{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 868560, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002302685074714935, "grad_norm": 0.7734375, "learning_rate": 1.3746891406465874e-07, "loss": 0.9869670867919922, "step": 200 }, { "epoch": 0.00460537014942987, "grad_norm": 0.71484375, "learning_rate": 2.756286266924565e-07, "loss": 0.9922489166259766, "step": 400 }, { "epoch": 0.006908055224144804, "grad_norm": 0.470703125, "learning_rate": 4.137883393202542e-07, "loss": 0.9945306396484375, "step": 600 }, { "epoch": 0.00921074029885974, "grad_norm": 0.77734375, "learning_rate": 5.51948051948052e-07, "loss": 0.971050033569336, "step": 800 }, { "epoch": 0.011513425373574674, "grad_norm": 0.56640625, "learning_rate": 6.901077645758497e-07, "loss": 0.98829833984375, "step": 1000 }, { "epoch": 0.013816110448289608, "grad_norm": 0.86328125, "learning_rate": 8.282674772036474e-07, "loss": 0.9930474853515625, "step": 1200 }, { "epoch": 0.016118795523004544, "grad_norm": 0.98828125, "learning_rate": 9.664271898314452e-07, "loss": 0.9899032592773438, "step": 1400 }, { "epoch": 0.01842148059771948, "grad_norm": 0.78515625, "learning_rate": 1.1045869024592427e-06, "loss": 0.9930052947998047, "step": 1600 }, { "epoch": 0.020724165672434413, "grad_norm": 1.0546875, "learning_rate": 1.2427466150870407e-06, "loss": 0.9895816802978515, "step": 1800 }, { "epoch": 0.023026850747149347, "grad_norm": 0.734375, "learning_rate": 1.3809063277148384e-06, "loss": 0.9816262817382813, "step": 2000 }, { "epoch": 0.025329535821864282, "grad_norm": 0.625, "learning_rate": 1.519066040342636e-06, "loss": 1.0000796508789063, "step": 2200 }, { "epoch": 0.027632220896579216, "grad_norm": 0.71484375, "learning_rate": 1.6572257529704338e-06, "loss": 0.9617407989501953, "step": 2400 }, { "epoch": 0.02993490597129415, "grad_norm": 0.546875, "learning_rate": 1.7953854655982317e-06, "loss": 0.9662563323974609, "step": 2600 }, { "epoch": 0.03223759104600909, "grad_norm": 0.69140625, "learning_rate": 1.9335451782260294e-06, "loss": 1.013211669921875, "step": 2800 }, { "epoch": 0.03454027612072402, "grad_norm": 0.77734375, "learning_rate": 2.071704890853827e-06, "loss": 0.9835720062255859, "step": 3000 }, { "epoch": 0.03684296119543896, "grad_norm": 0.765625, "learning_rate": 2.209864603481625e-06, "loss": 0.9656615447998047, "step": 3200 }, { "epoch": 0.03914564627015389, "grad_norm": 0.8203125, "learning_rate": 2.3480243161094226e-06, "loss": 0.9996417236328125, "step": 3400 }, { "epoch": 0.041448331344868826, "grad_norm": 0.72265625, "learning_rate": 2.4861840287372203e-06, "loss": 0.9792176055908203, "step": 3600 }, { "epoch": 0.04375101641958376, "grad_norm": 0.83984375, "learning_rate": 2.624343741365018e-06, "loss": 0.9834017944335938, "step": 3800 }, { "epoch": 0.046053701494298695, "grad_norm": 0.66015625, "learning_rate": 2.7625034539928157e-06, "loss": 1.0003073883056641, "step": 4000 }, { "epoch": 0.04835638656901363, "grad_norm": 0.7890625, "learning_rate": 2.9006631666206134e-06, "loss": 0.9826235961914063, "step": 4200 }, { "epoch": 0.050659071643728563, "grad_norm": 0.51171875, "learning_rate": 3.038822879248411e-06, "loss": 0.9803595733642578, "step": 4400 }, { "epoch": 0.0529617567184435, "grad_norm": 0.8359375, "learning_rate": 3.1769825918762093e-06, "loss": 0.9817047119140625, "step": 4600 }, { "epoch": 0.05526444179315843, "grad_norm": 1.2890625, "learning_rate": 3.315142304504007e-06, "loss": 0.9922354125976562, "step": 4800 }, { "epoch": 0.05756712686787337, "grad_norm": 0.57421875, "learning_rate": 3.4533020171318043e-06, "loss": 0.9926442718505859, "step": 5000 }, { "epoch": 0.0598698119425883, "grad_norm": 0.482421875, "learning_rate": 3.591461729759602e-06, "loss": 0.9734688568115234, "step": 5200 }, { "epoch": 0.06217249701730324, "grad_norm": 1.8984375, "learning_rate": 3.7296214423873997e-06, "loss": 0.983599624633789, "step": 5400 }, { "epoch": 0.06447518209201818, "grad_norm": 0.59765625, "learning_rate": 3.8677811550151974e-06, "loss": 0.9984064483642578, "step": 5600 }, { "epoch": 0.0667778671667331, "grad_norm": 0.5703125, "learning_rate": 4.005940867642995e-06, "loss": 0.9748104858398438, "step": 5800 }, { "epoch": 0.06908055224144805, "grad_norm": 1.5546875, "learning_rate": 4.144100580270793e-06, "loss": 1.0019890594482421, "step": 6000 }, { "epoch": 0.07138323731616297, "grad_norm": 0.53515625, "learning_rate": 4.282260292898591e-06, "loss": 0.978772964477539, "step": 6200 }, { "epoch": 0.07368592239087791, "grad_norm": 0.490234375, "learning_rate": 4.420420005526388e-06, "loss": 0.9969493103027344, "step": 6400 }, { "epoch": 0.07598860746559284, "grad_norm": 0.7578125, "learning_rate": 4.5585797181541864e-06, "loss": 0.9867162322998047, "step": 6600 }, { "epoch": 0.07829129254030778, "grad_norm": 0.75390625, "learning_rate": 4.696739430781984e-06, "loss": 0.9982801818847656, "step": 6800 }, { "epoch": 0.08059397761502271, "grad_norm": 0.81640625, "learning_rate": 4.834899143409782e-06, "loss": 0.9909251403808593, "step": 7000 }, { "epoch": 0.08289666268973765, "grad_norm": 0.80078125, "learning_rate": 4.97305885603758e-06, "loss": 1.0040445709228516, "step": 7200 }, { "epoch": 0.0851993477644526, "grad_norm": 0.50390625, "learning_rate": 5.111218568665377e-06, "loss": 1.0038322448730468, "step": 7400 }, { "epoch": 0.08750203283916752, "grad_norm": 0.68359375, "learning_rate": 5.2493782812931754e-06, "loss": 0.9839054107666015, "step": 7600 }, { "epoch": 0.08980471791388246, "grad_norm": 0.6640625, "learning_rate": 5.3875379939209736e-06, "loss": 0.9923789978027344, "step": 7800 }, { "epoch": 0.09210740298859739, "grad_norm": 0.61328125, "learning_rate": 5.52569770654877e-06, "loss": 0.9952265930175781, "step": 8000 }, { "epoch": 0.09441008806331233, "grad_norm": 0.73828125, "learning_rate": 5.663857419176568e-06, "loss": 0.9856996154785156, "step": 8200 }, { "epoch": 0.09671277313802726, "grad_norm": 0.66015625, "learning_rate": 5.8020171318043654e-06, "loss": 1.0003697204589843, "step": 8400 }, { "epoch": 0.0990154582127422, "grad_norm": 0.58203125, "learning_rate": 5.940176844432164e-06, "loss": 0.9982233428955078, "step": 8600 }, { "epoch": 0.10131814328745713, "grad_norm": 0.9453125, "learning_rate": 6.078336557059962e-06, "loss": 0.9870623016357422, "step": 8800 }, { "epoch": 0.10362082836217207, "grad_norm": 0.57421875, "learning_rate": 6.216496269687759e-06, "loss": 1.0076547241210938, "step": 9000 }, { "epoch": 0.105923513436887, "grad_norm": 0.71484375, "learning_rate": 6.354655982315557e-06, "loss": 1.013364028930664, "step": 9200 }, { "epoch": 0.10822619851160194, "grad_norm": 0.53515625, "learning_rate": 6.4928156949433544e-06, "loss": 0.9872899627685547, "step": 9400 }, { "epoch": 0.11052888358631686, "grad_norm": 0.4921875, "learning_rate": 6.630975407571153e-06, "loss": 0.9925249481201172, "step": 9600 }, { "epoch": 0.1128315686610318, "grad_norm": 0.9296875, "learning_rate": 6.769135120198951e-06, "loss": 0.9940272521972656, "step": 9800 }, { "epoch": 0.11513425373574673, "grad_norm": 0.640625, "learning_rate": 6.907294832826748e-06, "loss": 0.9853199005126954, "step": 10000 }, { "epoch": 0.11743693881046167, "grad_norm": 0.79296875, "learning_rate": 7.045454545454546e-06, "loss": 0.9513562774658203, "step": 10200 }, { "epoch": 0.1197396238851766, "grad_norm": 0.83984375, "learning_rate": 7.183614258082343e-06, "loss": 0.9889139556884765, "step": 10400 }, { "epoch": 0.12204230895989154, "grad_norm": 2.375, "learning_rate": 7.321773970710141e-06, "loss": 0.9937071990966797, "step": 10600 }, { "epoch": 0.12434499403460648, "grad_norm": 0.70703125, "learning_rate": 7.459933683337939e-06, "loss": 0.9788626098632812, "step": 10800 }, { "epoch": 0.12664767910932143, "grad_norm": 1.1953125, "learning_rate": 7.598093395965737e-06, "loss": 0.9843457794189453, "step": 11000 }, { "epoch": 0.12895036418403635, "grad_norm": 0.66796875, "learning_rate": 7.736253108593534e-06, "loss": 0.9941126251220703, "step": 11200 }, { "epoch": 0.13125304925875128, "grad_norm": 0.57421875, "learning_rate": 7.874412821221332e-06, "loss": 0.9951610565185547, "step": 11400 }, { "epoch": 0.1335557343334662, "grad_norm": 1.2890625, "learning_rate": 8.012572533849129e-06, "loss": 0.9955122375488281, "step": 11600 }, { "epoch": 0.13585841940818116, "grad_norm": 0.7265625, "learning_rate": 8.150732246476927e-06, "loss": 1.0030738830566406, "step": 11800 }, { "epoch": 0.1381611044828961, "grad_norm": 1.9453125, "learning_rate": 8.288891959104725e-06, "loss": 0.9774797058105469, "step": 12000 }, { "epoch": 0.14046378955761102, "grad_norm": 0.68359375, "learning_rate": 8.427051671732523e-06, "loss": 0.9933738708496094, "step": 12200 }, { "epoch": 0.14276647463232595, "grad_norm": 1.5234375, "learning_rate": 8.56521138436032e-06, "loss": 0.9964907073974609, "step": 12400 }, { "epoch": 0.1450691597070409, "grad_norm": 0.69921875, "learning_rate": 8.703371096988118e-06, "loss": 1.0063589477539063, "step": 12600 }, { "epoch": 0.14737184478175583, "grad_norm": 1.0703125, "learning_rate": 8.841530809615916e-06, "loss": 0.9975699615478516, "step": 12800 }, { "epoch": 0.14967452985647076, "grad_norm": 0.6953125, "learning_rate": 8.979690522243714e-06, "loss": 1.0073341369628905, "step": 13000 }, { "epoch": 0.15197721493118568, "grad_norm": 1.0859375, "learning_rate": 9.117850234871512e-06, "loss": 0.9989344024658203, "step": 13200 }, { "epoch": 0.15427990000590064, "grad_norm": 0.55859375, "learning_rate": 9.256009947499309e-06, "loss": 0.9917288970947266, "step": 13400 }, { "epoch": 0.15658258508061557, "grad_norm": 0.6796875, "learning_rate": 9.394169660127107e-06, "loss": 0.9956332397460937, "step": 13600 }, { "epoch": 0.1588852701553305, "grad_norm": 0.7578125, "learning_rate": 9.532329372754905e-06, "loss": 0.993236312866211, "step": 13800 }, { "epoch": 0.16118795523004542, "grad_norm": 0.458984375, "learning_rate": 9.670489085382703e-06, "loss": 1.0043616485595703, "step": 14000 }, { "epoch": 0.16349064030476038, "grad_norm": 0.53125, "learning_rate": 9.808648798010501e-06, "loss": 0.9785184478759765, "step": 14200 }, { "epoch": 0.1657933253794753, "grad_norm": 0.388671875, "learning_rate": 9.946808510638298e-06, "loss": 1.0018584442138672, "step": 14400 }, { "epoch": 0.16809601045419023, "grad_norm": 0.99609375, "learning_rate": 1.0084968223266096e-05, "loss": 0.9883576202392578, "step": 14600 }, { "epoch": 0.1703986955289052, "grad_norm": 0.59375, "learning_rate": 1.0223127935893894e-05, "loss": 0.9930864715576172, "step": 14800 }, { "epoch": 0.1727013806036201, "grad_norm": 0.73046875, "learning_rate": 1.0361287648521692e-05, "loss": 0.9924915313720704, "step": 15000 }, { "epoch": 0.17500406567833504, "grad_norm": 0.69140625, "learning_rate": 1.049944736114949e-05, "loss": 0.9670263671875, "step": 15200 }, { "epoch": 0.17730675075304997, "grad_norm": 0.56640625, "learning_rate": 1.0637607073777287e-05, "loss": 0.9942636108398437, "step": 15400 }, { "epoch": 0.17960943582776492, "grad_norm": 2.078125, "learning_rate": 1.0775766786405085e-05, "loss": 1.0009183502197265, "step": 15600 }, { "epoch": 0.18191212090247985, "grad_norm": 0.67578125, "learning_rate": 1.0913926499032883e-05, "loss": 0.9625146484375, "step": 15800 }, { "epoch": 0.18421480597719478, "grad_norm": 0.75390625, "learning_rate": 1.1052086211660681e-05, "loss": 0.9849910736083984, "step": 16000 }, { "epoch": 0.1865174910519097, "grad_norm": 0.466796875, "learning_rate": 1.119024592428848e-05, "loss": 1.0009237670898437, "step": 16200 }, { "epoch": 0.18882017612662466, "grad_norm": 0.5234375, "learning_rate": 1.1328405636916274e-05, "loss": 0.980335464477539, "step": 16400 }, { "epoch": 0.1911228612013396, "grad_norm": 0.6875, "learning_rate": 1.1466565349544072e-05, "loss": 1.0018857574462892, "step": 16600 }, { "epoch": 0.19342554627605452, "grad_norm": 0.5234375, "learning_rate": 1.160472506217187e-05, "loss": 1.0179067993164062, "step": 16800 }, { "epoch": 0.19572823135076944, "grad_norm": 0.984375, "learning_rate": 1.1742884774799668e-05, "loss": 0.9830726623535156, "step": 17000 }, { "epoch": 0.1980309164254844, "grad_norm": 0.73828125, "learning_rate": 1.1881044487427467e-05, "loss": 1.0245218658447266, "step": 17200 }, { "epoch": 0.20033360150019933, "grad_norm": 0.58203125, "learning_rate": 1.2019204200055263e-05, "loss": 0.9935623168945312, "step": 17400 }, { "epoch": 0.20263628657491425, "grad_norm": 0.5625, "learning_rate": 1.2157363912683061e-05, "loss": 0.9736779022216797, "step": 17600 }, { "epoch": 0.2049389716496292, "grad_norm": 0.53515625, "learning_rate": 1.229552362531086e-05, "loss": 0.9839263153076172, "step": 17800 }, { "epoch": 0.20724165672434414, "grad_norm": 1.1171875, "learning_rate": 1.2433683337938657e-05, "loss": 0.9675028228759766, "step": 18000 }, { "epoch": 0.20954434179905906, "grad_norm": 0.8984375, "learning_rate": 1.2571843050566456e-05, "loss": 0.9875794982910157, "step": 18200 }, { "epoch": 0.211847026873774, "grad_norm": 0.7265625, "learning_rate": 1.2710002763194252e-05, "loss": 0.9895236968994141, "step": 18400 }, { "epoch": 0.21414971194848895, "grad_norm": 0.5859375, "learning_rate": 1.284816247582205e-05, "loss": 0.9853239440917969, "step": 18600 }, { "epoch": 0.21645239702320387, "grad_norm": 0.79296875, "learning_rate": 1.2986322188449848e-05, "loss": 0.974911880493164, "step": 18800 }, { "epoch": 0.2187550820979188, "grad_norm": 0.79296875, "learning_rate": 1.3124481901077646e-05, "loss": 0.9828662109375, "step": 19000 }, { "epoch": 0.22105776717263373, "grad_norm": 0.71484375, "learning_rate": 1.3262641613705445e-05, "loss": 0.9706605529785156, "step": 19200 }, { "epoch": 0.22336045224734868, "grad_norm": 0.4140625, "learning_rate": 1.3400801326333241e-05, "loss": 0.9889375305175782, "step": 19400 }, { "epoch": 0.2256631373220636, "grad_norm": 0.7265625, "learning_rate": 1.3538961038961039e-05, "loss": 0.9776881408691406, "step": 19600 }, { "epoch": 0.22796582239677854, "grad_norm": 1.140625, "learning_rate": 1.3677120751588837e-05, "loss": 0.9969490814208984, "step": 19800 }, { "epoch": 0.23026850747149347, "grad_norm": 0.439453125, "learning_rate": 1.3815280464216635e-05, "loss": 0.9805326080322265, "step": 20000 }, { "epoch": 0.23257119254620842, "grad_norm": 0.6796875, "learning_rate": 