, "lr": 0.00051, "grad_norm": 0.5872856974601746, "tokens": 8357, "tok_per_s": 341.035911466911, "t": 25.04} {"step": 100, "loss": 0.3200133442878723, "lr": 0.001, "grad_norm": 0.18266485631465912, "tokens": 16659, "tok_per_s": 333.1970415471441, "t": 50.53} {"step": 150, "loss": 0.45751845836639404, "lr": 0.0009993400362330058, "grad_norm": 0.08737741410732269, "tokens": 25169, "tok_per_s": 333.5145290301892, "t": 76.0} {"step": 200, "loss": 0.48353636264801025, "lr": 0.0009973620807194618, "grad_norm": 0.08750754594802856, "tokens": 33572, "tok_per_s": 331.9550040145923, "t": 101.67} {"step": 250, "loss": 0.4154420495033264, "lr": 0.000994071935143687, "grad_norm": 0.03441664204001427, "tokens": 41743, "tok_per_s": 328.29015866994143, "t": 127.69} {"step": 300, "loss": 0.39720508456230164, "lr": 0.000989479250069539, "grad_norm": 0.01911080628633499, "tokens": 49922, "tok_per_s": 326.0899673570133, "t": 153.63} {"step": 350, "loss": 0.3880905508995056, "lr": 0.0009835974966336503, "grad_norm": 0.05504586920142174, "tokens": 58442, "tok_per_s": 326.73193972375856, "t": 179.4} {"step": 400, "loss": 0.3532821536064148, "lr": 0.0009764439270322612, "grad_norm": 0.11452716588973999, "tokens": 66780, "tok_per_s": 325.67248113180995, "t": 205.59} {"step": 450, "loss": 0.492530882358551, "lr": 0.0009680395239175562, "grad_norm": 0.08978056907653809, "tokens": 74983, "tok_per_s": 324.87406224670207, "t": 231.34} {"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4604913909897069, "val_loss_b2": 0.459025903309784, "val_loss_b4": 0.457789566318292, "val_loss_b8": 0.4582393029571578, "t": 263.56} {"step": 500, "loss": 0.32230260968208313, "lr": 0.0009584089388519307, "grad_norm": 0.06601792573928833, "tokens": 83177, "tok_per_s": 315.5552306033566, "t": 264.13} {"step": 550, "loss": 0.4194260537624359, "lr": 0.0009475804200007103, "grad_norm": 0.14841149747371674, "tokens": 91423, "tok_per_s": 315.8802138767271, "t": 289.96} {"step": 600, "loss": 0.3835363984107971, "lr": 0.0009355857292754152, "grad_norm": 0.06976689398288727, "tokens": 99986, "tok_per_s": 317.1668923294357, "t": 315.78} {"step": 650, "loss": 0.3506314754486084, "lr": 0.0009224600491706008, "grad_norm": 0.07876528054475784, "tokens": 108206, "tok_per_s": 317.2304097336468, "t": 341.63} {"step": 700, "loss": 0.43874818086624146, "lr": 0.0009082418795675396, "grad_norm": 0.09588900208473206, "tokens": 116415, "tok_per_s": 317.028499242122, "t": 367.74} {"step": 750, "loss": 0.3406626284122467, "lr": 0.0008929729248074364, "grad_norm": 0.03743654862046242, "tokens": 124709, "tok_per_s": 317.3944128904066, "t": 393.45} {"step": 800, "loss": 0.4290646016597748, "lr": 0.0008766979713654089, "grad_norm": 0.08828985691070557, "tokens": 132874, "tok_per_s": 317.8759067785736, "t": 418.54} {"step": 850, "loss": 0.3766106963157654, "lr": 0.0008594647564840406, "grad_norm": 0.2113341987133026, "tokens": 141506, "tok_per_s": 318.6494880253143, "t": 444.61} {"step": 900, "loss": 0.2938816249370575, "lr": 0.0008413238281518224, "grad_norm": 0.04780648648738861, "tokens": 149769, "tok_per_s": 318.83450376072534, "t": 470.27} {"step": 950, "loss": 0.3596324026584625, "lr": 0.0008223283968371944, "grad_norm": 0.09729944169521332, "tokens": 158176, "tok_per_s": 319.0728588590745, "t": 496.27} {"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4584581930687887, "val_loss_b2": 0.45632744963501637, "val_loss_b4": 0.45418797883569106, "val_loss_b8": 0.4571841800665256, "t": 528.7} {"step": 1000, "loss": 0.4126054048538208, "lr": 0.000802534179413072, "grad_norm": 0.09198828786611557, "tokens": 166573, "tok_per_s": 315.0607638178343, "t": 529.24} {"step": 1050, "loss": 0.36693912744522095, "lr": 0.0007819992357296598, "grad_norm": 0.14042602479457855, "tokens": 