{"step": 0, "loss": 0.430623322725296, "lr": 1e-05, "grad_norm": 0.09646869450807571, "tokens": 139, "tok_per_s": 203.30346221241948, "t": 1.19} {"step": 50, "loss": 0.31626564264297485, "lr": 0.00051, "grad_norm": 0.11560578644275665, "tokens": 8357, "tok_per_s": 148.82672549333114, "t": 56.65} {"step": 100, "loss": 0.32004091143608093, "lr": 0.001, "grad_norm": 0.06376565992832184, "tokens": 16659, "tok_per_s": 150.3311171967063, "t": 111.32} {"step": 150, "loss": 0.45409780740737915, "lr": 0.0009993400362330058, "grad_norm": 0.05533059313893318, "tokens": 25169, "tok_per_s": 152.7847108568346, "t": 165.24} {"step": 200, "loss": 0.48393678665161133, "lr": 0.0009973620807194618, "grad_norm": 0.07814832031726837, "tokens": 33572, "tok_per_s": 153.51680295158684, "t": 219.19} {"step": 250, "loss": 0.4184119999408722, "lr": 0.000994071935143687, "grad_norm": 0.051827967166900635, "tokens": 41743, "tok_per_s": 152.56058475948052, "t": 274.12} {"step": 300, "loss": 0.3970698118209839, "lr": 0.000989479250069539, "grad_norm": 0.022306786850094795, "tokens": 49922, "tok_per_s": 151.6477937729032, "t": 329.7} {"step": 350, "loss": 0.38927754759788513, "lr": 0.0009835974966336503, "grad_norm": 0.05678004026412964, "tokens": 58442, "tok_per_s": 152.2953106485795, "t": 384.25} {"step": 400, "loss": 0.34559404850006104, "lr": 0.0009764439270322612, "grad_norm": 0.052990902215242386, "tokens": 66780, "tok_per_s": 152.57509093138225, "t": 438.19} {"step": 450, "loss": 0.4869305491447449, "lr": 0.0009680395239175562, "grad_norm": 0.060661159455776215, "tokens": 74983, "tok_per_s": 152.1434931686714, "t": 493.35} {"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4594262331327586, "val_loss_b2": 0.45697404834188926, "val_loss_b4": 0.45439473016324333, "val_loss_b8": 0.4547064646292696, "t": 560.42} {"step": 500, "loss": 0.32437166571617126, "lr": 0.0009584089388519307, "grad_norm": 0.07037805765867233, "tokens": 83177, "tok_per_s": 148.26468909937023, "t": 561.5} {"step": 550, "loss": 0.42457497119903564, "lr": 0.0009475804200007103, "grad_norm": 0.24533061683177948, "tokens": 91423, "tok_per_s": 148.57182654201367, "t": 615.85} {"step": 600, "loss": 0.37946760654449463, "lr": 0.0009355857292754152, "grad_norm": 0.05572519078850746, "tokens": 99986, "tok_per_s": 149.12548464206017, "t": 670.98} {"step": 650, "loss": 0.35455653071403503, "lr": 0.0009224600491706008, "grad_norm": 0.0736238956451416, "tokens": 108206, "tok_per_s": 149.14957085837142, "t": 725.99} {"step": 700, "loss": 0.4394410252571106, "lr": 0.0009082418795675396, "grad_norm": 0.18634991347789764, "tokens": 116415, "tok_per_s": 149.20904824730871, "t": 780.72} {"step": 750, "loss": 0.33788907527923584, "lr": 0.0008929729248074364, "grad_norm": 0.06176457181572914, "tokens": 124709, "tok_per_s": 149.35701349985234, "t": 835.47} {"step": 800, "loss": 0.41877418756484985, "lr": 0.0008766979713654089, "grad_norm": 0.09123989939689636, "tokens": 132874, "tok_per_s": 149.37780365436785, "t": 890.02} {"step": 850, "loss": 0.36878329515457153, "lr": 0.0008594647564840406, "grad_norm": 0.08209313452243805, "tokens": 141506, "tok_per_s": 149.70065852033815, "t": 945.76} {"step": 900, "loss": 0.28941383957862854, "lr": 0.0008413238281518224, "grad_norm": 0.07920273393392563, "tokens": 149769, "tok_per_s": 149.771770791186, "t": 1000.48} {"step": 950, "loss": 0.3539820611476898, "lr": 0.0008223283968371944, "grad_norm": 0.05385209247469902, "tokens": 158176, "tok_per_s": 149.9412829291194, "t": 1055.42} {"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45807183323498724, "val_loss_b2": 0.4552198234246011, "val_loss_b4": 0.4522481610940677, "val_loss_b8": 0.45329890526122446, "t": 1122.65} {"step": 1000, "loss": 0.41146716475486755, "lr": 0.000802534179413072, "grad_norm": 0.08157921582460403, "tokens": 166573, "tok_per_s": 148.2852448571434, "t": 