1.3953440176844434e-05, "loss": 0.9756855773925781, "step": 20200 }, { "epoch": 0.23487387762092335, "grad_norm": 0.63671875, "learning_rate": 1.4091599889472232e-05, "loss": 0.9778380584716797, "step": 20400 }, { "epoch": 0.23717656269563828, "grad_norm": 1.3125, "learning_rate": 1.4229759602100028e-05, "loss": 0.9680982208251954, "step": 20600 }, { "epoch": 0.2394792477703532, "grad_norm": 0.60546875, "learning_rate": 1.4367919314727826e-05, "loss": 1.0011354827880858, "step": 20800 }, { "epoch": 0.24178193284506816, "grad_norm": 0.62890625, "learning_rate": 1.4506079027355623e-05, "loss": 0.982271499633789, "step": 21000 }, { "epoch": 0.2440846179197831, "grad_norm": 0.59765625, "learning_rate": 1.4644238739983421e-05, "loss": 0.978791732788086, "step": 21200 }, { "epoch": 0.24638730299449801, "grad_norm": 0.796875, "learning_rate": 1.4782398452611219e-05, "loss": 0.9688619995117187, "step": 21400 }, { "epoch": 0.24868998806921297, "grad_norm": 0.625, "learning_rate": 1.4920558165239015e-05, "loss": 0.9980213928222657, "step": 21600 }, { "epoch": 0.25099267314392787, "grad_norm": 0.89453125, "learning_rate": 1.5058717877866815e-05, "loss": 1.0045819854736329, "step": 21800 }, { "epoch": 0.25329535821864285, "grad_norm": 0.8984375, "learning_rate": 1.5196877590494613e-05, "loss": 0.9890023040771484, "step": 22000 }, { "epoch": 0.2555980432933578, "grad_norm": 0.9140625, "learning_rate": 1.533503730312241e-05, "loss": 0.9958658599853516, "step": 22200 }, { "epoch": 0.2579007283680727, "grad_norm": 0.66015625, "learning_rate": 1.547319701575021e-05, "loss": 1.0080494689941406, "step": 22400 }, { "epoch": 0.26020341344278763, "grad_norm": 0.671875, "learning_rate": 1.5611356728378008e-05, "loss": 0.974377670288086, "step": 22600 }, { "epoch": 0.26250609851750256, "grad_norm": 0.62890625, "learning_rate": 1.5749516441005806e-05, "loss": 0.9929348754882813, "step": 22800 }, { "epoch": 0.2648087835922175, "grad_norm": 0.64453125, "learning_rate": 1.58876761536336e-05, "loss": 0.9754251098632812, "step": 23000 }, { "epoch": 0.2671114686669324, "grad_norm": 0.60546875, "learning_rate": 1.60258358662614e-05, "loss": 0.9828868103027344, "step": 23200 }, { "epoch": 0.26941415374164734, "grad_norm": 0.69921875, "learning_rate": 1.6163995578889194e-05, "loss": 0.9940708923339844, "step": 23400 }, { "epoch": 0.2717168388163623, "grad_norm": 0.52734375, "learning_rate": 1.6302155291516992e-05, "loss": 0.996038818359375, "step": 23600 }, { "epoch": 0.27401952389107725, "grad_norm": 0.796875, "learning_rate": 1.644031500414479e-05, "loss": 0.9999778747558594, "step": 23800 }, { "epoch": 0.2763222089657922, "grad_norm": 0.95703125, "learning_rate": 1.6578474716772588e-05, "loss": 0.9920552825927734, "step": 24000 }, { "epoch": 0.2786248940405071, "grad_norm": 0.67578125, "learning_rate": 1.6716634429400386e-05, "loss": 0.9706204223632813, "step": 24200 }, { "epoch": 0.28092757911522204, "grad_norm": 0.64453125, "learning_rate": 1.6854794142028184e-05, "loss": 0.9838566589355469, "step": 24400 }, { "epoch": 0.28323026418993696, "grad_norm": 0.6015625, "learning_rate": 1.6992953854655982e-05, "loss": 0.9927280426025391, "step": 24600 }, { "epoch": 0.2855329492646519, "grad_norm": 0.65234375, "learning_rate": 1.713111356728378e-05, "loss": 0.9818917083740234, "step": 24800 }, { "epoch": 0.2878356343393669, "grad_norm": 0.59375, "learning_rate": 1.726927327991158e-05, "loss": 1.0006220245361328, "step": 25000 }, { "epoch": 0.2901383194140818, "grad_norm": 0.55859375, "learning_rate": 1.7407432992539373e-05, "loss": 0.9794861602783204, "step": 25200 }, { "epoch": 0.29244100448879673, "grad_norm": 0.6953125, "learning_rate": 1.754559270516717e-05, "loss": 1.0012014770507813, "step": 25400 }, { "epoch": 0.29474368956351166, "grad_norm": 0.76953125, "learning_rate": 1.768375241779497e-05, "loss": 0.9826255035400391, "step": 25600 }, { "epoch": 0.2970463746382266, "grad_norm": 0.640625, "learning_rate": 1.7821912130422768e-05, "loss": 0.9798987579345703, "step": 25800 }, { "epoch": 0.2993490597129415, "grad_norm": 0.92578125, "learning_rate": 1.7960071843050566e-05, "loss": 0.9695772552490234, "step": 26000 }, { "epoch": 0.30165174478765644, "grad_norm": 2.25, "learning_rate": 1.8098231555678364e-05, "loss": 0.9748085784912109, "step": 26200 }, { "epoch": 0.30395442986237137, "grad_norm": 0.78125, "learning_rate": 1.8236391268306162e-05, "loss": 0.9792256927490235, "step": 26400 }, { "epoch": 0.30625711493708635, "grad_norm": 0.5546875, "learning_rate": 1.837455098093396e-05, "loss": 0.9950776672363282, "step": 26600 }, { "epoch": 0.3085598000118013, "grad_norm": 0.7265625, "learning_rate": 1.851271069356176e-05, "loss": 0.9882295989990234, "step": 26800 }, { "epoch": 0.3108624850865162, "grad_norm": 0.70703125, "learning_rate": 1.8650870406189557e-05, "loss": 0.9964749908447266, "step": 27000 }, { "epoch": 0.31316517016123113, "grad_norm": 0.64453125, "learning_rate": 1.878903011881735e-05, "loss": 0.9571038818359375, "step": 27200 }, { "epoch": 0.31546785523594606, "grad_norm": 0.466796875, "learning_rate": 1.892718983144515e-05, "loss": 0.9926722717285156, "step": 27400 }, { "epoch": 0.317770540310661, "grad_norm": 1.03125, "learning_rate": 1.9065349544072948e-05, "loss": 1.017679443359375, "step": 27600 }, { "epoch": 0.3200732253853759, "grad_norm": 0.61328125, "learning_rate": 1.9203509256700746e-05, "loss": 0.9835760498046875, "step": 27800 }, { "epoch": 0.32237591046009084, "grad_norm": 0.86328125, "learning_rate": 1.9341668969328544e-05, "loss": 1.0087098693847656, "step": 28000 }, { "epoch": 0.3246785955348058, "grad_norm": 0.64453125, "learning_rate": 1.9479828681956342e-05, "loss": 0.9972708892822265, "step": 28200 }, { "epoch": 0.32698128060952075, "grad_norm": 0.640625, "learning_rate": 1.961798839458414e-05, "loss": 1.008561553955078, "step": 28400 }, { "epoch": 0.3292839656842357, "grad_norm": 0.9453125, "learning_rate": 1.975614810721194e-05, "loss": 0.9927769470214843, "step": 28600 }, { "epoch": 0.3315866507589506, "grad_norm": 2.765625, "learning_rate": 1.9894307819839737e-05, "loss": 0.9703852844238281, "step": 28800 }, { "epoch": 0.33388933583366553, "grad_norm": 0.84765625, "learning_rate": 2.0032467532467535e-05, "loss": 0.9893107604980469, "step": 29000 }, { "epoch": 0.33619202090838046, "grad_norm": 0.81640625, "learning_rate": 2.017062724509533e-05, "loss": 1.0032604217529297, "step": 29200 }, { "epoch": 0.3384947059830954, "grad_norm": 0.65234375, "learning_rate": 2.0308786957723128e-05, "loss": 0.9759930419921875, "step": 29400 }, { "epoch": 0.3407973910578104, "grad_norm": 0.75, "learning_rate": 2.0446946670350926e-05, "loss": 0.9818559265136719, "step": 29600 }, { "epoch": 0.3431000761325253, "grad_norm": 1.046875, "learning_rate": 2.0585106382978724e-05, "loss": 0.9869992065429688, "step": 29800 }, { "epoch": 0.3454027612072402, "grad_norm": 0.62109375, "learning_rate": 2.0723266095606522e-05, "loss": 1.0209011077880858, "step": 30000 }, { "epoch": 0.34770544628195516, "grad_norm": 0.73828125, "learning_rate": 2.086142580823432e-05, "loss": 0.9973705291748047, "step": 30200 }, { "epoch": 0.3500081313566701, "grad_norm": 0.76171875, "learning_rate": 2.0999585520862118e-05, "loss": 0.9845616149902344, "step": 30400 }, { "epoch": 0.352310816431385, "grad_norm": 0.6328125, "learning_rate": 2.1137745233489916e-05, "loss": 0.9949858093261719, "step": 30600 }, { "epoch": 0.35461350150609994, "grad_norm": 0.96484375, "learning_rate": 2.1275904946117715e-05, "loss": 1.0123253631591798, "step": 30800 }, { "epoch": 0.35691618658081486, "grad_norm": 0.765625, "learning_rate": 2.1414064658745513e-05, "loss": 0.9973126220703125, "step": 31000 }, { "epoch": 0.35921887165552985, "grad_norm": 0.5390625, "learning_rate": 2.155222437137331e-05, "loss": 1.0002081298828125, "step": 31200 }, { "epoch": 0.3615215567302448, "grad_norm": 1.46875, "learning_rate": 2.1690384084001106e-05, "loss": 1.0208023071289063, "step": 31400 }, { "epoch": 0.3638242418049597, "grad_norm": 0.56640625, "learning_rate": 2.1828543796628904e-05, "loss": 0.994631118774414, "step": 31600 }, { "epoch": 0.36612692687967463, "grad_norm": 0.66015625, "learning_rate": 2.1966703509256702e-05, "loss": 1.0063703918457032, "step": 31800 }, { "epoch": 0.36842961195438956, "grad_norm": 0.58984375, "learning_rate": 2.21048632218845e-05, "loss": 0.9737712097167969, "step": 32000 }, { "epoch": 0.3707322970291045, "grad_norm": 0.48828125, "learning_rate": 2.2243022934512298e-05, "loss": 0.9741205596923828, "step": 32200 }, { "epoch": 0.3730349821038194, "grad_norm": 0.8828125, "learning_rate": 2.2381182647140096e-05, "loss": 0.9894085693359375, "step": 32400 }, { "epoch": 0.3753376671785344, "grad_norm": 0.466796875, "learning_rate": 2.2519342359767894e-05, "loss": 0.9812338256835937, "step": 32600 }, { "epoch": 0.3776403522532493, "grad_norm": 0.4765625, "learning_rate": 2.2657502072395693e-05, "loss": 0.9896620178222656, "step": 32800 }, { "epoch": 0.37994303732796425, "grad_norm": 0.494140625, "learning_rate": 2.2795661785023487e-05, "loss": 1.001156997680664, "step": 33000 }, { "epoch": 0.3822457224026792, "grad_norm": 0.58984375, "learning_rate": 2.2933821497651285e-05, "loss": 0.9897576141357421, "step": 33200 }, { "epoch": 0.3845484074773941, "grad_norm": 0.578125, "learning_rate": 2.307198121027908e-05, "loss": 0.9884554290771485, "step": 33400 }, { "epoch": 0.38685109255210903, "grad_norm": 0.515625, "learning_rate": 2.3210140922906878e-05, "loss": 0.9887247467041016, "step": 33600 }, { "epoch": 0.38915377762682396, "grad_norm": 0.5859375, "learning_rate": 2.3348300635534676e-05, "loss": 1.0124942779541015, "step": 33800 }, { "epoch": 0.3914564627015389, "grad_norm": 0.38671875, "learning_rate": 2.3486460348162475e-05, "loss": 0.9673490905761719, "step": 34000 }, { "epoch": 0.39375914777625387, "grad_norm": 0.474609375, "learning_rate": 2.3624620060790273e-05, "loss": 0.9783273315429688, "step": 34200 }, { "epoch": 0.3960618328509688, "grad_norm": 0.625, "learning_rate": 2.376277977341807e-05, "loss": 1.0001426696777345, "step": 34400 }, { "epoch": 0.3983645179256837, "grad_norm": 0.8359375, "learning_rate": 2.390093948604587e-05, "loss": 0.9712574768066407, "step": 34600 }, { "epoch": 0.40066720300039865, "grad_norm": 0.62109375, "learning_rate": 2.4039099198673667e-05, "loss": 0.9945822143554688, "step": 34800 }, { "epoch": 0.4029698880751136, "grad_norm": 0.70703125, "learning_rate": 2.4177258911301465e-05, "loss": 0.9821370697021484, "step": 35000 }, { "epoch": 0.4052725731498285, "grad_norm": 0.5859375, "learning_rate": 2.4315418623929263e-05, "loss": 0.9928865814208985, "step": 35200 }, { "epoch": 0.40757525822454344, "grad_norm": 0.62109375, "learning_rate": 2.4453578336557058e-05, "loss": 0.9809159851074218, "step": 35400 }, { "epoch": 0.4098779432992584, "grad_norm": 0.62109375, "learning_rate": 2.4591738049184856e-05, "loss": 0.9863732147216797, "step": 35600 }, { "epoch": 0.41218062837397335, "grad_norm": 0.5859375, "learning_rate": 2.4729897761812654e-05, "loss": 1.0015038299560546, "step": 35800 }, { "epoch": 0.4144833134486883, "grad_norm": 0.67578125, "learning_rate": 2.4868057474440453e-05, "loss": 0.9992890167236328, "step": 36000 }, { "epoch": 0.4167859985234032, "grad_norm": 1.0703125, "learning_rate": 2.500621718706825e-05, "loss": 0.9928932952880859, "step": 36200 }, { "epoch": 0.41908868359811813, "grad_norm": 0.62109375, "learning_rate": 2.514437689969605e-05, "loss": 0.9791075897216797, "step": 36400 }, { "epoch": 0.42139136867283306, "grad_norm": 0.470703125, "learning_rate": 2.5282536612323847e-05, "loss": 0.9951918792724609, "step": 36600 }, { "epoch": 0.423694053747548, "grad_norm": 0.70703125, "learning_rate": 2.5420696324951645e-05, "loss": 0.9908084869384766, "step": 36800 }, { "epoch": 0.4259967388222629, "grad_norm": 0.890625, "learning_rate": 2.5558856037579443e-05, "loss": 0.979951171875, "step": 37000 }, { "epoch": 0.4282994238969779, "grad_norm": 0.70703125, "learning_rate": 2.569701575020724e-05, "loss": 0.9870540618896484, "step": 37200 }, { "epoch": 0.4306021089716928, "grad_norm": 0.6875, "learning_rate": 2.583517546283504e-05, "loss": 0.9819743347167968, "step": 37400 }, { "epoch": 0.43290479404640775, "grad_norm": 0.58203125, "learning_rate": 2.5973335175462834e-05, "loss": 0.9861982727050781, "step": 37600 }, { "epoch": 0.4352074791211227, "grad_norm": 0.515625, "learning_rate": 2.6111494888090632e-05, "loss": 0.9916728973388672, "step": 37800 }, { "epoch": 0.4375101641958376, "grad_norm": 0.51171875, "learning_rate": 2.624965460071843e-05, "loss": 0.9688997650146485, "step": 38000 }, { "epoch": 0.43981284927055253, "grad_norm": 0.70703125, "learning_rate": 2.638781431334623e-05, "loss": 0.9839357757568359, "step": 38200 }, { "epoch": 0.44211553434526746, "grad_norm": 0.64453125, "learning_rate": 2.6525974025974027e-05, "loss": 0.9878810119628906, "step": 38400 }, { "epoch": 0.44441821941998244, "grad_norm": 0.85546875, "learning_rate": 2.6664133738601825e-05, "loss": 0.9786476135253906, "step": 38600 }, { "epoch": 0.44672090449469737, "grad_norm": 0.80859375, "learning_rate": 2.6802293451229623e-05, "loss": 0.9965245056152344, "step": 38800 }, { "epoch": 0.4490235895694123, "grad_norm": 0.93359375, "learning_rate": 2.694045316385742e-05, "loss": 0.9912705993652344, "step": 39000 }, { "epoch": 0.4513262746441272, "grad_norm": 0.63671875, "learning_rate": 2.707861287648522e-05, "loss": 0.986620864868164, "step": 39200 }, { "epoch": 0.45362895971884215, "grad_norm": 0.75390625, "learning_rate": 2.7216772589113018e-05, "loss": 0.9704518127441406, "step": 39400 }, { "epoch": 0.4559316447935571, "grad_norm": 0.546875, "learning_rate": 2.7354932301740812e-05, "loss": 0.9987767791748047, "step": 39600 }, { "epoch": 0.458234329868272, "grad_norm": 0.82421875, "learning_rate": 2.749309201436861e-05, "loss": 1.0047703552246094, "step": 39800 }, { "epoch": 0.46053701494298693, "grad_norm": 0.60546875, "learning_rate": 2.763125172699641e-05, "loss": 0.9702092742919922, "step": 40000 }, { "epoch": 0.4628397000177019, "grad_norm": 0.99609375, "learning_rate": 2.7769411439624207e-05, "loss": 0.9662624359130859, "step": 40200 }, { "epoch": 0.46514238509241684, "grad_norm": 0.55859375, "learning_rate": 