174773, "tok_per_s": 315.42779267534263, "t": 554.62} {"step": 1100, "loss": 0.43881696462631226, "lr": 0.0007607837983149056, "grad_norm": 0.05978560447692871, "tokens": 183200, "tok_per_s": 315.8452748832409, "t": 580.57} {"step": 1150, "loss": 0.46572089195251465, "lr": 0.0007389500957021191, "grad_norm": 0.15345531702041626, "tokens": 191474, "tok_per_s": 315.96266882985316, "t": 606.54} {"step": 1200, "loss": 0.4063732922077179, "lr": 0.0007165621699029615, "grad_norm": 0.2569475471973419, "tokens": 200061, "tok_per_s": 316.4714223366606, "t": 632.7} {"step": 1250, "loss": 0.39052674174308777, "lr": 0.000693685688561191, "grad_norm": 0.15839019417762756, "tokens": 208455, "tok_per_s": 316.64674733251707, "t": 658.86} {"step": 1300, "loss": 0.388981431722641, "lr": 0.0006703877523381495, "grad_norm": 0.2273511439561844, "tokens": 216814, "tok_per_s": 317.160175358587, "t": 684.15} {"step": 1350, "loss": 0.3423897922039032, "lr": 0.0006467366980949609, "grad_norm": 0.20026110112667084, "tokens": 225136, "tok_per_s": 317.4888723478244, "t": 709.65} {"step": 1400, "loss": 0.34345322847366333, "lr": 0.0006228018984487442, "grad_norm": 0.11182186752557755, "tokens": 233471, "tok_per_s": 317.5220958840195, "t": 735.83} {"step": 1450, "loss": 0.30933189392089844, "lr": 0.0005986535582907738, "grad_norm": 0.10891305655241013, "tokens": 241795, "tok_per_s": 317.54622688836406, "t": 761.98} {"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45632406265762654, "val_loss_b2": 0.4535597062804183, "val_loss_b4": 0.45358924809320034, "val_loss_b8": 0.46567067352640856, "t": 794.45} {"step": 1500, "loss": 0.3173529803752899, "lr": 0.000574362508863438, "grad_norm": 0.07007183879613876, "tokens": 250085, "tok_per_s": 314.76747339604407, "t": 795.04} {"step": 1550, "loss": 0.3833349645137787, "lr": 0.00055, "grad_norm": 0.1301269680261612, "tokens": 258187, "tok_per_s": 314.9839019862463, "t": 820.22} {"step": 1600, "loss": 0.35653769969940186, "lr": 0.0005256374911365621, "grad_norm": 0.18991577625274658, "tokens": 266247, "tok_per_s": 314.8401943954354, "t": 846.2} {"step": 1650, "loss": 0.32828477025032043, "lr": 0.0005013464417092262, "grad_norm": 0.1639462262392044, "tokens": 274738, "tok_per_s": 315.2297898350132, "t": 872.08} {"step": 1700, "loss": 0.37509918212890625, "lr": 0.00047719810155125587, "grad_norm": 0.12979307770729065, "tokens": 283093, "tok_per_s": 315.31556807739, "t": 898.35} {"step": 1750, "loss": 0.38399025797843933, "lr": 0.0004532633019050392, "grad_norm": 0.0933946818113327, "tokens": 291261, "tok_per_s": 315.3903767113807, "t": 924.03} {"step": 1800, "loss": 0.4040701985359192, "lr": 0.0004296122476618507, "grad_norm": 0.19485753774642944, "tokens": 299555, "tok_per_s": 315.5476939783343, "t": 949.85} {"step": 1850, "loss": 0.416336327791214, "lr": 0.00040631431143880916, "grad_norm": 0.12129907310009003, "tokens": 307521, "tok_per_s": 315.3970866105778, "t": 975.56} {"step": 1900, "loss": 0.39371052384376526, "lr": 0.00038343783009703845, "grad_norm": 0.11515633016824722, "tokens": 315892, "tok_per_s": 315.5625720387272, "t": 1001.58} {"step": 1950, "loss": 0.35341987013816833, "lr": 0.000361049904297881, "grad_norm": 0.10040514171123505, "tokens": 324298, "tok_per_s": 315.5854166711373, "t": 1028.15} {"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4552681144086406, "val_loss_b2": 0.45249231863985395, "val_loss_b4": 0.45186789274333206, "val_loss_b8": 0.45929638395878175, "t": 1060.24} {"step": 2000, "loss": 0.28930509090423584, "lr": 0.0003392162016850945, "grad_norm": 0.16511349380016327, "tokens": 332486, "tok_per_s": 313.6030509521384, "t": 1060.75} {"step": 2050, "loss": 0.45662567019462585, "lr": 0.0003180007642703402, "grad_norm": 0.14923787117004395, "tokens": 340738, "tok_per_s": 