1123.83} {"step": 1050, "loss": 0.35536378622055054, "lr": 0.0007819992357296598, "grad_norm": 0.07169362902641296, "tokens": 174773, "tok_per_s": 148.38678466031516, "t": 1178.32} {"step": 1100, "loss": 0.4355790913105011, "lr": 0.0007607837983149056, "grad_norm": 0.07180934399366379, "tokens": 183200, "tok_per_s": 148.60495517818538, "t": 1233.3} {"step": 1150, "loss": 0.4673303961753845, "lr": 0.0007389500957021191, "grad_norm": 0.19262319803237915, "tokens": 191474, "tok_per_s": 148.7223804014528, "t": 1287.96} {"step": 1200, "loss": 0.3917759954929352, "lr": 0.0007165621699029615, "grad_norm": 0.1391720026731491, "tokens": 200061, "tok_per_s": 149.0385821621779, "t": 1342.84} {"step": 1250, "loss": 0.3868783712387085, "lr": 0.000693685688561191, "grad_norm": 0.10632302612066269, "tokens": 208455, "tok_per_s": 149.19513707294269, "t": 1397.7} {"step": 1300, "loss": 0.3828953504562378, "lr": 0.0006703877523381495, "grad_norm": 0.19501130282878876, "tokens": 216814, "tok_per_s": 149.4697355322118, "t": 1451.06} {"step": 1350, "loss": 0.3337797522544861, "lr": 0.0006467366980949609, "grad_norm": 0.14037370681762695, "tokens": 225136, "tok_per_s": 149.68138496043562, "t": 1504.6} {"step": 1400, "loss": 0.3423234820365906, "lr": 0.0006228018984487442, "grad_norm": 0.08871813863515854, "tokens": 233471, "tok_per_s": 149.76101198875006, "t": 1559.46} {"step": 1450, "loss": 0.3102428615093231, "lr": 0.0005986535582907738, "grad_norm": 0.06003474444150925, "tokens": 241795, "tok_per_s": 149.88594558330536, "t": 1613.7} {"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4558290976970404, "val_loss_b2": 0.4522764460684455, "val_loss_b4": 0.44971600960721636, "val_loss_b8": 0.45684011185797874, "t": 1668.26} {"step": 1500, "loss": 0.31346070766448975, "lr": 0.000574362508863438, "grad_norm": 0.06406529247760773, "tokens": 250085, "tok_per_s": 149.8630800376198, "t": 1669.26} {"step": 1550, "loss": 0.383423388004303, "lr": 0.00055, "grad_norm": 0.10479037463665009, "tokens": 258187, "tok_per_s": 150.75223004041047, "t": 1713.16} {"step": 1600, "loss": 0.34890681505203247, "lr": 0.0005256374911365621, "grad_norm": 0.15650342404842377, "tokens": 266247, "tok_per_s": 151.51014906097063, "t": 1757.79} {"step": 1650, "loss": 0.3048892319202423, "lr": 0.0005013464417092262, "grad_norm": 0.12539225816726685, "tokens": 274738, "tok_per_s": 152.48135666059008, "t": 1802.28} {"step": 1700, "loss": 0.36610063910484314, "lr": 0.00047719810155125587, "grad_norm": 0.086125448346138, "tokens": 283093, "tok_per_s": 153.3331256860968, "t": 1846.76} {"step": 1750, "loss": 0.3848368227481842, "lr": 0.0004532633019050392, "grad_norm": 0.0800352543592453, "tokens": 291261, "tok_per_s": 154.03601432775795, "t": 1891.36} {"step": 1800, "loss": 0.39081433415412903, "lr": 0.0004296122476618507, "grad_norm": 0.10234438627958298, "tokens": 299555, "tok_per_s": 154.80664575508678, "t": 1935.53} {"step": 1850, "loss": 0.4074227213859558, "lr": 0.00040631431143880916, "grad_norm": 0.0860469862818718, "tokens": 307521, "tok_per_s": 155.39443519410466, "t": 1979.47} {"step": 1900, "loss": 0.39075911045074463, "lr": 0.00038343783009703845, "grad_norm": 0.1089826449751854, "tokens": 315892, "tok_per_s": 156.12276009119165, "t": 2023.86} {"step": 1950, "loss": 0.35079824924468994, "lr": 0.000361049904297881, "grad_norm": 0.04373926669359207, "tokens": 324298, "tok_per_s": 156.83143055006346, "t": 2068.31} {"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45601102717114295, "val_loss_b2": 0.45294854534030726, "val_loss_b4": 0.4527920590885288, "val_loss_b8": 0.46246462446413, "t": 2120.84} {"step": 2000, "loss": 0.28441286087036133, "lr": 0.0003392162016850945, "grad_norm": 0.13223236799240112, "tokens": 332486, "tok_per_s": 156.7442369406395, "t": 2121.7} {"step": 2050, "loss": 0.46192628145217896, "lr": 