2.7907571152252005e-05, "loss": 0.9837642669677734, "step": 40400 }, { "epoch": 0.46744507016713177, "grad_norm": 0.439453125, "learning_rate": 2.8045730864879803e-05, "loss": 0.9509716796875, "step": 40600 }, { "epoch": 0.4697477552418467, "grad_norm": 0.48828125, "learning_rate": 2.81838905775076e-05, "loss": 0.9896253204345703, "step": 40800 }, { "epoch": 0.4720504403165616, "grad_norm": 0.6328125, "learning_rate": 2.83220502901354e-05, "loss": 0.9683509063720703, "step": 41000 }, { "epoch": 0.47435312539127655, "grad_norm": 0.7890625, "learning_rate": 2.8460210002763197e-05, "loss": 0.9861078643798828, "step": 41200 }, { "epoch": 0.4766558104659915, "grad_norm": 0.59375, "learning_rate": 2.8598369715390995e-05, "loss": 1.0022505950927734, "step": 41400 }, { "epoch": 0.4789584955407064, "grad_norm": 0.6953125, "learning_rate": 2.873652942801879e-05, "loss": 0.9984149932861328, "step": 41600 }, { "epoch": 0.4812611806154214, "grad_norm": 0.5625, "learning_rate": 2.887468914064659e-05, "loss": 0.990358657836914, "step": 41800 }, { "epoch": 0.4835638656901363, "grad_norm": 0.84375, "learning_rate": 2.9012848853274387e-05, "loss": 0.9875827026367188, "step": 42000 }, { "epoch": 0.48586655076485125, "grad_norm": 0.64453125, "learning_rate": 2.9151008565902185e-05, "loss": 0.9853507995605468, "step": 42200 }, { "epoch": 0.4881692358395662, "grad_norm": 0.578125, "learning_rate": 2.9289168278529983e-05, "loss": 0.9948759460449219, "step": 42400 }, { "epoch": 0.4904719209142811, "grad_norm": 0.78515625, "learning_rate": 2.9427327991157778e-05, "loss": 0.9923246765136718, "step": 42600 }, { "epoch": 0.49277460598899603, "grad_norm": 0.984375, "learning_rate": 2.9565487703785576e-05, "loss": 0.9764729309082031, "step": 42800 }, { "epoch": 0.49507729106371096, "grad_norm": 0.7265625, "learning_rate": 2.9703647416413374e-05, "loss": 0.9748880004882813, "step": 43000 }, { "epoch": 0.49737997613842594, "grad_norm": 0.63671875, "learning_rate": 2.9841807129041172e-05, "loss": 1.002592544555664, "step": 43200 }, { "epoch": 0.49968266121314087, "grad_norm": 0.62109375, "learning_rate": 2.997996684166897e-05, "loss": 1.0050338745117187, "step": 43400 }, { "epoch": 0.5019853462878557, "grad_norm": 0.83984375, "learning_rate": 2.999378281293175e-05, "loss": 1.0200328826904297, "step": 43600 }, { "epoch": 0.5042880313625707, "grad_norm": 0.58203125, "learning_rate": 2.9986511249109234e-05, "loss": 0.998750228881836, "step": 43800 }, { "epoch": 0.5065907164372857, "grad_norm": 0.7109375, "learning_rate": 2.9979239685286716e-05, "loss": 0.9793384552001954, "step": 44000 }, { "epoch": 0.5088934015120006, "grad_norm": 0.6640625, "learning_rate": 2.9971968121464202e-05, "loss": 0.9925625610351563, "step": 44200 }, { "epoch": 0.5111960865867156, "grad_norm": 0.6796875, "learning_rate": 2.9964696557641688e-05, "loss": 0.9737508392333984, "step": 44400 }, { "epoch": 0.5134987716614304, "grad_norm": 0.64453125, "learning_rate": 2.9957424993819174e-05, "loss": 0.987296142578125, "step": 44600 }, { "epoch": 0.5158014567361454, "grad_norm": 0.515625, "learning_rate": 2.9950153429996657e-05, "loss": 0.9984680938720704, "step": 44800 }, { "epoch": 0.5181041418108603, "grad_norm": 0.5234375, "learning_rate": 2.994288186617414e-05, "loss": 0.9554759979248046, "step": 45000 }, { "epoch": 0.5204068268855753, "grad_norm": 0.828125, "learning_rate": 2.9935610302351625e-05, "loss": 1.0087938690185547, "step": 45200 }, { "epoch": 0.5227095119602901, "grad_norm": 0.58203125, "learning_rate": 2.9928338738529108e-05, "loss": 0.9874359130859375, "step": 45400 }, { "epoch": 0.5250121970350051, "grad_norm": 0.58203125, "learning_rate": 2.9921067174706593e-05, "loss": 0.9804747009277344, "step": 45600 }, { "epoch": 0.5273148821097201, "grad_norm": 1.2734375, "learning_rate": 2.991379561088408e-05, "loss": 0.9834337615966797, "step": 45800 }, { "epoch": 0.529617567184435, "grad_norm": 0.65625, "learning_rate": 2.9906524047061562e-05, "loss": 0.9804586791992187, "step": 46000 }, { "epoch": 0.53192025225915, "grad_norm": 0.453125, "learning_rate": 2.9899252483239044e-05, "loss": 0.9947004699707032, "step": 46200 }, { "epoch": 0.5342229373338648, "grad_norm": 0.734375, "learning_rate": 2.989198091941653e-05, "loss": 0.9872706604003906, "step": 46400 }, { "epoch": 0.5365256224085798, "grad_norm": 0.84765625, "learning_rate": 2.9884709355594013e-05, "loss": 0.9967252349853516, "step": 46600 }, { "epoch": 0.5388283074832947, "grad_norm": 0.62890625, "learning_rate": 2.98774377917715e-05, "loss": 0.9788603210449218, "step": 46800 }, { "epoch": 0.5411309925580097, "grad_norm": 0.77734375, "learning_rate": 2.9870166227948985e-05, "loss": 1.0005274963378907, "step": 47000 }, { "epoch": 0.5434336776327247, "grad_norm": 0.7421875, "learning_rate": 2.9862894664126467e-05, "loss": 0.9859010314941407, "step": 47200 }, { "epoch": 0.5457363627074395, "grad_norm": 0.7578125, "learning_rate": 2.9855623100303953e-05, "loss": 0.997774429321289, "step": 47400 }, { "epoch": 0.5480390477821545, "grad_norm": 0.41796875, "learning_rate": 2.9848351536481436e-05, "loss": 0.9882254028320312, "step": 47600 }, { "epoch": 0.5503417328568694, "grad_norm": 0.640625, "learning_rate": 2.984107997265892e-05, "loss": 0.9773269653320312, "step": 47800 }, { "epoch": 0.5526444179315844, "grad_norm": 0.90625, "learning_rate": 2.9833808408836404e-05, "loss": 0.9920169830322265, "step": 48000 }, { "epoch": 0.5549471030062992, "grad_norm": 0.82421875, "learning_rate": 2.982653684501389e-05, "loss": 0.9774995422363282, "step": 48200 }, { "epoch": 0.5572497880810142, "grad_norm": 0.6015625, "learning_rate": 2.9819265281191376e-05, "loss": 0.9765099334716797, "step": 48400 }, { "epoch": 0.5595524731557292, "grad_norm": 0.51171875, "learning_rate": 2.981199371736886e-05, "loss": 0.9840308380126953, "step": 48600 }, { "epoch": 0.5618551582304441, "grad_norm": 0.66015625, "learning_rate": 2.980472215354634e-05, "loss": 1.0011785125732422, "step": 48800 }, { "epoch": 0.5641578433051591, "grad_norm": 0.71875, "learning_rate": 2.9797450589723827e-05, "loss": 0.9817601013183593, "step": 49000 }, { "epoch": 0.5664605283798739, "grad_norm": 0.6484375, "learning_rate": 2.979017902590131e-05, "loss": 1.0076644134521484, "step": 49200 }, { "epoch": 0.5687632134545889, "grad_norm": 0.8203125, "learning_rate": 2.9782907462078795e-05, "loss": 0.9878813171386719, "step": 49400 }, { "epoch": 0.5710658985293038, "grad_norm": 0.7265625, "learning_rate": 2.977563589825628e-05, "loss": 0.9952576446533203, "step": 49600 }, { "epoch": 0.5733685836040188, "grad_norm": 0.5859375, "learning_rate": 2.9768364334433764e-05, "loss": 0.9908863067626953, "step": 49800 }, { "epoch": 0.5756712686787337, "grad_norm": 1.359375, "learning_rate": 2.9761092770611246e-05, "loss": 0.9856517791748047, "step": 50000 }, { "epoch": 0.5779739537534486, "grad_norm": 0.345703125, "learning_rate": 2.9753821206788732e-05, "loss": 1.0019198608398439, "step": 50200 }, { "epoch": 0.5802766388281636, "grad_norm": 0.765625, "learning_rate": 2.9746549642966218e-05, "loss": 0.9981635284423828, "step": 50400 }, { "epoch": 0.5825793239028785, "grad_norm": 0.6015625, "learning_rate": 2.97392780791437e-05, "loss": 1.0029985046386718, "step": 50600 }, { "epoch": 0.5848820089775935, "grad_norm": 0.462890625, "learning_rate": 2.9732006515321187e-05, "loss": 1.0053339385986328, "step": 50800 }, { "epoch": 0.5871846940523083, "grad_norm": 0.6328125, "learning_rate": 2.9724734951498672e-05, "loss": 0.9716258239746094, "step": 51000 }, { "epoch": 0.5894873791270233, "grad_norm": 1.6953125, "learning_rate": 2.9717463387676155e-05, "loss": 0.9866657257080078, "step": 51200 }, { "epoch": 0.5917900642017382, "grad_norm": 0.83984375, "learning_rate": 2.9710191823853638e-05, "loss": 0.9880976104736328, "step": 51400 }, { "epoch": 0.5940927492764532, "grad_norm": 0.7734375, "learning_rate": 2.9702920260031123e-05, "loss": 0.9747943878173828, "step": 51600 }, { "epoch": 0.5963954343511682, "grad_norm": 0.79296875, "learning_rate": 2.9695648696208606e-05, "loss": 0.9976082611083984, "step": 51800 }, { "epoch": 0.598698119425883, "grad_norm": 0.50390625, "learning_rate": 2.9688377132386092e-05, "loss": 1.0007020568847655, "step": 52000 }, { "epoch": 0.601000804500598, "grad_norm": 0.6484375, "learning_rate": 2.9681105568563578e-05, "loss": 0.9923267364501953, "step": 52200 }, { "epoch": 0.6033034895753129, "grad_norm": 0.494140625, "learning_rate": 2.967383400474106e-05, "loss": 1.0014637756347655, "step": 52400 }, { "epoch": 0.6056061746500279, "grad_norm": 0.6015625, "learning_rate": 2.9666562440918543e-05, "loss": 0.9647525024414062, "step": 52600 }, { "epoch": 0.6079088597247427, "grad_norm": 0.6796875, "learning_rate": 2.965929087709603e-05, "loss": 0.9859085083007812, "step": 52800 }, { "epoch": 0.6102115447994577, "grad_norm": 0.65234375, "learning_rate": 2.965201931327351e-05, "loss": 0.9939171600341797, "step": 53000 }, { "epoch": 0.6125142298741727, "grad_norm": 0.81640625, "learning_rate": 2.9644747749450997e-05, "loss": 0.9924463653564453, "step": 53200 }, { "epoch": 0.6148169149488876, "grad_norm": 0.91015625, "learning_rate": 2.9637476185628483e-05, "loss": 0.9631312561035156, "step": 53400 }, { "epoch": 0.6171196000236026, "grad_norm": 0.90234375, "learning_rate": 2.963020462180597e-05, "loss": 0.9812735748291016, "step": 53600 }, { "epoch": 0.6194222850983174, "grad_norm": 0.7265625, "learning_rate": 2.962293305798345e-05, "loss": 1.0052700805664063, "step": 53800 }, { "epoch": 0.6217249701730324, "grad_norm": 0.453125, "learning_rate": 2.9615661494160934e-05, "loss": 0.97032958984375, "step": 54000 }, { "epoch": 0.6240276552477473, "grad_norm": 0.98046875, "learning_rate": 2.960838993033842e-05, "loss": 1.013146286010742, "step": 54200 }, { "epoch": 0.6263303403224623, "grad_norm": 0.953125, "learning_rate": 2.9601118366515903e-05, "loss": 0.9846820831298828, "step": 54400 }, { "epoch": 0.6286330253971772, "grad_norm": 0.5625, "learning_rate": 2.959384680269339e-05, "loss": 0.9867259979248046, "step": 54600 }, { "epoch": 0.6309357104718921, "grad_norm": 0.546875, "learning_rate": 2.9586575238870874e-05, "loss": 0.9823355102539062, "step": 54800 }, { "epoch": 0.6332383955466071, "grad_norm": 0.58984375, "learning_rate": 2.9579303675048357e-05, "loss": 0.9936563873291016, "step": 55000 }, { "epoch": 0.635541080621322, "grad_norm": 0.5, "learning_rate": 2.957203211122584e-05, "loss": 0.9837480926513672, "step": 55200 }, { "epoch": 0.637843765696037, "grad_norm": 0.8828125, "learning_rate": 2.9564760547403325e-05, "loss": 0.9884334564208984, "step": 55400 }, { "epoch": 0.6401464507707518, "grad_norm": 0.5546875, "learning_rate": 2.9557488983580808e-05, "loss": 0.9931166839599609, "step": 55600 }, { "epoch": 0.6424491358454668, "grad_norm": 0.890625, "learning_rate": 2.9550217419758294e-05, "loss": 0.9690689086914063, "step": 55800 }, { "epoch": 0.6447518209201817, "grad_norm": 0.89453125, "learning_rate": 2.954294585593578e-05, "loss": 0.9920832824707031, "step": 56000 }, { "epoch": 0.6470545059948967, "grad_norm": 0.65625, "learning_rate": 2.9535674292113266e-05, "loss": 0.9990323638916015, "step": 56200 }, { "epoch": 0.6493571910696117, "grad_norm": 0.75390625, "learning_rate": 2.9528402728290745e-05, "loss": 0.9787998199462891, "step": 56400 }, { "epoch": 0.6516598761443265, "grad_norm": 0.62890625, "learning_rate": 2.952113116446823e-05, "loss": 1.0044151306152345, "step": 56600 }, { "epoch": 0.6539625612190415, "grad_norm": 0.64453125, "learning_rate": 2.9513859600645717e-05, "loss": 0.9847600555419922, "step": 56800 }, { "epoch": 0.6562652462937564, "grad_norm": 0.6015625, "learning_rate": 2.95065880368232e-05, "loss": 0.9836011505126954, "step": 57000 }, { "epoch": 0.6585679313684714, "grad_norm": 0.451171875, "learning_rate": 2.9499316473000685e-05, "loss": 0.9912583923339844, "step": 57200 }, { "epoch": 0.6608706164431862, "grad_norm": 0.7578125, "learning_rate": 2.949204490917817e-05, "loss": 0.9929079437255859, "step": 57400 }, { "epoch": 0.6631733015179012, "grad_norm": 0.99609375, "learning_rate": 2.9484773345355653e-05, "loss": 0.9952792358398438, "step": 57600 }, { "epoch": 0.6654759865926162, "grad_norm": 0.91015625, "learning_rate": 2.9477501781533136e-05, "loss": 0.9805123138427735, "step": 57800 }, { "epoch": 0.6677786716673311, "grad_norm": 0.921875, "learning_rate": 2.9470230217710622e-05, "loss": 0.989420166015625, "step": 58000 }, { "epoch": 0.670081356742046, "grad_norm": 0.734375, "learning_rate": 2.9462958653888104e-05, "loss": 0.9806766510009766, "step": 58200 }, { "epoch": 0.6723840418167609, "grad_norm": 0.46875, "learning_rate": 2.945568709006559e-05, "loss": 1.0109115600585938, "step": 58400 }, { "epoch": 0.6746867268914759, "grad_norm": 0.63671875, "learning_rate": 2.9448415526243076e-05, "loss": 0.9819956207275391, "step": 58600 }, { "epoch": 0.6769894119661908, "grad_norm": 0.5390625, "learning_rate": 2.944114396242056e-05, "loss": 0.9844336700439453, "step": 58800 }, { "epoch": 0.6792920970409058, "grad_norm": 1.1484375, "learning_rate": 2.943387239859804e-05, "loss": 0.9926036071777343, "step": 59000 }, { "epoch": 0.6815947821156207, "grad_norm": 0.86328125, "learning_rate": 2.9426600834775527e-05, "loss": 0.9849551391601562, "step": 59200 }, { "epoch": 0.6838974671903356, "grad_norm": 0.4609375, "learning_rate": 2.9419329270953013e-05, "loss": 1.0088782501220703, "step": 59400 }, { "epoch": 0.6862001522650506, "grad_norm": 0.96484375, "learning_rate": 2.9412057707130496e-05, "loss": 0.9990327453613281, "step": 59600 }, { "epoch": 0.6885028373397655, "grad_norm": 0.84765625, "learning_rate": 2.940478614330798e-05, "loss": 0.99803955078125, "step": 59800 }, { "epoch": 0.6908055224144805, "grad_norm": 0.423828125, "learning_rate": 2.9397514579485467e-05, "loss": 0.9917265319824219, "step": 60000 }, { "epoch": 0.6931082074891953, "grad_norm": 0.9609375, "learning_rate": 2.9390243015662947e-05, "loss": 0.9893582916259765, "step": 60200 }, { "epoch": 0.6954108925639103, "grad_norm": 0.54296875, "learning_rate": 2.9382971451840432e-05, "loss": 0.9903961944580079, "step": 60400 }, { "epoch": 0.6977135776386253, "grad_norm": 0.765625, "learning_rate": 2.937569988801792e-05, "loss": 0.99945556640625, "step": 