313.6758754890311, "t": 1086.81} {"step": 2100, "loss": 0.3676287829875946, "lr": 0.000297465820586928, "grad_norm": 0.1273709535598755, "tokens": 349148, "tok_per_s": 313.94726090539666, "t": 1112.66} {"step": 2150, "loss": 0.34017086029052734, "lr": 0.0002776716031628058, "grad_norm": 0.14788047969341278, "tokens": 357576, "tok_per_s": 314.29933753172645, "t": 1138.23} {"step": 2200, "loss": 0.3585178852081299, "lr": 0.00025867617184817756, "grad_norm": 0.20928049087524414, "tokens": 366097, "tok_per_s": 314.6587556180631, "t": 1164.01} {"step": 2250, "loss": 0.28358742594718933, "lr": 0.00024053524351595949, "grad_norm": 0.18976014852523804, "tokens": 374285, "tok_per_s": 314.57213370313184, "t": 1190.36} {"step": 2300, "loss": 0.3739510774612427, "lr": 0.0002233020286345913, "grad_norm": 0.11758474260568619, "tokens": 382864, "tok_per_s": 314.9411882743058, "t": 1216.21} {"step": 2350, "loss": 0.44766464829444885, "lr": 0.00020702707519256364, "grad_norm": 0.12240925431251526, "tokens": 391427, "tok_per_s": 315.2267488134669, "t": 1242.27} {"step": 2400, "loss": 0.6324288249015808, "lr": 0.00019175812043246033, "grad_norm": 0.19599948823451996, "tokens": 399797, "tok_per_s": 315.2090131298968, "t": 1268.89} {"step": 2450, "loss": 0.3411107361316681, "lr": 0.00017753995082939931, "grad_norm": 0.14806079864501953, "tokens": 407948, "tok_per_s": 315.12566841018287, "t": 1295.09} {"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4540346652313428, "val_loss_b2": 0.45003071931149935, "val_loss_b4": 0.44636783534050456, "val_loss_b8": 0.44803128399949993, "t": 1327.48} {"step": 2500, "loss": 0.4019432067871094, "lr": 0.00016441427072458494, "grad_norm": 0.1425098031759262, "tokens": 416019, "tok_per_s": 313.39534889600293, "t": 1327.99} {"step": 2550, "loss": 0.3293187618255615, "lr": 0.0001524195799992897, "grad_norm": 0.16499076783657074, "tokens": 424449, "tok_per_s": 313.5995304815762, "t": 1354.01} {"step": 2600, "loss": 0.3666548430919647, "lr": 0.0001415910611480694, "grad_norm": 0.19848975539207458, "tokens": 432494, "tok_per_s": 313.490251535329, "t": 1380.15} {"step": 2650, "loss": 0.28945302963256836, "lr": 0.00013196047608244387, "grad_norm": 0.13678458333015442, "tokens": 440693, "tok_per_s": 314.04809712577264, "t": 1403.8} {"step": 2700, "loss": 0.40452057123184204, "lr": 0.00012355607296773896, "grad_norm": 0.16162781417369843, "tokens": 449079, "tok_per_s": 315.4462016937261, "t": 1424.16} {"step": 2750, "loss": 0.3052932024002075, "lr": 0.00011640250336634969, "grad_norm": 0.09845831990242004, "tokens": 457686, "tok_per_s": 317.01758581513513, "t": 1444.26} {"step": 2800, "loss": 0.4136039912700653, "lr": 0.00011052074993046101, "grad_norm": 0.17848391830921173, "tokens": 466220, "tok_per_s": 318.37520920124956, "t": 1464.91} {"step": 2850, "loss": 0.46885907649993896, "lr": 0.00010592806485631325, "grad_norm": 0.22849717736244202, "tokens": 474198, "tok_per_s": 319.35261278923105, "t": 1485.41} {"step": 2900, "loss": 0.45611774921417236, "lr": 0.00010263791928053818, "grad_norm": 0.21390825510025024, "tokens": 482297, "tok_per_s": 320.2935000330281, "t": 1506.33} {"step": 2950, "loss": 0.396045446395874, "lr": 0.0001006599637669943, "grad_norm": 0.2216213196516037, "tokens": 490516, "tok_per_s": 321.31906309968707, "t": 1527.11} {"step": 2999, "loss": 0.5132167339324951, "lr": 0.0001000002640500325, "grad_norm": 0.24137398600578308, "tokens": 498543, "tok_per_s": 322.34213947444687, "t": 1547.16} {"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4525557969696361, "val_loss_b2": 0.44941951700946625, "val_loss_b4": 0.4488635328733727, "val_loss_b8": 0.45463565207867274, "t": 1552.77} {"step": 2999, "checkpoint_sha256": "c55e6cf9ff3e1e6aa896a8be10e4e4658fa3483609e77aa0a2f94d0b8bc58bb9", "t": 1552.87}