0.0003180007642703402, "grad_norm": 0.14879104495048523, "tokens": 340738, "tok_per_s": 157.50016192331373, "t": 2163.92} {"step": 2100, "loss": 0.3730167746543884, "lr": 0.000297465820586928, "grad_norm": 0.12707780301570892, "tokens": 349148, "tok_per_s": 158.29160806452373, "t": 2206.23} {"step": 2150, "loss": 0.34113383293151855, "lr": 0.0002776716031628058, "grad_norm": 0.09816351532936096, "tokens": 357576, "tok_per_s": 159.07528860043, "t": 2248.34} {"step": 2200, "loss": 0.354623943567276, "lr": 0.00025867617184817756, "grad_norm": 0.13758626580238342, "tokens": 366097, "tok_per_s": 160.64851792135653, "t": 2279.37} {"step": 2250, "loss": 0.2746962606906891, "lr": 0.00024053524351595949, "grad_norm": 0.1078144833445549, "tokens": 374285, "tok_per_s": 162.0412024326828, "t": 2310.32} {"step": 2300, "loss": 0.3693453371524811, "lr": 0.0002233020286345913, "grad_norm": 0.09350574761629105, "tokens": 382864, "tok_per_s": 163.54464960966592, "t": 2341.54} {"step": 2350, "loss": 0.449652761220932, "lr": 0.00020702707519256364, "grad_norm": 0.09200843423604965, "tokens": 391427, "tok_per_s": 165.02249730495103, "t": 2372.46} {"step": 2400, "loss": 0.6372146010398865, "lr": 0.00019175812043246033, "grad_norm": 0.16516390442848206, "tokens": 399797, "tok_per_s": 166.35690554691172, "t": 2403.75} {"step": 2450, "loss": 0.33922722935676575, "lr": 0.00017753995082939931, "grad_norm": 0.10634790360927582, "tokens": 407948, "tok_per_s": 167.59273064145202, "t": 2434.66} {"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45402526667460014, "val_loss_b2": 0.45017814260212996, "val_loss_b4": 0.44784448321903203, "val_loss_b8": 0.4558290093329342, "t": 2472.22} {"step": 2500, "loss": 0.40230390429496765, "lr": 0.00016441427072458494, "grad_norm": 0.15944024920463562, "tokens": 416019, "tok_per_s": 168.26955261310005, "t": 2472.84} {"step": 2550, "loss": 0.3239855170249939, "lr": 0.0001524195799992897, "grad_norm": 0.10084546357393265, "tokens": 424449, "tok_per_s": 169.59003912031824, "t": 2503.29} {"step": 2600, "loss": 0.3674469590187073, "lr": 0.0001415910611480694, "grad_norm": 0.14146648347377777, "tokens": 432494, "tok_per_s": 170.76401886032957, "t": 2533.2} {"step": 2650, "loss": 0.29585787653923035, "lr": 0.00013196047608244387, "grad_norm": 0.1219630166888237, "tokens": 440693, "tok_per_s": 171.9011413232835, "t": 2564.14} {"step": 2700, "loss": 0.401299387216568, "lr": 0.00012355607296773896, "grad_norm": 0.14812071621418, "tokens": 449079, "tok_per_s": 173.09884556359114, "t": 2594.85} {"step": 2750, "loss": 0.30322858691215515, "lr": 0.00011640250336634969, "grad_norm": 0.07447124272584915, "tokens": 457686, "tok_per_s": 174.3509509548352, "t": 2625.59} {"step": 2800, "loss": 0.4089607894420624, "lr": 0.00011052074993046101, "grad_norm": 0.13401761651039124, "tokens": 466220, "tok_per_s": 175.5236868287209, "t": 2656.67} {"step": 2850, "loss": 0.4673190116882324, "lr": 0.00010592806485631325, "grad_norm": 0.21694199740886688, "tokens": 474198, "tok_per_s": 176.53596140461326, "t": 2686.63} {"step": 2900, "loss": 0.4375755488872528, "lr": 0.00010263791928053818, "grad_norm": 0.2667647898197174, "tokens": 482297, "tok_per_s": 177.60961852145763, "t": 2715.99} {"step": 2950, "loss": 0.39300939440727234, "lr": 0.0001006599637669943, "grad_norm": 0.14076247811317444, "tokens": 490516, "tok_per_s": 178.69416445318947, "t": 2745.5} {"step": 2999, "loss": 0.504745602607727, "lr": 0.0001000002640500325, "grad_norm": 0.1784607470035553, "tokens": 498543, "tok_per_s": 179.78546969385926, "t": 2773.49} {"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4536697186525964, "val_loss_b2": 0.4508313573364438, "val_loss_b4": 0.45120430744710727, "val_loss_b8": 0.463173512345526, "t": 2780.43} {"step": 2999, "checkpoint_sha256": "72707f7b2535af0916d773bf3a1a6a9769999fe63a78299b4ed37790a9f4f372", "t": 2780.47}