60600 }, { "epoch": 0.7000162627133402, "grad_norm": 1.0625, "learning_rate": 2.93684283241954e-05, "loss": 1.0101787567138671, "step": 60800 }, { "epoch": 0.7023189477880551, "grad_norm": 1.578125, "learning_rate": 2.9361156760372887e-05, "loss": 1.004135513305664, "step": 61000 }, { "epoch": 0.70462163286277, "grad_norm": 1.3046875, "learning_rate": 2.9353885196550373e-05, "loss": 0.9818244934082031, "step": 61200 }, { "epoch": 0.706924317937485, "grad_norm": 0.57421875, "learning_rate": 2.9346613632727855e-05, "loss": 0.9904888916015625, "step": 61400 }, { "epoch": 0.7092270030121999, "grad_norm": 1.3515625, "learning_rate": 2.9339342068905338e-05, "loss": 0.966075668334961, "step": 61600 }, { "epoch": 0.7115296880869149, "grad_norm": 0.6328125, "learning_rate": 2.9332070505082824e-05, "loss": 0.981036376953125, "step": 61800 }, { "epoch": 0.7138323731616297, "grad_norm": 0.484375, "learning_rate": 2.9324798941260306e-05, "loss": 0.9956706237792968, "step": 62000 }, { "epoch": 0.7161350582363447, "grad_norm": 0.5546875, "learning_rate": 2.9317527377437792e-05, "loss": 0.9858502197265625, "step": 62200 }, { "epoch": 0.7184377433110597, "grad_norm": 0.55859375, "learning_rate": 2.9310255813615278e-05, "loss": 0.99573974609375, "step": 62400 }, { "epoch": 0.7207404283857746, "grad_norm": 0.578125, "learning_rate": 2.9302984249792764e-05, "loss": 0.9763796234130859, "step": 62600 }, { "epoch": 0.7230431134604896, "grad_norm": 1.7734375, "learning_rate": 2.9295712685970243e-05, "loss": 0.9572287750244141, "step": 62800 }, { "epoch": 0.7253457985352044, "grad_norm": 0.52734375, "learning_rate": 2.928844112214773e-05, "loss": 1.0051393127441406, "step": 63000 }, { "epoch": 0.7276484836099194, "grad_norm": 0.58984375, "learning_rate": 2.9281169558325215e-05, "loss": 0.9663025665283204, "step": 63200 }, { "epoch": 0.7299511686846343, "grad_norm": 0.6796875, "learning_rate": 2.9273897994502697e-05, "loss": 0.9826088714599609, "step": 63400 }, { "epoch": 0.7322538537593493, "grad_norm": 0.58984375, "learning_rate": 2.9266626430680183e-05, "loss": 0.9884089660644532, "step": 63600 }, { "epoch": 0.7345565388340642, "grad_norm": 0.953125, "learning_rate": 2.925935486685767e-05, "loss": 0.9830115509033203, "step": 63800 }, { "epoch": 0.7368592239087791, "grad_norm": 0.73828125, "learning_rate": 2.9252083303035152e-05, "loss": 0.9935911560058593, "step": 64000 }, { "epoch": 0.7391619089834941, "grad_norm": 0.455078125, "learning_rate": 2.9244811739212634e-05, "loss": 0.9883312225341797, "step": 64200 }, { "epoch": 0.741464594058209, "grad_norm": 0.404296875, "learning_rate": 2.923754017539012e-05, "loss": 0.9756713104248047, "step": 64400 }, { "epoch": 0.743767279132924, "grad_norm": 0.55078125, "learning_rate": 2.9230268611567603e-05, "loss": 0.996288070678711, "step": 64600 }, { "epoch": 0.7460699642076388, "grad_norm": 0.91796875, "learning_rate": 2.922299704774509e-05, "loss": 0.9647946166992187, "step": 64800 }, { "epoch": 0.7483726492823538, "grad_norm": 0.490234375, "learning_rate": 2.9215725483922575e-05, "loss": 0.9827190399169922, "step": 65000 }, { "epoch": 0.7506753343570688, "grad_norm": 0.9765625, "learning_rate": 2.920845392010006e-05, "loss": 0.9791514587402343, "step": 65200 }, { "epoch": 0.7529780194317837, "grad_norm": 0.56640625, "learning_rate": 2.920118235627754e-05, "loss": 0.9852659606933594, "step": 65400 }, { "epoch": 0.7552807045064986, "grad_norm": 0.486328125, "learning_rate": 2.9193910792455026e-05, "loss": 0.9933679962158203, "step": 65600 }, { "epoch": 0.7575833895812135, "grad_norm": 0.9296875, "learning_rate": 2.918663922863251e-05, "loss": 1.0145327758789062, "step": 65800 }, { "epoch": 0.7598860746559285, "grad_norm": 0.6875, "learning_rate": 2.9179367664809994e-05, "loss": 0.9841469573974609, "step": 66000 }, { "epoch": 0.7621887597306434, "grad_norm": 0.72265625, "learning_rate": 2.917209610098748e-05, "loss": 1.0026850128173828, "step": 66200 }, { "epoch": 0.7644914448053584, "grad_norm": 0.5390625, "learning_rate": 2.9164824537164966e-05, "loss": 0.9971443939208985, "step": 66400 }, { "epoch": 0.7667941298800732, "grad_norm": 0.91015625, "learning_rate": 2.9157552973342445e-05, "loss": 0.9800926971435547, "step": 66600 }, { "epoch": 0.7690968149547882, "grad_norm": 0.734375, "learning_rate": 2.915028140951993e-05, "loss": 0.9816303253173828, "step": 66800 }, { "epoch": 0.7713995000295032, "grad_norm": 0.65625, "learning_rate": 2.9143009845697417e-05, "loss": 0.9932497406005859, "step": 67000 }, { "epoch": 0.7737021851042181, "grad_norm": 0.53515625, "learning_rate": 2.91357382818749e-05, "loss": 0.9947916412353516, "step": 67200 }, { "epoch": 0.776004870178933, "grad_norm": 1.0078125, "learning_rate": 2.9128466718052385e-05, "loss": 0.9930197143554688, "step": 67400 }, { "epoch": 0.7783075552536479, "grad_norm": 0.7734375, "learning_rate": 2.912119515422987e-05, "loss": 0.9941978454589844, "step": 67600 }, { "epoch": 0.7806102403283629, "grad_norm": 0.5546875, "learning_rate": 2.9113923590407354e-05, "loss": 0.9890399932861328, "step": 67800 }, { "epoch": 0.7829129254030778, "grad_norm": 0.921875, "learning_rate": 2.9106652026584836e-05, "loss": 0.983370361328125, "step": 68000 }, { "epoch": 0.7852156104777928, "grad_norm": 0.96484375, "learning_rate": 2.9099380462762322e-05, "loss": 0.9984974670410156, "step": 68200 }, { "epoch": 0.7875182955525077, "grad_norm": 0.6484375, "learning_rate": 2.9092108898939808e-05, "loss": 0.9801548004150391, "step": 68400 }, { "epoch": 0.7898209806272226, "grad_norm": 0.59375, "learning_rate": 2.908483733511729e-05, "loss": 0.989987564086914, "step": 68600 }, { "epoch": 0.7921236657019376, "grad_norm": 0.419921875, "learning_rate": 2.9077565771294776e-05, "loss": 0.9926038360595704, "step": 68800 }, { "epoch": 0.7944263507766525, "grad_norm": 1.0078125, "learning_rate": 2.9070294207472262e-05, "loss": 0.9818599700927735, "step": 69000 }, { "epoch": 0.7967290358513675, "grad_norm": 0.61328125, "learning_rate": 2.906302264364974e-05, "loss": 0.9795211029052734, "step": 69200 }, { "epoch": 0.7990317209260823, "grad_norm": 1.0, "learning_rate": 2.9055751079827227e-05, "loss": 0.9876821899414062, "step": 69400 }, { "epoch": 0.8013344060007973, "grad_norm": 0.5234375, "learning_rate": 2.9048479516004713e-05, "loss": 0.9914775085449219, "step": 69600 }, { "epoch": 0.8036370910755123, "grad_norm": 0.671875, "learning_rate": 2.9041207952182196e-05, "loss": 0.9936875152587891, "step": 69800 }, { "epoch": 0.8059397761502272, "grad_norm": 0.4765625, "learning_rate": 2.9033936388359682e-05, "loss": 0.9944598388671875, "step": 70000 }, { "epoch": 0.8082424612249421, "grad_norm": 0.458984375, "learning_rate": 2.9026664824537168e-05, "loss": 0.9848135375976562, "step": 70200 }, { "epoch": 0.810545146299657, "grad_norm": 1.1015625, "learning_rate": 2.9019393260714647e-05, "loss": 0.9835179138183594, "step": 70400 }, { "epoch": 0.812847831374372, "grad_norm": 0.90625, "learning_rate": 2.9012121696892133e-05, "loss": 0.9890862274169921, "step": 70600 }, { "epoch": 0.8151505164490869, "grad_norm": 1.75, "learning_rate": 2.900485013306962e-05, "loss": 0.9792247009277344, "step": 70800 }, { "epoch": 0.8174532015238019, "grad_norm": 1.03125, "learning_rate": 2.8997578569247105e-05, "loss": 0.9930565643310547, "step": 71000 }, { "epoch": 0.8197558865985168, "grad_norm": 0.75390625, "learning_rate": 2.8990307005424587e-05, "loss": 1.0037332153320313, "step": 71200 }, { "epoch": 0.8220585716732317, "grad_norm": 0.8359375, "learning_rate": 2.8983035441602073e-05, "loss": 0.9568766021728515, "step": 71400 }, { "epoch": 0.8243612567479467, "grad_norm": 0.5390625, "learning_rate": 2.897576387777956e-05, "loss": 1.0169525146484375, "step": 71600 }, { "epoch": 0.8266639418226616, "grad_norm": 0.447265625, "learning_rate": 2.8968492313957038e-05, "loss": 0.9906223297119141, "step": 71800 }, { "epoch": 0.8289666268973765, "grad_norm": 0.46484375, "learning_rate": 2.8961220750134524e-05, "loss": 1.0080840301513672, "step": 72000 }, { "epoch": 0.8312693119720914, "grad_norm": 0.89453125, "learning_rate": 2.895394918631201e-05, "loss": 0.9585226440429687, "step": 72200 }, { "epoch": 0.8335719970468064, "grad_norm": 0.80078125, "learning_rate": 2.8946677622489492e-05, "loss": 0.9908672332763672, "step": 72400 }, { "epoch": 0.8358746821215213, "grad_norm": 2.46875, "learning_rate": 2.893940605866698e-05, "loss": 0.9811976623535156, "step": 72600 }, { "epoch": 0.8381773671962363, "grad_norm": 1.0546875, "learning_rate": 2.8932134494844464e-05, "loss": 0.9929940795898438, "step": 72800 }, { "epoch": 0.8404800522709512, "grad_norm": 0.52734375, "learning_rate": 2.8924862931021943e-05, "loss": 0.9645259857177735, "step": 73000 }, { "epoch": 0.8427827373456661, "grad_norm": 0.427734375, "learning_rate": 2.891759136719943e-05, "loss": 0.9708584594726563, "step": 73200 }, { "epoch": 0.8450854224203811, "grad_norm": 0.5859375, "learning_rate": 2.8910319803376915e-05, "loss": 0.981541748046875, "step": 73400 }, { "epoch": 0.847388107495096, "grad_norm": 0.78515625, "learning_rate": 2.8903048239554398e-05, "loss": 0.9799684143066406, "step": 73600 }, { "epoch": 0.849690792569811, "grad_norm": 1.1875, "learning_rate": 2.8895776675731884e-05, "loss": 0.9951773834228516, "step": 73800 }, { "epoch": 0.8519934776445258, "grad_norm": 0.458984375, "learning_rate": 2.888850511190937e-05, "loss": 1.0009957122802735, "step": 74000 }, { "epoch": 0.8542961627192408, "grad_norm": 0.47265625, "learning_rate": 2.8881233548086855e-05, "loss": 0.9798103332519531, "step": 74200 }, { "epoch": 0.8565988477939558, "grad_norm": 0.7109375, "learning_rate": 2.8873961984264335e-05, "loss": 0.9798514556884765, "step": 74400 }, { "epoch": 0.8589015328686707, "grad_norm": 0.703125, "learning_rate": 2.886669042044182e-05, "loss": 0.9884852600097657, "step": 74600 }, { "epoch": 0.8612042179433856, "grad_norm": 0.7109375, "learning_rate": 2.8859418856619306e-05, "loss": 1.0256126403808594, "step": 74800 }, { "epoch": 0.8635069030181005, "grad_norm": 0.89453125, "learning_rate": 2.885214729279679e-05, "loss": 0.99552734375, "step": 75000 }, { "epoch": 0.8658095880928155, "grad_norm": 0.65234375, "learning_rate": 2.8844875728974275e-05, "loss": 0.9917625427246094, "step": 75200 }, { "epoch": 0.8681122731675304, "grad_norm": 0.59375, "learning_rate": 2.883760416515176e-05, "loss": 0.9782889556884765, "step": 75400 }, { "epoch": 0.8704149582422454, "grad_norm": 1.1875, "learning_rate": 2.883033260132924e-05, "loss": 0.9814031219482422, "step": 75600 }, { "epoch": 0.8727176433169603, "grad_norm": 0.65234375, "learning_rate": 2.8823061037506726e-05, "loss": 0.9945686340332032, "step": 75800 }, { "epoch": 0.8750203283916752, "grad_norm": 1.0078125, "learning_rate": 2.8815789473684212e-05, "loss": 0.9448981475830078, "step": 76000 }, { "epoch": 0.8773230134663902, "grad_norm": 0.6328125, "learning_rate": 2.8808517909861694e-05, "loss": 1.0142716979980468, "step": 76200 }, { "epoch": 0.8796256985411051, "grad_norm": 0.69921875, "learning_rate": 2.880124634603918e-05, "loss": 0.9929308319091796, "step": 76400 }, { "epoch": 0.88192838361582, "grad_norm": 0.609375, "learning_rate": 2.8793974782216666e-05, "loss": 0.9916824340820313, "step": 76600 }, { "epoch": 0.8842310686905349, "grad_norm": 0.8125, "learning_rate": 2.878670321839415e-05, "loss": 1.0056848907470703, "step": 76800 }, { "epoch": 0.8865337537652499, "grad_norm": 1.4375, "learning_rate": 2.877943165457163e-05, "loss": 0.9842034149169921, "step": 77000 }, { "epoch": 0.8888364388399649, "grad_norm": 0.474609375, "learning_rate": 2.8772160090749117e-05, "loss": 1.0175214385986329, "step": 77200 }, { "epoch": 0.8911391239146798, "grad_norm": 1.03125, "learning_rate": 2.8764888526926603e-05, "loss": 0.9752666473388671, "step": 77400 }, { "epoch": 0.8934418089893947, "grad_norm": 0.53515625, "learning_rate": 2.8757616963104086e-05, "loss": 0.9827954864501953, "step": 77600 }, { "epoch": 0.8957444940641096, "grad_norm": 0.486328125, "learning_rate": 2.875034539928157e-05, "loss": 0.9853438568115235, "step": 77800 }, { "epoch": 0.8980471791388246, "grad_norm": 0.96484375, "learning_rate": 2.8743073835459057e-05, "loss": 0.9848164367675781, "step": 78000 }, { "epoch": 0.9003498642135395, "grad_norm": 0.875, "learning_rate": 2.8735802271636536e-05, "loss": 0.9895773315429688, "step": 78200 }, { "epoch": 0.9026525492882544, "grad_norm": 0.67578125, "learning_rate": 2.8728530707814022e-05, "loss": 0.9734499359130859, "step": 78400 }, { "epoch": 0.9049552343629693, "grad_norm": 0.60546875, "learning_rate": 2.8721259143991508e-05, "loss": 0.9732881927490235, "step": 78600 }, { "epoch": 0.9072579194376843, "grad_norm": 0.63671875, "learning_rate": 2.871398758016899e-05, "loss": 0.9826437377929688, "step": 78800 }, { "epoch": 0.9095606045123993, "grad_norm": 0.79296875, "learning_rate": 2.8706716016346477e-05, "loss": 0.9796221160888672, "step": 79000 }, { "epoch": 0.9118632895871142, "grad_norm": 0.41796875, "learning_rate": 2.8699444452523963e-05, "loss": 1.0010478973388672, "step": 79200 }, { "epoch": 0.9141659746618291, "grad_norm": 0.9140625, "learning_rate": 2.8692172888701442e-05, "loss": 0.9749209594726562, "step": 79400 }, { "epoch": 0.916468659736544, "grad_norm": 0.5078125, "learning_rate": 2.8684901324878928e-05, "loss": 0.9853527069091796, "step": 79600 }, { "epoch": 0.918771344811259, "grad_norm": 0.447265625, "learning_rate": 2.8677629761056414e-05, "loss": 1.0083032989501952, "step": 79800 }, { "epoch": 0.9210740298859739, "grad_norm": 0.8828125, "learning_rate": 2.86703581972339e-05, "loss": 0.9884980010986328, "step": 80000 }, { "epoch": 0.9233767149606888, "grad_norm": 0.76953125, "learning_rate": 2.8663086633411382e-05, "loss": 0.9641397857666015, "step": 80200 }, { "epoch": 0.9256794000354038, "grad_norm": 0.83984375, "learning_rate": 2.8655815069588868e-05, "loss": 0.9726267242431641, "step": 80400 }, { "epoch": 0.9279820851101187, "grad_norm": 0.67578125, "learning_rate": 2.864854350576635e-05, "loss": 1.001600570678711, "step": 80600 }, { "epoch": 0.9302847701848337, "grad_norm": 0.9375, "learning_rate": 2.8641271941943833e-05, "loss": 0.9985619354248046, "step": 80800 }, { "epoch": 0.9325874552595486, "grad_norm": 1.4140625, "learning_rate": 2.863400037812132e-05, "loss": 0.967567138671875, "step": 81000 }, { "epoch": 0.9348901403342635, "grad_norm": 0.828125, "learning_rate": 2.8626728814298805e-05, "loss": 1.0003462219238282, "step": 81200 }, { "epoch": 0.9371928254089784, "grad_norm": 0.7890625, "learning_rate": 2.8619457250476287e-05, "loss": 0.9940373229980469, "step": 81400 }, { "epoch": 0.9394955104836934, "grad_norm": 0.78125, "learning_rate": 2.8612185686653773e-05, "loss": 0.9728090667724609, "step": 81600 }, { "epoch": 0.9417981955584084, "grad_norm": 0.400390625, "learning_rate": 2.860491412283126e-05, "loss": 0.9660067749023438, "step": 81800 }, { "epoch": 0.9441008806331233, "grad_norm": 1.0234375, "learning_rate": 2.859764255900874e-05, "loss": 0.9793297576904297, "step": 82000 }, { "epoch": 0.9464035657078382, "grad_norm": 0.76171875, "learning_rate": 2.8590370995186224e-05, "loss": 0.9641354370117188, "step": 82200 }, { "epoch": 0.9487062507825531, "grad_norm": 1.8125, "learning_rate": 2.858309943136371e-05, "loss": 0.9971208953857422, "step": 82400 }, { "epoch": 0.9510089358572681, "grad_norm": 0.7578125, "learning_rate": 2.8575827867541193e-05, "loss": 0.9889365386962891, "step": 82600 }, { "epoch": 0.953311620931983, "grad_norm": 0.62109375, "learning_rate": 2.856855630371868e-05, "loss": 0.995948715209961, "step": 82800 }, { "epoch": 0.9556143060066979, "grad_norm": 0.84765625, "learning_rate": 2.8561284739896165e-05, "loss": 0.9824695587158203, "step": 83000 }, { "epoch": 0.9579169910814128, "grad_norm": 1.3828125, "learning_rate": 2.8554013176073647e-05, "loss": 0.97533935546875, "step": 83200 }, { "epoch": 0.9602196761561278, "grad_norm": 0.56640625, "learning_rate": 2.854674161225113e-05, "loss": 0.9821726226806641, "step": 83400 }, { "epoch": 0.9625223612308428, "grad_norm": 1.171875, "learning_rate": 2.8539470048428615e-05, "loss": 0.9993029022216797, "step": 83600 }, { "epoch": 0.9648250463055577, "grad_norm": 0.828125, "learning_rate": 2.85321984846061e-05, "loss": 0.9740554046630859, "step": 83800 }, { "epoch": 0.9671277313802726, "grad_norm": 0.6484375, "learning_rate": 2.8524926920783584e-05, "loss": 0.9690258026123046, "step": 84000 }, { "epoch": 0.9694304164549875, "grad_norm": 0.73828125, "learning_rate": 2.851765535696107e-05, "loss": 0.9684633636474609, "step": 84200 }, { "epoch": 0.9717331015297025, "grad_norm": 0.7421875, "learning_rate": 2.8510383793138556e-05, "loss": 0.9727975463867188, "step": 84400 }, { "epoch": 0.9740357866044174, "grad_norm": 0.65625, "learning_rate": 2.8503112229316035e-05, "loss": 0.9977262878417968, "step": 84600 }, { "epoch": 0.9763384716791323, "grad_norm": 0.71484375, "learning_rate": 2.849584066549352e-05, "loss": 0.9849166107177735, "step": 84800 }, { "epoch": 0.9786411567538473, "grad_norm": 0.9140625, "learning_rate": 2.8488569101671007e-05, "loss": 1.0033737182617188, "step": 85000 }, { "epoch": 0.9809438418285622, "grad_norm": 0.55859375, "learning_rate": 2.848129753784849e-05, "loss": 0.9663671875, "step": 85200 }, { "epoch": 0.9832465269032772, "grad_norm": 0.734375, "learning_rate": 2.8474025974025975e-05, "loss": 0.9906986236572266, "step": 85400 }, { "epoch": 0.9855492119779921, "grad_norm": 0.5859375, "learning_rate": 2.846675441020346e-05, "loss": 0.9876493072509765, "step": 85600 }, { "epoch": 0.987851897052707, "grad_norm": 0.65625, "learning_rate": 2.8459482846380944e-05, "loss": 0.997586898803711, "step": 85800 }, { "epoch": 0.9901545821274219, "grad_norm": 0.8515625, "learning_rate": 2.8452211282558426e-05, "loss": 0.995333480834961, "step": 86000 }, { "epoch": 0.9924572672021369, "grad_norm": 0.8203125, "learning_rate": 2.8444939718735912e-05, "loss": 0.99697509765625, "step": 86200 }, { "epoch": 0.9947599522768519, "grad_norm": 0.74609375, "learning_rate": 2.8437668154913398e-05, "loss": 0.9929368591308594, "step": 86400 }, { "epoch": 0.9970626373515667, "grad_norm": 0.54296875, "learning_rate": 2.843039659109088e-05, "loss": 1.0003439331054687, "step": 86600 }, { "epoch": 0.9993653224262817, "grad_norm": 1.1015625, "learning_rate": 2.8423125027268366e-05, "loss": 0.9839323425292968, "step": 86800 }, { "epoch": 1.0, "eval_loss": NaN, "eval_runtime": 466.187, "eval_samples_per_second": 60.836, "eval_steps_per_second": 30.419, "step": 86856 }, { "epoch": 1.0016579332537947, "grad_norm": 0.71484375, "learning_rate": 2.841585346344585e-05, "loss": 0.9767461395263672, "step": 87000 }, { "epoch": 1.0039606183285097, "grad_norm": 0.875, "learning_rate": 2.840858189962333e-05, "loss": 0.9855145263671875, "step": 87200 }, { "epoch": 1.0062633034032247, "grad_norm": 0.7265625, "learning_rate": 2.8401310335800817e-05, "loss": 0.9700740051269531, "step": 87400 }, { "epoch": 1.0085659884779397, "grad_norm": 0.95703125, "learning_rate": 2.8394038771978303e-05, "loss": 0.9850736236572266, "step": 87600 }, { "epoch": 1.0108686735526544, "grad_norm": 0.9453125, "learning_rate": 2.8386767208155786e-05, "loss": 0.9656169128417968, "step": 87800 }, { "epoch": 1.0131713586273694, "grad_norm": 0.59375, "learning_rate": 2.837949564433327e-05, "loss": 0.9913868713378906, "step": 88000 }, { "epoch": 1.0154740437020844, "grad_norm": 0.51171875, "learning_rate": 2.8372224080510758e-05, "loss": 0.9808352661132812, "step": 88200 }, { "epoch": 1.0177767287767994, "grad_norm": 0.69921875, "learning_rate": 2.8364952516688237e-05, "loss": 0.9822716522216797, "step": 88400 }, { "epoch": 1.0200794138515141, "grad_norm": 0.703125, "learning_rate": 2.8357680952865723e-05, "loss": 0.9840770721435547, "step": 88600 }, { "epoch": 1.022382098926229, "grad_norm": 0.67578125, "learning_rate": 2.835040938904321e-05, "loss": 0.9758528137207031, "step": 88800 }, { "epoch": 1.024684784000944, "grad_norm": 0.61328125, "learning_rate": 2.8343137825220694e-05, "loss": 1.005013427734375, "step": 89000 }, { "epoch": 1.026987469075659, "grad_norm": 0.5703125, "learning_rate": 2.8335866261398177e-05, "loss": 1.0009622955322266, "step": 89200 }, { "epoch": 1.029290154150374, "grad_norm": 0.57421875, "learning_rate": 2.8328594697575663e-05, "loss": 0.9745167541503906, "step": 89400 }, { "epoch": 1.0315928392250888, "grad_norm": 0.98828125, "learning_rate": 2.8321323133753145e-05, "loss": 0.9853366088867187, "step": 89600 }, { "epoch": 1.0338955242998038, "grad_norm": 0.84765625, "learning_rate": 2.8314051569930628e-05, "loss": 0.9802220916748047, "step": 89800 }, { "epoch": 1.0361982093745188, "grad_norm": 0.765625, "learning_rate": 2.8306780006108114e-05, "loss": 0.9878942108154297, "step": 90000 }, { "epoch": 1.0385008944492338, "grad_norm": 0.63671875, "learning_rate": 2.82995084422856e-05, "loss": 1.0209328460693359, "step": 90200 }, { "epoch": 1.0408035795239488, "grad_norm": 1.1953125, "learning_rate": 2.8292236878463082e-05, "loss": 0.9749903869628906, "step": 90400 }, { "epoch": 1.0431062645986635, "grad_norm": 0.7265625, "learning_rate": 2.8284965314640568e-05, "loss": 0.964295654296875, "step": 90600 }, { "epoch": 1.0454089496733785, "grad_norm": 0.71484375, "learning_rate": 2.8277693750818054e-05, "loss": 1.0175611877441406, "step": 90800 }, { "epoch": 1.0477116347480935, "grad_norm": 0.87109375, "learning_rate": 2.8270422186995533e-05, "loss": 1.0039064025878905, "step": 91000 }, { "epoch": 1.0500143198228085, "grad_norm": 0.6875, "learning_rate": 2.826315062317302e-05, "loss": 0.9765067291259766, "step": 91200 }, { "epoch": 1.0523170048975232, "grad_norm": 0.75390625, "learning_rate": 2.8255879059350505e-05, "loss": 1.002488555908203, "step": 91400 }, { "epoch": 1.0546196899722382, "grad_norm": 0.419921875, "learning_rate": 2.824860749552799e-05, "loss": 0.9849620819091797, "step": 91600 }, { "epoch": 1.0569223750469532, "grad_norm": 0.8671875, "learning_rate": 2.8241335931705474e-05, "loss": 0.9739988708496093, "step": 91800 }, { "epoch": 1.0592250601216682, "grad_norm": 1.03125, "learning_rate": 2.823406436788296e-05, "loss": 0.9917415618896485, "step": 92000 }, { "epoch": 1.0615277451963832, "grad_norm": 0.953125, "learning_rate": 2.8226792804060442e-05, "loss": 0.9903607177734375, "step": 92200 }, { "epoch": 1.063830430271098, "grad_norm": 0.55078125, "learning_rate": 2.8219521240237925e-05, "loss": 0.9716462707519531, "step": 92400 }, { "epoch": 1.066133115345813, "grad_norm": 0.4453125, "learning_rate": 2.821224967641541e-05, "loss": 0.9898148345947265, "step": 92600 }, { "epoch": 1.0684358004205279, "grad_norm": 0.9921875, "learning_rate": 2.8204978112592896e-05, "loss": 0.9770774841308594, "step": 92800 }, { "epoch": 1.0707384854952429, "grad_norm": 0.51171875, "learning_rate": 2.819770654877038e-05, "loss": 1.016856918334961, "step": 93000 }, { "epoch": 1.0730411705699576, "grad_norm": 1.125, "learning_rate": 2.8190434984947865e-05, "loss": 0.9860330200195313, "step": 93200 }, { "epoch": 1.0753438556446726, "grad_norm": 1.21875, "learning_rate": 2.8183163421125347e-05, "loss": 0.9857374572753906, "step": 93400 }, { "epoch": 1.0776465407193876, "grad_norm": 0.68359375, "learning_rate": 2.817589185730283e-05, "loss": 0.9712320709228516, "step": 93600 }, { "epoch": 1.0799492257941026, "grad_norm": 0.8046875, "learning_rate": 2.8168620293480316e-05, "loss": 0.9812728881835937, "step": 93800 }, { "epoch": 1.0822519108688176, "grad_norm": 0.55859375, "learning_rate": 2.81613487296578e-05, "loss": 0.9942698669433594, "step": 94000 }, { "epoch": 1.0845545959435323, "grad_norm": 0.5234375, "learning_rate": 2.8154077165835284e-05, "loss": 0.9869801330566407, "step": 94200 }, { "epoch": 1.0868572810182473, "grad_norm": 0.65234375, "learning_rate": 2.814680560201277e-05, "loss": 0.9874109649658203, "step": 94400 }, { "epoch": 1.0891599660929623, "grad_norm": 0.66796875, "learning_rate": 2.8139534038190256e-05, "loss": 0.974925537109375, "step": 94600 }, { "epoch": 1.0914626511676773, "grad_norm": 0.8671875, "learning_rate": 2.813226247436774e-05, "loss": 0.9871249389648438, "step": 94800 }, { "epoch": 1.093765336242392, "grad_norm": 0.75, "learning_rate": 2.812499091054522e-05, "loss": 0.9713893127441406, "step": 95000 }, { "epoch": 1.096068021317107, "grad_norm": 0.439453125, "learning_rate": 2.8117719346722707e-05, "loss": 0.9837332916259766, "step": 95200 }, { "epoch": 1.098370706391822, "grad_norm": 0.9296875, "learning_rate": 2.8110447782900193e-05, "loss": 0.9709980010986328, "step": 95400 }, { "epoch": 1.100673391466537, "grad_norm": 1.015625, "learning_rate": 2.8103176219077675e-05, "loss": 0.9841094207763672, "step": 95600 }, { "epoch": 1.102976076541252, "grad_norm": 0.56640625, "learning_rate": 2.809590465525516e-05, "loss": 0.989020767211914, "step": 95800 }, { "epoch": 1.1052787616159667, "grad_norm": 0.5078125, "learning_rate": 2.8088633091432644e-05, "loss": 0.9772124481201172, "step": 96000 }, { "epoch": 1.1075814466906817, "grad_norm": 0.57421875, "learning_rate": 2.8081361527610126e-05, "loss": 0.9723876953125, "step": 96200 }, { "epoch": 1.1098841317653967, "grad_norm": 0.58203125, "learning_rate": 2.8074089963787612e-05, "loss": 0.9917980194091797, "step": 96400 }, { "epoch": 1.1121868168401117, "grad_norm": 0.49609375, "learning_rate": 2.8066818399965098e-05, "loss": 0.9809168243408203, "step": 96600 }, { "epoch": 1.1144895019148267, "grad_norm": 0.6328125, "learning_rate": 2.805954683614258e-05, "loss": 0.9748997497558594, "step": 96800 }, { "epoch": 1.1167921869895414, "grad_norm": 0.98046875, "learning_rate": 2.8052275272320067e-05, "loss": 0.9917316436767578, "step": 97000 }, { "epoch": 1.1190948720642564, "grad_norm": 1.0703125, "learning_rate": 2.804500370849755e-05, "loss": 0.9702124786376953, "step": 97200 }, { "epoch": 1.1213975571389714, "grad_norm": 0.8203125, "learning_rate": 2.8037732144675035e-05, "loss": 0.9899410247802735, "step": 97400 }, { "epoch": 1.1237002422136864, "grad_norm": 0.83984375, "learning_rate": 2.8030460580852518e-05, "loss": 0.9802442169189454, "step": 97600 }, { "epoch": 1.1260029272884013, "grad_norm": 0.59375, "learning_rate": 2.8023189017030004e-05, "loss": 0.9868735504150391, "step": 97800 }, { "epoch": 1.128305612363116, "grad_norm": 0.7421875, "learning_rate": 2.801591745320749e-05, "loss": 0.9881065368652344, "step": 98000 }, { "epoch": 1.130608297437831, "grad_norm": 0.55859375, "learning_rate": 2.8008645889384972e-05, "loss": 0.9748045349121094, "step": 98200 }, { "epoch": 1.132910982512546, "grad_norm": 0.5625, "learning_rate": 2.8001374325562458e-05, "loss": 0.9920476531982422, "step": 98400 }, { "epoch": 1.135213667587261, "grad_norm": 0.96875, "learning_rate": 2.799410276173994e-05, "loss": 1.0023683166503907, "step": 98600 }, { "epoch": 1.1375163526619758, "grad_norm": 0.490234375, "learning_rate": 2.7986831197917423e-05, "loss": 0.9839882659912109, "step": 98800 }, { "epoch": 1.1398190377366908, "grad_norm": 0.53515625, "learning_rate": 2.797955963409491e-05, "loss": 0.9793102264404296, "step": 99000 }, { "epoch": 1.1421217228114058, "grad_norm": 0.78515625, "learning_rate": 2.7972288070272395e-05, "loss": 0.9812483215332031, "step": 99200 }, { "epoch": 1.1444244078861208, "grad_norm": 0.63671875, "learning_rate": 2.7965016506449877e-05, "loss": 0.9835822296142578, "step": 99400 }, { "epoch": 1.1467270929608357, "grad_norm": 0.48046875, "learning_rate": 2.7957744942627363e-05, "loss": 0.9863402557373047, "step": 99600 }, { "epoch": 1.1490297780355505, "grad_norm": 0.54296875, "learning_rate": 2.7950473378804846e-05, "loss": 0.9773790740966797, "step": 99800 }, { "epoch": 1.1513324631102655, "grad_norm": 0.80078125, "learning_rate": 2.7943201814982328e-05, "loss": 0.9791139984130859, "step": 100000 }, { "epoch": 1.1536351481849805, "grad_norm": 0.72265625, "learning_rate": 2.7935930251159814e-05, "loss": 1.0102542114257813, "step": 100200 }, { "epoch": 1.1559378332596955, "grad_norm": 0.515625, "learning_rate": 2.79286586873373e-05, "loss": 0.9698152923583985, "step": 100400 }, { "epoch": 1.1582405183344102, "grad_norm": 0.5625, "learning_rate": 2.7921387123514786e-05, "loss": 0.9856640625, "step": 100600 }, { "epoch": 1.1605432034091252, "grad_norm": 0.7421875, "learning_rate": 2.791411555969227e-05, "loss": 0.9970908355712891, "step": 100800 }, { "epoch": 1.1628458884838402, "grad_norm": 1.1171875, "learning_rate": 2.7906843995869754e-05, "loss": 0.9615906524658203, "step": 101000 }, { "epoch": 1.1651485735585552, "grad_norm": 0.73046875, "learning_rate": 2.7899572432047237e-05, "loss": 0.9927642822265625, "step": 101200 }, { "epoch": 1.1674512586332702, "grad_norm": 1.078125, "learning_rate": 2.789230086822472e-05, "loss": 0.9984485626220703, "step": 101400 }, { "epoch": 1.169753943707985, "grad_norm": 0.98828125, "learning_rate": 2.7885029304402205e-05, "loss": 0.9728903198242187, "step": 101600 }, { "epoch": 1.1720566287827, "grad_norm": 0.65625, "learning_rate": 2.787775774057969e-05, "loss": 0.968542709350586, "step": 101800 }, { "epoch": 1.1743593138574149, "grad_norm": 0.81640625, "learning_rate": 2.7870486176757174e-05, "loss": 0.9618368530273438, "step": 102000 }, { "epoch": 1.1766619989321299, "grad_norm": 0.453125, "learning_rate": 2.786321461293466e-05, "loss": 0.9763688659667968, "step": 102200 }, { "epoch": 1.1789646840068446, "grad_norm": 0.92578125, "learning_rate": 2.7855943049112142e-05, "loss": 0.9664765167236328, "step": 102400 }, { "epoch": 1.1812673690815596, "grad_norm": 0.765625, "learning_rate": 2.7848671485289625e-05, "loss": 1.0016697692871093, "step": 102600 }, { "epoch": 1.1835700541562746, "grad_norm": 0.8515625, "learning_rate": 2.784139992146711e-05, "loss": 0.982967529296875, "step": 102800 }, { "epoch": 1.1858727392309896, "grad_norm": 0.6640625, "learning_rate": 2.7834128357644597e-05, "loss": 0.9826297760009766, "step": 103000 }, { "epoch": 1.1881754243057046, "grad_norm": 0.6015625, "learning_rate": 2.782685679382208e-05, "loss": 1.0046814727783202, "step": 103200 }, { "epoch": 1.1904781093804193, "grad_norm": 0.76171875, "learning_rate": 2.7819585229999565e-05, "loss": 0.9985332489013672, "step": 103400 }, { "epoch": 1.1927807944551343, "grad_norm": 0.4765625, "learning_rate": 2.7812313666177048e-05, "loss": 0.9772327423095704, "step": 103600 }, { "epoch": 1.1950834795298493, "grad_norm": 0.79296875, "learning_rate": 2.7805042102354533e-05, "loss": 0.9572280883789063, "step": 103800 }, { "epoch": 1.1973861646045643, "grad_norm": 0.98828125, "learning_rate": 2.7797770538532016e-05, "loss": 1.0030010223388672, "step": 104000 }, { "epoch": 1.199688849679279, "grad_norm": 0.87109375, "learning_rate": 2.7790498974709502e-05, "loss": 1.004496841430664, "step": 104200 }, { "epoch": 1.201991534753994, "grad_norm": 0.72265625, "learning_rate": 2.7783227410886988e-05, "loss": 0.9863777160644531, "step": 104400 }, { "epoch": 1.204294219828709, "grad_norm": 0.76171875, "learning_rate": 2.777595584706447e-05, "loss": 0.9835929870605469, "step": 104600 }, { "epoch": 1.206596904903424, "grad_norm": 0.5859375, "learning_rate": 2.7768684283241956e-05, "loss": 0.9846414947509765, "step": 104800 }, { "epoch": 1.208899589978139, "grad_norm": 0.7421875, "learning_rate": 2.776141271941944e-05, "loss": 0.9859349060058594, "step": 105000 }, { "epoch": 1.211202275052854, "grad_norm": 1.0390625, "learning_rate": 2.775414115559692e-05, "loss": 0.9805864715576171, "step": 105200 }, { "epoch": 1.2135049601275687, "grad_norm": 1.5625, "learning_rate": 2.7746869591774407e-05, "loss": 1.0142818450927735, "step": 105400 }, { "epoch": 1.2158076452022837, "grad_norm": 0.69140625, "learning_rate": 2.7739598027951893e-05, "loss": 0.9921229553222656, "step": 105600 }, { "epoch": 1.2181103302769987, "grad_norm": 0.5078125, "learning_rate": 2.7732326464129376e-05, "loss": 0.9776945495605469, "step": 105800 }, { "epoch": 1.2204130153517136, "grad_norm": 0.58984375, "learning_rate": 2.772505490030686e-05, "loss": 0.9756576538085937, "step": 106000 }, { "epoch": 1.2227157004264284, "grad_norm": 0.71875, "learning_rate": 2.7717783336484344e-05, "loss": 0.9888297271728516, "step": 106200 }, { "epoch": 1.2250183855011434, "grad_norm": 0.60546875, "learning_rate": 2.771051177266183e-05, "loss": 0.9722689819335938, "step": 106400 }, { "epoch": 1.2273210705758584, "grad_norm": 0.51171875, "learning_rate": 2.7703240208839313e-05, "loss": 0.976254653930664, "step": 106600 }, { "epoch": 1.2296237556505734, "grad_norm": 0.53125, "learning_rate": 2.76959686450168e-05, "loss": 0.9966973114013672, "step": 106800 }, { "epoch": 1.2319264407252883, "grad_norm": 0.65625, "learning_rate": 2.7688697081194284e-05, "loss": 0.9784175109863281, "step": 107000 }, { "epoch": 1.234229125800003, "grad_norm": 0.47265625, "learning_rate": 2.7681425517371767e-05, "loss": 0.9850876617431641, "step": 107200 }, { "epoch": 1.236531810874718, "grad_norm": 0.68359375, "learning_rate": 2.767415395354925e-05, "loss": 0.9829400634765625, "step": 107400 }, { "epoch": 1.238834495949433, "grad_norm": 0.63671875, "learning_rate": 2.7666882389726735e-05, "loss": 0.9864478302001953, "step": 107600 }, { "epoch": 1.241137181024148, "grad_norm": 1.78125, "learning_rate": 2.7659610825904218e-05, "loss": 1.0001952362060547, "step": 107800 }, { "epoch": 1.2434398660988628, "grad_norm": 0.5625, "learning_rate": 2.7652339262081704e-05, "loss": 0.9876364135742187, "step": 108000 }, { "epoch": 1.2457425511735778, "grad_norm": 0.59375, "learning_rate": 2.764506769825919e-05, "loss": 1.0017476654052735, "step": 108200 }, { "epoch": 1.2480452362482928, "grad_norm": 0.443359375, "learning_rate": 2.7637796134436672e-05, "loss": 0.9773336029052735, "step": 108400 }, { "epoch": 1.2503479213230078, "grad_norm": 0.5, "learning_rate": 2.7630524570614158e-05, "loss": 0.9803909301757813, "step": 108600 }, { "epoch": 1.2526506063977227, "grad_norm": 0.6875, "learning_rate": 2.762325300679164e-05, "loss": 0.9660771942138672, "step": 108800 }, { "epoch": 1.2549532914724375, "grad_norm": 0.609375, "learning_rate": 2.7615981442969123e-05, "loss": 0.9591829681396484, "step": 109000 }, { "epoch": 1.2572559765471525, "grad_norm": 1.1875, "learning_rate": 2.760870987914661e-05, "loss": 1.0150857543945313, "step": 109200 }, { "epoch": 1.2595586616218675, "grad_norm": 1.1484375, "learning_rate": 2.7601438315324095e-05, "loss": 1.011795425415039, "step": 109400 }, { "epoch": 1.2618613466965825, "grad_norm": 1.0234375, "learning_rate": 2.759416675150158e-05, "loss": 1.0024031066894532, "step": 109600 }, { "epoch": 1.2641640317712972, "grad_norm": 1.0625, "learning_rate": 2.7586895187679063e-05, "loss": 0.9753433990478516, "step": 109800 }, { "epoch": 1.2664667168460122, "grad_norm": 1.015625, "learning_rate": 2.7579623623856546e-05, "loss": 0.9753445434570313, "step": 110000 }, { "epoch": 1.2687694019207272, "grad_norm": 0.953125, "learning_rate": 2.7572352060034032e-05, "loss": 0.9854216003417968, "step": 110200 }, { "epoch": 1.2710720869954422, "grad_norm": 0.4765625, "learning_rate": 2.7565080496211514e-05, "loss": 0.9756188201904297, "step": 110400 }, { "epoch": 1.2733747720701571, "grad_norm": 0.6875, "learning_rate": 2.7557808932389e-05, "loss": 0.9979515075683594, "step": 110600 }, { "epoch": 1.2756774571448721, "grad_norm": 1.0078125, "learning_rate": 2.7550537368566486e-05, "loss": 1.0006640625, "step": 110800 }, { "epoch": 1.277980142219587, "grad_norm": 0.68359375, "learning_rate": 2.754326580474397e-05, "loss": 0.9963182067871094, "step": 111000 }, { "epoch": 1.2802828272943019, "grad_norm": 0.74609375, "learning_rate": 2.7535994240921455e-05, "loss": 0.9819471740722656, "step": 111200 }, { "epoch": 1.2825855123690169, "grad_norm": 0.53515625, "learning_rate": 2.7528722677098937e-05, "loss": 0.9869737243652343, "step": 111400 }, { "epoch": 1.2848881974437316, "grad_norm": 0.9375, "learning_rate": 2.752145111327642e-05, "loss": 1.0044972229003906, "step": 111600 }, { "epoch": 1.2871908825184466, "grad_norm": 0.52734375, "learning_rate": 2.7514179549453906e-05, "loss": 0.9748899078369141, "step": 111800 }, { "epoch": 1.2894935675931616, "grad_norm": 0.828125, "learning_rate": 2.750690798563139e-05, "loss": 0.9800602722167969, "step": 112000 }, { "epoch": 1.2917962526678766, "grad_norm": 0.8125, "learning_rate": 2.7499636421808877e-05, "loss": 0.9784731292724609, "step": 112200 }, { "epoch": 1.2940989377425915, "grad_norm": 0.40625, "learning_rate": 2.749236485798636e-05, "loss": 0.9836808013916015, "step": 112400 }, { "epoch": 1.2964016228173065, "grad_norm": 2.5, "learning_rate": 2.7485093294163843e-05, "loss": 0.991956558227539, "step": 112600 }, { "epoch": 1.2987043078920213, "grad_norm": 0.7890625, "learning_rate": 2.747782173034133e-05, "loss": 0.9863188934326171, "step": 112800 }, { "epoch": 1.3010069929667363, "grad_norm": 1.0, "learning_rate": 2.747055016651881e-05, "loss": 1.0016487121582032, "step": 113000 }, { "epoch": 1.3033096780414513, "grad_norm": 0.89453125, "learning_rate": 2.7463278602696297e-05, "loss": 0.9983952331542969, "step": 113200 }, { "epoch": 1.305612363116166, "grad_norm": 0.6796875, "learning_rate": 2.7456007038873783e-05, "loss": 1.014336395263672, "step": 113400 }, { "epoch": 1.307915048190881, "grad_norm": 0.72265625, "learning_rate": 2.7448735475051265e-05, "loss": 0.970293197631836, "step": 113600 }, { "epoch": 1.310217733265596, "grad_norm": 0.95703125, "learning_rate": 2.7441463911228748e-05, "loss": 0.9937506866455078, "step": 113800 }, { "epoch": 1.312520418340311, "grad_norm": 1.0703125, "learning_rate": 2.7434192347406234e-05, "loss": 0.9721630859375, "step": 114000 }, { "epoch": 1.314823103415026, "grad_norm": 0.62109375, "learning_rate": 2.7426920783583716e-05, "loss": 0.9970010375976562, "step": 114200 }, { "epoch": 1.317125788489741, "grad_norm": 0.71875, "learning_rate": 2.7419649219761202e-05, "loss": 1.006850814819336, "step": 114400 }, { "epoch": 1.3194284735644557, "grad_norm": 0.58984375, "learning_rate": 2.7412377655938688e-05, "loss": 1.0042724609375, "step": 114600 }, { "epoch": 1.3217311586391707, "grad_norm": 0.828125, "learning_rate": 2.740510609211617e-05, "loss": 0.9619822692871094, "step": 114800 }, { "epoch": 1.3240338437138857, "grad_norm": 0.482421875, "learning_rate": 2.7397834528293657e-05, "loss": 0.9862764739990234, "step": 115000 }, { "epoch": 1.3263365287886004, "grad_norm": 0.6328125, "learning_rate": 2.739056296447114e-05, "loss": 0.9918037414550781, "step": 115200 }, { "epoch": 1.3286392138633154, "grad_norm": 0.8515625, "learning_rate": 2.7383291400648625e-05, "loss": 1.0145311737060547, "step": 115400 }, { "epoch": 1.3309418989380304, "grad_norm": 0.7265625, "learning_rate": 2.7376019836826108e-05, "loss": 0.9897518920898437, "step": 115600 }, { "epoch": 1.3332445840127454, "grad_norm": 0.609375, "learning_rate": 2.7368748273003593e-05, "loss": 0.9979398345947266, "step": 115800 }, { "epoch": 1.3355472690874604, "grad_norm": 0.458984375, "learning_rate": 2.736147670918108e-05, "loss": 0.9715717315673829, "step": 116000 }, { "epoch": 1.3378499541621753, "grad_norm": 0.6328125, "learning_rate": 2.7354205145358562e-05, "loss": 0.9838251495361328, "step": 116200 }, { "epoch": 1.34015263923689, "grad_norm": 0.875, "learning_rate": 2.7346933581536044e-05, "loss": 0.9873313140869141, "step": 116400 }, { "epoch": 1.342455324311605, "grad_norm": 0.72265625, "learning_rate": 2.733966201771353e-05, "loss": 0.9789092254638672, "step": 116600 }, { "epoch": 1.34475800938632, "grad_norm": 0.6640625, "learning_rate": 2.7332390453891013e-05, "loss": 0.9955917358398437, "step": 116800 }, { "epoch": 1.347060694461035, "grad_norm": 0.66796875, "learning_rate": 2.73251188900685e-05, "loss": 0.985167007446289, "step": 117000 }, { "epoch": 1.3493633795357498, "grad_norm": 0.59375, "learning_rate": 2.7317847326245985e-05, "loss": 0.9772294616699219, "step": 117200 }, { "epoch": 1.3516660646104648, "grad_norm": 0.6640625, "learning_rate": 2.7310575762423467e-05, "loss": 0.9946612548828125, "step": 117400 }, { "epoch": 1.3539687496851798, "grad_norm": 0.7109375, "learning_rate": 2.730330419860095e-05, "loss": 0.97852783203125, "step": 117600 }, { "epoch": 1.3562714347598948, "grad_norm": 0.53125, "learning_rate": 2.7296032634778436e-05, "loss": 1.0050527191162109, "step": 117800 }, { "epoch": 1.3585741198346097, "grad_norm": 0.546875, "learning_rate": 2.728876107095592e-05, "loss": 0.9625944519042968, "step": 118000 }, { "epoch": 1.3608768049093245, "grad_norm": 0.65234375, "learning_rate": 2.7281489507133404e-05, "loss": 0.9805034637451172, "step": 118200 }, { "epoch": 1.3631794899840395, "grad_norm": 0.6484375, "learning_rate": 2.727421794331089e-05, "loss": 0.991854248046875, "step": 118400 }, { "epoch": 1.3654821750587545, "grad_norm": 1.015625, "learning_rate": 2.7266946379488376e-05, "loss": 0.9891043853759766, "step": 118600 }, { "epoch": 1.3677848601334694, "grad_norm": 0.88671875, "learning_rate": 2.725967481566586e-05, "loss": 0.9937184143066407, "step": 118800 }, { "epoch": 1.3700875452081842, "grad_norm": 0.55859375, "learning_rate": 2.725240325184334e-05, "loss": 0.9900875854492187, "step": 119000 }, { "epoch": 1.3723902302828992, "grad_norm": 0.8046875, "learning_rate": 2.7245131688020827e-05, "loss": 0.956904296875, "step": 119200 }, { "epoch": 1.3746929153576142, "grad_norm": 0.494140625, "learning_rate": 2.723786012419831e-05, "loss": 0.989427719116211, "step": 119400 }, { "epoch": 1.3769956004323292, "grad_norm": 0.64453125, "learning_rate": 2.7230588560375795e-05, "loss": 0.9846376800537109, "step": 119600 }, { "epoch": 1.3792982855070441, "grad_norm": 0.68359375, "learning_rate": 2.722331699655328e-05, "loss": 0.9800340270996094, "step": 119800 }, { "epoch": 1.3816009705817591, "grad_norm": 0.8203125, "learning_rate": 2.7216045432730764e-05, "loss": 0.9806147003173828, "step": 120000 }, { "epoch": 1.3839036556564739, "grad_norm": 0.56640625, "learning_rate": 2.7208773868908246e-05, "loss": 0.978929672241211, "step": 120200 }, { "epoch": 1.3862063407311889, "grad_norm": 0.68359375, "learning_rate": 2.7201502305085732e-05, "loss": 0.9661943054199219, "step": 120400 }, { "epoch": 1.3885090258059039, "grad_norm": 0.5859375, "learning_rate": 2.7194230741263215e-05, "loss": 0.9726935577392578, "step": 120600 }, { "epoch": 1.3908117108806186, "grad_norm": 0.87890625, "learning_rate": 2.71869591774407e-05, "loss": 0.9841280364990235, "step": 120800 }, { "epoch": 1.3931143959553336, "grad_norm": 0.62890625, "learning_rate": 2.7179687613618187e-05, "loss": 1.0080772399902345, "step": 121000 }, { "epoch": 1.3954170810300486, "grad_norm": 0.9375, "learning_rate": 2.7172416049795672e-05, "loss": 0.9903179931640625, "step": 121200 }, { "epoch": 1.3977197661047636, "grad_norm": 0.65625, "learning_rate": 2.7165144485973155e-05, "loss": 0.97442626953125, "step": 121400 }, { "epoch": 1.4000224511794785, "grad_norm": 1.4375, "learning_rate": 2.7157872922150637e-05, "loss": 0.9792997741699219, "step": 121600 }, { "epoch": 1.4023251362541935, "grad_norm": 0.58984375, "learning_rate": 2.7150601358328123e-05, "loss": 0.9764759063720703, "step": 121800 }, { "epoch": 1.4046278213289083, "grad_norm": 0.90625, "learning_rate": 2.7143329794505606e-05, "loss": 1.0077233123779297, "step": 122000 }, { "epoch": 1.4069305064036233, "grad_norm": 0.65234375, "learning_rate": 2.7136058230683092e-05, "loss": 0.9881072235107422, "step": 122200 }, { "epoch": 1.4092331914783383, "grad_norm": 0.61328125, "learning_rate": 2.7128786666860578e-05, "loss": 0.9633769989013672, "step": 122400 }, { "epoch": 1.411535876553053, "grad_norm": 0.63671875, "learning_rate": 2.712151510303806e-05, "loss": 0.9723685455322265, "step": 122600 }, { "epoch": 1.413838561627768, "grad_norm": 1.28125, "learning_rate": 2.7114243539215543e-05, "loss": 0.9701836395263672, "step": 122800 }, { "epoch": 1.416141246702483, "grad_norm": 0.451171875, "learning_rate": 2.710697197539303e-05, "loss": 0.9833367919921875, "step": 123000 }, { "epoch": 1.418443931777198, "grad_norm": 0.6953125, "learning_rate": 2.709970041157051e-05, "loss": 0.9934508514404297, "step": 123200 }, { "epoch": 1.420746616851913, "grad_norm": 0.72265625, "learning_rate": 2.7092428847747997e-05, "loss": 0.9717855072021484, "step": 123400 }, { "epoch": 1.423049301926628, "grad_norm": 0.5625, "learning_rate": 2.7085157283925483e-05, "loss": 1.0004611206054688, "step": 123600 }, { "epoch": 1.4253519870013427, "grad_norm": 0.546875, "learning_rate": 2.7077885720102966e-05, "loss": 0.991996841430664, "step": 123800 }, { "epoch": 1.4276546720760577, "grad_norm": 0.68359375, "learning_rate": 2.7070614156280448e-05, "loss": 0.9875720977783203, "step": 124000 }, { "epoch": 1.4299573571507727, "grad_norm": 1.3203125, "learning_rate": 2.7063342592457934e-05, "loss": 0.9992472076416016, "step": 124200 }, { "epoch": 1.4322600422254876, "grad_norm": 0.796875, "learning_rate": 2.705607102863542e-05, "loss": 0.9760001373291015, "step": 124400 }, { "epoch": 1.4345627273002024, "grad_norm": 1.03125, "learning_rate": 2.7048799464812902e-05, "loss": 1.0076248168945312, "step": 124600 }, { "epoch": 1.4368654123749174, "grad_norm": 1.6953125, "learning_rate": 2.704152790099039e-05, "loss": 0.986727066040039, "step": 124800 }, { "epoch": 1.4391680974496324, "grad_norm": 0.71484375, "learning_rate": 2.7034256337167874e-05, "loss": 0.9612811279296875, "step": 125000 }, { "epoch": 1.4414707825243473, "grad_norm": 0.52734375, "learning_rate": 2.7026984773345357e-05, "loss": 0.9965091705322265, "step": 125200 }, { "epoch": 1.4437734675990623, "grad_norm": 0.69140625, "learning_rate": 2.701971320952284e-05, "loss": 0.984040756225586, "step": 125400 }, { "epoch": 1.446076152673777, "grad_norm": 0.67578125, "learning_rate": 2.7012441645700325e-05, "loss": 0.9824740600585937, "step": 125600 }, { "epoch": 1.448378837748492, "grad_norm": 0.55859375, "learning_rate": 2.7005170081877808e-05, "loss": 0.9734669494628906, "step": 125800 }, { "epoch": 1.450681522823207, "grad_norm": 0.7734375, "learning_rate": 2.6997898518055294e-05, "loss": 0.9760218811035156, "step": 126000 }, { "epoch": 1.452984207897922, "grad_norm": 0.9375, "learning_rate": 2.699062695423278e-05, "loss": 0.979968032836914, "step": 126200 }, { "epoch": 1.4552868929726368, "grad_norm": 0.65625, "learning_rate": 2.6983355390410262e-05, "loss": 0.9945246887207031, "step": 126400 }, { "epoch": 1.4575895780473518, "grad_norm": 1.2734375, "learning_rate": 2.6976083826587745e-05, "loss": 0.9984708404541016, "step": 126600 }, { "epoch": 1.4598922631220668, "grad_norm": 0.6953125, "learning_rate": 2.696881226276523e-05, "loss": 0.9899350738525391, "step": 126800 }, { "epoch": 1.4621949481967818, "grad_norm": 0.609375, "learning_rate": 2.6961540698942716e-05, "loss": 1.0038150787353515, "step": 127000 }, { "epoch": 1.4644976332714967, "grad_norm": 0.62109375, "learning_rate": 2.69542691351202e-05, "loss": 0.9827015686035157, "step": 127200 }, { "epoch": 1.4668003183462117, "grad_norm": 0.62890625, "learning_rate": 2.6946997571297685e-05, "loss": 0.9892060089111329, "step": 127400 }, { "epoch": 1.4691030034209265, "grad_norm": 0.5625, "learning_rate": 2.693972600747517e-05, "loss": 0.9666407012939453, "step": 127600 }, { "epoch": 1.4714056884956415, "grad_norm": 0.9609375, "learning_rate": 2.693245444365265e-05, "loss": 0.973760986328125, "step": 127800 }, { "epoch": 1.4737083735703564, "grad_norm": 0.73046875, "learning_rate": 2.6925182879830136e-05, "loss": 0.9950855255126954, "step": 128000 }, { "epoch": 1.4760110586450712, "grad_norm": 0.76953125, "learning_rate": 2.6917911316007622e-05, "loss": 0.9772869873046875, "step": 128200 }, { "epoch": 1.4783137437197862, "grad_norm": 1.3046875, "learning_rate": 2.6910639752185104e-05, "loss": 1.0049010467529298, "step": 128400 }, { "epoch": 1.4806164287945012, "grad_norm": 0.6953125, "learning_rate": 2.690336818836259e-05, "loss": 0.9666265106201172, "step": 128600 }, { "epoch": 1.4829191138692162, "grad_norm": 0.5546875, "learning_rate": 2.6896096624540076e-05, "loss": 0.9786612701416015, "step": 128800 }, { "epoch": 1.4852217989439311, "grad_norm": 0.76953125, "learning_rate": 2.688882506071756e-05, "loss": 1.0051888275146483, "step": 129000 }, { "epoch": 1.4875244840186461, "grad_norm": 0.83984375, "learning_rate": 2.688155349689504e-05, "loss": 0.9594706726074219, "step": 129200 }, { "epoch": 1.4898271690933609, "grad_norm": 0.57421875, "learning_rate": 2.6874281933072527e-05, "loss": 0.9975163269042969, "step": 129400 }, { "epoch": 1.4921298541680759, "grad_norm": 0.462890625, "learning_rate": 2.686701036925001e-05, "loss": 0.9801680755615234, "step": 129600 }, { "epoch": 1.4944325392427908, "grad_norm": 2.34375, "learning_rate": 2.6859738805427496e-05, "loss": 0.9652777862548828, "step": 129800 }, { "epoch": 1.4967352243175056, "grad_norm": 0.91015625, "learning_rate": 2.685246724160498e-05, "loss": 0.9953791809082031, "step": 130000 }, { "epoch": 1.4990379093922206, "grad_norm": 0.640625, "learning_rate": 2.6845195677782467e-05, "loss": 0.9773629760742187, "step": 130200 }, { "epoch": 1.5013405944669356, "grad_norm": 0.55859375, "learning_rate": 2.6837924113959947e-05, "loss": 0.9973490142822266, "step": 130400 }, { "epoch": 1.5036432795416506, "grad_norm": 0.4453125, "learning_rate": 2.6830652550137432e-05, "loss": 0.9864173126220703, "step": 130600 }, { "epoch": 1.5059459646163655, "grad_norm": 0.7578125, "learning_rate": 2.682338098631492e-05, "loss": 0.9872917175292969, "step": 130800 }, { "epoch": 1.5082486496910805, "grad_norm": 0.64453125, "learning_rate": 2.68161094224924e-05, "loss": 0.9996871185302735, "step": 131000 }, { "epoch": 1.5105513347657955, "grad_norm": 0.98046875, "learning_rate": 2.6808837858669887e-05, "loss": 1.005075912475586, "step": 131200 }, { "epoch": 1.5128540198405103, "grad_norm": 0.93359375, "learning_rate": 2.6801566294847373e-05, "loss": 0.9876535034179688, "step": 131400 }, { "epoch": 1.5151567049152252, "grad_norm": 0.66015625, "learning_rate": 2.6794294731024855e-05, "loss": 0.9811707305908203, "step": 131600 }, { "epoch": 1.51745938998994, "grad_norm": 0.74609375, "learning_rate": 2.6787023167202338e-05, "loss": 0.9567855072021484, "step": 131800 }, { "epoch": 1.519762075064655, "grad_norm": 0.66796875, "learning_rate": 2.6779751603379824e-05, "loss": 0.9803247833251953, "step": 132000 }, { "epoch": 1.52206476013937, "grad_norm": 1.1171875, "learning_rate": 2.6772480039557306e-05, "loss": 0.9724285125732421, "step": 132200 }, { "epoch": 1.524367445214085, "grad_norm": 0.6328125, "learning_rate": 2.6765208475734792e-05, "loss": 0.9653998565673828, "step": 132400 }, { "epoch": 1.5266701302888, "grad_norm": 0.9765625, "learning_rate": 2.6757936911912278e-05, "loss": 0.9880249786376953, "step": 132600 }, { "epoch": 1.528972815363515, "grad_norm": 0.7421875, "learning_rate": 2.6750665348089764e-05, "loss": 0.9710153198242187, "step": 132800 }, { "epoch": 1.53127550043823, "grad_norm": 0.796875, "learning_rate": 2.6743393784267243e-05, "loss": 0.9638467407226563, "step": 133000 }, { "epoch": 1.5335781855129447, "grad_norm": 0.828125, "learning_rate": 2.673612222044473e-05, "loss": 0.9837078094482422, "step": 133200 }, { "epoch": 1.5358808705876597, "grad_norm": 0.54296875, "learning_rate": 2.6728850656622215e-05, "loss": 0.9877970886230468, "step": 133400 }, { "epoch": 1.5381835556623744, "grad_norm": 0.515625, "learning_rate": 2.6721579092799697e-05, "loss": 0.9861704254150391, "step": 133600 }, { "epoch": 1.5404862407370894, "grad_norm": 0.71875, "learning_rate": 2.6714307528977183e-05, "loss": 0.9800881958007812, "step": 133800 }, { "epoch": 1.5427889258118044, "grad_norm": 1.0, "learning_rate": 2.670703596515467e-05, "loss": 0.9763209533691406, "step": 134000 }, { "epoch": 1.5450916108865194, "grad_norm": 0.416015625, "learning_rate": 2.669976440133215e-05, "loss": 0.9747321319580078, "step": 134200 }, { "epoch": 1.5473942959612343, "grad_norm": 0.7265625, "learning_rate": 2.6692492837509634e-05, "loss": 0.9830812072753906, "step": 134400 }, { "epoch": 1.5496969810359493, "grad_norm": 0.7265625, "learning_rate": 2.668522127368712e-05, "loss": 0.967867660522461, "step": 134600 }, { "epoch": 1.5519996661106643, "grad_norm": 0.9296875, "learning_rate": 2.6677949709864603e-05, "loss": 0.9955473327636719, "step": 134800 }, { "epoch": 1.554302351185379, "grad_norm": 0.72265625, "learning_rate": 2.667067814604209e-05, "loss": 0.9771687316894532, "step": 135000 }, { "epoch": 1.556605036260094, "grad_norm": 0.98046875, "learning_rate": 2.6663406582219575e-05, "loss": 0.9583516693115235, "step": 135200 }, { "epoch": 1.5589077213348088, "grad_norm": 0.99609375, "learning_rate": 2.6656135018397057e-05, "loss": 0.9967800140380859, "step": 135400 }, { "epoch": 1.5612104064095238, "grad_norm": 0.57421875, "learning_rate": 2.664886345457454e-05, "loss": 0.9840859985351562, "step": 135600 }, { "epoch": 1.5635130914842388, "grad_norm": 0.671875, "learning_rate": 2.6641591890752026e-05, "loss": 0.9754515075683594, "step": 135800 }, { "epoch": 1.5658157765589538, "grad_norm": 0.921875, "learning_rate": 2.663432032692951e-05, "loss": 0.9733502960205078, "step": 136000 }, { "epoch": 1.5681184616336687, "grad_norm": 0.8046875, "learning_rate": 2.6627048763106994e-05, "loss": 0.9950527954101562, "step": 136200 }, { "epoch": 1.5704211467083837, "grad_norm": 1.140625, "learning_rate": 2.661977719928448e-05, "loss": 0.9778156280517578, "step": 136400 }, { "epoch": 1.5727238317830987, "grad_norm": 0.98828125, "learning_rate": 2.6612505635461966e-05, "loss": 0.9937000274658203, "step": 136600 }, { "epoch": 1.5750265168578135, "grad_norm": 0.4296875, "learning_rate": 2.6605234071639445e-05, "loss": 0.9916617584228515, "step": 136800 }, { "epoch": 1.5773292019325285, "grad_norm": 0.59375, "learning_rate": 2.659796250781693e-05, "loss": 0.9857948303222657, "step": 137000 }, { "epoch": 1.5796318870072432, "grad_norm": 1.09375, "learning_rate": 2.6590690943994417e-05, "loss": 0.9857929992675781, "step": 137200 }, { "epoch": 1.5819345720819582, "grad_norm": 0.458984375, "learning_rate": 2.65834193801719e-05, "loss": 0.9621226501464843, "step": 137400 }, { "epoch": 1.5842372571566732, "grad_norm": 0.71484375, "learning_rate": 2.6576147816349385e-05, "loss": 0.98962158203125, "step": 137600 }, { "epoch": 1.5865399422313882, "grad_norm": 0.4453125, "learning_rate": 2.656887625252687e-05, "loss": 0.981746826171875, "step": 137800 }, { "epoch": 1.5888426273061032, "grad_norm": 0.79296875, "learning_rate": 2.656160468870435e-05, "loss": 0.982820053100586, "step": 138000 }, { "epoch": 1.5911453123808181, "grad_norm": 0.46875, "learning_rate": 2.6554333124881836e-05, "loss": 0.9794469451904297, "step": 138200 }, { "epoch": 1.5934479974555331, "grad_norm": 1.0078125, "learning_rate": 2.6547061561059322e-05, "loss": 0.9850052642822266, "step": 138400 }, { "epoch": 1.5957506825302479, "grad_norm": 0.478515625, "learning_rate": 2.6539789997236808e-05, "loss": 0.9982978820800781, "step": 138600 }, { "epoch": 1.5980533676049629, "grad_norm": 0.74609375, "learning_rate": 2.653251843341429e-05, "loss": 0.9814372253417969, "step": 138800 }, { "epoch": 1.6003560526796778, "grad_norm": 0.65625, "learning_rate": 2.6525246869591776e-05, "loss": 0.9815452575683594, "step": 139000 }, { "epoch": 1.6026587377543926, "grad_norm": 0.52734375, "learning_rate": 2.6517975305769262e-05, "loss": 0.9756555938720703, "step": 139200 }, { "epoch": 1.6049614228291076, "grad_norm": 0.98046875, "learning_rate": 2.651070374194674e-05, "loss": 0.97823974609375, "step": 139400 }, { "epoch": 1.6072641079038226, "grad_norm": 0.94921875, "learning_rate": 2.6503432178124227e-05, "loss": 0.9964341735839843, "step": 139600 }, { "epoch": 1.6095667929785376, "grad_norm": 0.64453125, "learning_rate": 2.6496160614301713e-05, "loss": 0.9912190246582031, "step": 139800 }, { "epoch": 1.6118694780532525, "grad_norm": 0.57421875, "learning_rate": 2.6488889050479196e-05, "loss": 0.9697745513916015, "step": 140000 }, { "epoch": 1.6141721631279675, "grad_norm": 0.95703125, "learning_rate": 2.6481617486656682e-05, "loss": 0.9726390838623047, "step": 140200 }, { "epoch": 1.6164748482026825, "grad_norm": 0.73828125, "learning_rate": 2.6474345922834168e-05, "loss": 0.9908740997314454, "step": 140400 }, { "epoch": 1.6187775332773973, "grad_norm": 0.546875, "learning_rate": 2.6467074359011647e-05, "loss": 0.9849369049072265, "step": 140600 }, { "epoch": 1.6210802183521122, "grad_norm": 0.470703125, "learning_rate": 2.6459802795189133e-05, "loss": 0.9715933227539062, "step": 140800 }, { "epoch": 1.623382903426827, "grad_norm": 0.6953125, "learning_rate": 2.645253123136662e-05, "loss": 0.9683143615722656, "step": 141000 }, { "epoch": 1.625685588501542, "grad_norm": 0.77734375, "learning_rate": 2.64452596675441e-05, "loss": 1.0068618774414062, "step": 141200 }, { "epoch": 1.627988273576257, "grad_norm": 0.53125, "learning_rate": 2.6437988103721587e-05, "loss": 0.9583765411376953, "step": 141400 }, { "epoch": 1.630290958650972, "grad_norm": 0.67578125, "learning_rate": 2.6430716539899073e-05, "loss": 0.9848359680175781, "step": 141600 }, { "epoch": 1.632593643725687, "grad_norm": 0.76171875, "learning_rate": 2.642344497607656e-05, "loss": 0.9773321533203125, "step": 141800 }, { "epoch": 1.634896328800402, "grad_norm": 0.6953125, "learning_rate": 2.6416173412254038e-05, "loss": 0.9831598663330078, "step": 142000 }, { "epoch": 1.637199013875117, "grad_norm": 0.80078125, "learning_rate": 2.6408901848431524e-05, "loss": 0.9870728302001953, "step": 142200 }, { "epoch": 1.6395016989498317, "grad_norm": 0.66015625, "learning_rate": 2.640163028460901e-05, "loss": 0.9868105316162109, "step": 142400 }, { "epoch": 1.6418043840245466, "grad_norm": 0.640625, "learning_rate": 2.6394358720786492e-05, "loss": 1.0004991912841796, "step": 142600 }, { "epoch": 1.6441070690992614, "grad_norm": 1.296875, "learning_rate": 2.6387087156963978e-05, "loss": 0.9994534301757813, "step": 142800 }, { "epoch": 1.6464097541739764, "grad_norm": 0.671875, "learning_rate": 2.6379815593141464e-05, "loss": 0.9692447662353516, "step": 143000 }, { "epoch": 1.6487124392486914, "grad_norm": 5.09375, "learning_rate": 2.6372544029318943e-05, "loss": 0.9961146545410157, "step": 143200 }, { "epoch": 1.6510151243234064, "grad_norm": 0.67578125, "learning_rate": 2.636527246549643e-05, "loss": 0.9730229187011719, "step": 143400 }, { "epoch": 1.6533178093981213, "grad_norm": 1.7578125, "learning_rate": 2.6358000901673915e-05, "loss": 0.9857634735107422, "step": 143600 }, { "epoch": 1.6556204944728363, "grad_norm": 0.8828125, "learning_rate": 2.6350729337851398e-05, "loss": 0.9707545471191407, "step": 143800 }, { "epoch": 1.6579231795475513, "grad_norm": 0.95703125, "learning_rate": 2.6343457774028884e-05, "loss": 0.9886442565917969, "step": 144000 }, { "epoch": 1.660225864622266, "grad_norm": 0.9140625, "learning_rate": 2.633618621020637e-05, "loss": 0.9728403472900391, "step": 144200 }, { "epoch": 1.662528549696981, "grad_norm": 0.7421875, "learning_rate": 2.6328914646383852e-05, "loss": 0.9904885864257813, "step": 144400 }, { "epoch": 1.6648312347716958, "grad_norm": 1.015625, "learning_rate": 2.6321643082561335e-05, "loss": 0.9826412963867187, "step": 144600 }, { "epoch": 1.6671339198464108, "grad_norm": 0.8671875, "learning_rate": 2.631437151873882e-05, "loss": 0.977677001953125, "step": 144800 }, { "epoch": 1.6694366049211258, "grad_norm": 0.84765625, "learning_rate": 2.6307099954916306e-05, "loss": 0.9630680847167968, "step": 145000 }, { "epoch": 1.6717392899958408, "grad_norm": 0.73046875, "learning_rate": 2.629982839109379e-05, "loss": 0.9929466247558594, "step": 145200 }, { "epoch": 1.6740419750705557, "grad_norm": 2.21875, "learning_rate": 2.6292556827271275e-05, "loss": 0.97507080078125, "step": 145400 }, { "epoch": 1.6763446601452707, "grad_norm": 0.54296875, "learning_rate": 2.628528526344876e-05, "loss": 0.9925634765625, "step": 145600 }, { "epoch": 1.6786473452199857, "grad_norm": 1.484375, "learning_rate": 2.627801369962624e-05, "loss": 0.9717263031005859, "step": 145800 }, { "epoch": 1.6809500302947005, "grad_norm": 0.62890625, "learning_rate": 2.6270742135803726e-05, "loss": 0.9731719207763672, "step": 146000 }, { "epoch": 1.6832527153694155, "grad_norm": 0.6015625, "learning_rate": 2.6263470571981212e-05, "loss": 0.9792316436767579, "step": 146200 }, { "epoch": 1.6855554004441304, "grad_norm": 0.5, "learning_rate": 2.6256199008158694e-05, "loss": 0.9754666900634765, "step": 146400 }, { "epoch": 1.6878580855188452, "grad_norm": 0.578125, "learning_rate": 2.624892744433618e-05, "loss": 0.9769933319091797, "step": 146600 }, { "epoch": 1.6901607705935602, "grad_norm": 0.73828125, "learning_rate": 2.6241655880513666e-05, "loss": 0.9838820648193359, "step": 146800 }, { "epoch": 1.6924634556682752, "grad_norm": 0.5390625, "learning_rate": 2.6234384316691145e-05, "loss": 0.9945056915283204, "step": 147000 }, { "epoch": 1.6947661407429901, "grad_norm": 0.859375, "learning_rate": 2.622711275286863e-05, "loss": 0.9864218139648437, "step": 147200 }, { "epoch": 1.6970688258177051, "grad_norm": 0.67578125, "learning_rate": 2.6219841189046117e-05, "loss": 0.9742472839355468, "step": 147400 }, { "epoch": 1.6993715108924201, "grad_norm": 0.67578125, "learning_rate": 2.6212569625223603e-05, "loss": 0.9858525085449219, "step": 147600 }, { "epoch": 1.7016741959671349, "grad_norm": 0.890625, "learning_rate": 2.6205298061401085e-05, "loss": 0.9894911956787109, "step": 147800 }, { "epoch": 1.7039768810418499, "grad_norm": 0.90625, "learning_rate": 2.619802649757857e-05, "loss": 0.9979306030273437, "step": 148000 }, { "epoch": 1.7062795661165648, "grad_norm": 0.5390625, "learning_rate": 2.6190754933756057e-05, "loss": 0.9839297485351562, "step": 148200 }, { "epoch": 1.7085822511912796, "grad_norm": 0.66796875, "learning_rate": 2.6183483369933536e-05, "loss": 0.9801649475097656, "step": 148400 }, { "epoch": 1.7108849362659946, "grad_norm": 0.734375, "learning_rate": 2.6176211806111022e-05, "loss": 0.9773529815673828, "step": 148600 }, { "epoch": 1.7131876213407096, "grad_norm": 0.4453125, "learning_rate": 2.6168940242288508e-05, "loss": 0.9774404907226563, "step": 148800 }, { "epoch": 1.7154903064154245, "grad_norm": 0.8515625, "learning_rate": 2.616166867846599e-05, "loss": 0.9896322631835938, "step": 149000 }, { "epoch": 1.7177929914901395, "grad_norm": 0.6796875, "learning_rate": 2.6154397114643477e-05, "loss": 0.9660794067382813, "step": 149200 }, { "epoch": 1.7200956765648545, "grad_norm": 0.640625, "learning_rate": 2.6147125550820963e-05, "loss": 0.9710120391845704, "step": 149400 }, { "epoch": 1.7223983616395695, "grad_norm": 0.609375, "learning_rate": 2.6139853986998442e-05, "loss": 0.9865705871582031, "step": 149600 }, { "epoch": 1.7247010467142843, "grad_norm": 0.84375, "learning_rate": 2.6132582423175928e-05, "loss": 0.9635546875, "step": 149800 }, { "epoch": 1.7270037317889992, "grad_norm": 0.416015625, "learning_rate": 2.6125310859353414e-05, "loss": 0.9851200866699219, "step": 150000 }, { "epoch": 1.729306416863714, "grad_norm": 1.2578125, "learning_rate": 2.6118039295530896e-05, "loss": 0.9768991088867187, "step": 150200 }, { "epoch": 1.731609101938429, "grad_norm": 0.59375, "learning_rate": 2.6110767731708382e-05, "loss": 0.9886154174804688, "step": 150400 }, { "epoch": 1.733911787013144, "grad_norm": 0.5390625, "learning_rate": 2.6103496167885868e-05, "loss": 0.977115249633789, "step": 150600 }, { "epoch": 1.736214472087859, "grad_norm": 0.58984375, "learning_rate": 2.609622460406335e-05, "loss": 0.9892723846435547, "step": 150800 }, { "epoch": 1.738517157162574, "grad_norm": 0.796875, "learning_rate": 2.6088953040240833e-05, "loss": 1.0145347595214844, "step": 151000 }, { "epoch": 1.740819842237289, "grad_norm": 0.77734375, "learning_rate": 2.608168147641832e-05, "loss": 0.9738581848144531, "step": 151200 }, { "epoch": 1.743122527312004, "grad_norm": 1.21875, "learning_rate": 2.6074409912595805e-05, "loss": 0.9952706146240234, "step": 151400 }, { "epoch": 1.7454252123867187, "grad_norm": 0.5078125, "learning_rate": 2.6067138348773287e-05, "loss": 0.9953517913818359, "step": 151600 }, { "epoch": 1.7477278974614336, "grad_norm": 0.63671875, "learning_rate": 2.6059866784950773e-05, "loss": 0.9769023895263672, "step": 151800 }, { "epoch": 1.7500305825361484, "grad_norm": 0.65625, "learning_rate": 2.605259522112826e-05, "loss": 1.0000345611572266, "step": 152000 }, { "epoch": 1.7523332676108634, "grad_norm": 0.578125, "learning_rate": 2.6045323657305738e-05, "loss": 0.9734282684326172, "step": 152200 }, { "epoch": 1.7546359526855784, "grad_norm": 0.62890625, "learning_rate": 2.6038052093483224e-05, "loss": 0.983162841796875, "step": 152400 }, { "epoch": 1.7569386377602934, "grad_norm": 0.6484375, "learning_rate": 2.603078052966071e-05, "loss": 0.9792951202392578, "step": 152600 }, { "epoch": 1.7592413228350083, "grad_norm": 0.5625, "learning_rate": 2.6023508965838193e-05, "loss": 0.9730397033691406, "step": 152800 }, { "epoch": 1.7615440079097233, "grad_norm": 0.53515625, "learning_rate": 2.601623740201568e-05, "loss": 0.9625283050537109, "step": 153000 }, { "epoch": 1.7638466929844383, "grad_norm": 0.44140625, "learning_rate": 2.6008965838193164e-05, "loss": 0.9787934112548828, "step": 153200 }, { "epoch": 1.766149378059153, "grad_norm": 1.1875, "learning_rate": 2.6001694274370647e-05, "loss": 0.9870194244384766, "step": 153400 }, { "epoch": 1.768452063133868, "grad_norm": 1.046875, "learning_rate": 2.599442271054813e-05, "loss": 0.9825399017333984, "step": 153600 }, { "epoch": 1.7707547482085828, "grad_norm": 0.8046875, "learning_rate": 2.5987151146725615e-05, "loss": 0.9877588653564453, "step": 153800 }, { "epoch": 1.7730574332832978, "grad_norm": 0.96875, "learning_rate": 2.59798795829031e-05, "loss": 0.981055679321289, "step": 154000 }, { "epoch": 1.7753601183580128, "grad_norm": 0.90625, "learning_rate": 2.5972608019080584e-05, "loss": 0.9929129028320313, "step": 154200 }, { "epoch": 1.7776628034327278, "grad_norm": 1.0390625, "learning_rate": 2.596533645525807e-05, "loss": 0.975859375, "step": 154400 }, { "epoch": 1.7799654885074427, "grad_norm": 0.51171875, "learning_rate": 2.5958064891435552e-05, "loss": 0.9847544860839844, "step": 154600 }, { "epoch": 1.7822681735821577, "grad_norm": 0.60546875, "learning_rate": 2.5950793327613035e-05, "loss": 0.9796549224853516, "step": 154800 }, { "epoch": 1.7845708586568727, "grad_norm": 0.53515625, "learning_rate": 2.594352176379052e-05, "loss": 0.9731486511230468, "step": 155000 }, { "epoch": 1.7868735437315875, "grad_norm": 0.69921875, "learning_rate": 2.5936250199968007e-05, "loss": 0.9948165893554688, "step": 155200 }, { "epoch": 1.7891762288063024, "grad_norm": 0.625, "learning_rate": 2.592897863614549e-05, "loss": 0.9961344909667968, "step": 155400 }, { "epoch": 1.7914789138810174, "grad_norm": 0.8515625, "learning_rate": 2.5921707072322975e-05, "loss": 0.9734591674804688, "step": 155600 }, { "epoch": 1.7937815989557322, "grad_norm": 1.484375, "learning_rate": 2.591443550850046e-05, "loss": 0.956961669921875, "step": 155800 }, { "epoch": 1.7960842840304472, "grad_norm": 0.51953125, "learning_rate": 2.590716394467794e-05, "loss": 0.9658924865722657, "step": 156000 }, { "epoch": 1.7983869691051622, "grad_norm": 0.890625, "learning_rate": 2.5899892380855426e-05, "loss": 0.9590577697753906, "step": 156200 }, { "epoch": 1.8006896541798771, "grad_norm": 0.68359375, "learning_rate": 2.5892620817032912e-05, "loss": 1.0172974395751953, "step": 156400 }, { "epoch": 1.8029923392545921, "grad_norm": 0.65234375, "learning_rate": 2.5885349253210398e-05, "loss": 0.9836770629882813, "step": 156600 }, { "epoch": 1.805295024329307, "grad_norm": 1.96875, "learning_rate": 2.587807768938788e-05, "loss": 0.990052719116211, "step": 156800 }, { "epoch": 1.807597709404022, "grad_norm": 0.60546875, "learning_rate": 2.5870806125565366e-05, "loss": 0.9714091491699218, "step": 157000 }, { "epoch": 1.8099003944787369, "grad_norm": 0.65625, "learning_rate": 2.586353456174285e-05, "loss": 0.9685219573974609, "step": 157200 }, { "epoch": 1.8122030795534518, "grad_norm": 0.86328125, "learning_rate": 2.585626299792033e-05, "loss": 0.9915869140625, "step": 157400 }, { "epoch": 1.8145057646281666, "grad_norm": 0.671875, "learning_rate": 2.5848991434097817e-05, "loss": 0.9873688507080078, "step": 157600 }, { "epoch": 1.8168084497028816, "grad_norm": 0.78125, "learning_rate": 2.5841719870275303e-05, "loss": 0.9832802581787109, "step": 157800 }, { "epoch": 1.8191111347775966, "grad_norm": 0.435546875, "learning_rate": 2.5834448306452786e-05, "loss": 0.9880329895019532, "step": 158000 }, { "epoch": 1.8214138198523115, "grad_norm": 0.466796875, "learning_rate": 2.582717674263027e-05, "loss": 0.9875634765625, "step": 158200 }, { "epoch": 1.8237165049270265, "grad_norm": 0.51171875, "learning_rate": 2.5819905178807758e-05, "loss": 0.9814795684814454, "step": 158400 }, { "epoch": 1.8260191900017415, "grad_norm": 0.69140625, "learning_rate": 2.5812633614985237e-05, "loss": 0.9618077850341797, "step": 158600 }, { "epoch": 1.8283218750764565, "grad_norm": 0.79296875, "learning_rate": 2.5805362051162723e-05, "loss": 0.9954774475097656, "step": 158800 }, { "epoch": 1.8306245601511713, "grad_norm": 0.71875, "learning_rate": 2.579809048734021e-05, "loss": 0.992311782836914, "step": 159000 }, { "epoch": 1.8329272452258862, "grad_norm": 0.55859375, "learning_rate": 2.5790818923517694e-05, "loss": 0.9816593933105469, "step": 159200 }, { "epoch": 1.835229930300601, "grad_norm": 0.5234375, "learning_rate": 2.5783547359695177e-05, "loss": 0.9977922821044922, "step": 159400 }, { "epoch": 1.837532615375316, "grad_norm": 0.73046875, "learning_rate": 2.5776275795872663e-05, "loss": 0.9930438995361328, "step": 159600 }, { "epoch": 1.839835300450031, "grad_norm": 0.640625, "learning_rate": 2.5769004232050145e-05, "loss": 0.9736163330078125, "step": 159800 }, { "epoch": 1.842137985524746, "grad_norm": 0.63671875, "learning_rate": 2.5761732668227628e-05, "loss": 0.9892105865478515, "step": 160000 }, { "epoch": 1.844440670599461, "grad_norm": 0.7265625, "learning_rate": 2.5754461104405114e-05, "loss": 0.9836799621582031, "step": 160200 }, { "epoch": 1.846743355674176, "grad_norm": 0.609375, "learning_rate": 2.57471895405826e-05, "loss": 0.9932373809814453, "step": 160400 }, { "epoch": 1.849046040748891, "grad_norm": 0.5390625, "learning_rate": 2.5739917976760082e-05, "loss": 0.9650992584228516, "step": 160600 }, { "epoch": 1.8513487258236057, "grad_norm": 0.96875, "learning_rate": 2.5732646412937568e-05, "loss": 0.979215087890625, "step": 160800 }, { "epoch": 1.8536514108983206, "grad_norm": 1.09375, "learning_rate": 2.572537484911505e-05, "loss": 0.9821718597412109, "step": 161000 }, { "epoch": 1.8559540959730354, "grad_norm": 0.62109375, "learning_rate": 2.5718103285292533e-05, "loss": 0.9929822540283203, "step": 161200 }, { "epoch": 1.8582567810477504, "grad_norm": 0.7265625, "learning_rate": 2.571083172147002e-05, "loss": 0.9742303466796876, "step": 161400 }, { "epoch": 1.8605594661224654, "grad_norm": 0.81640625, "learning_rate": 2.5703560157647505e-05, "loss": 0.9975980377197265, "step": 161600 }, { "epoch": 1.8628621511971803, "grad_norm": 0.55078125, "learning_rate": 2.5696288593824988e-05, "loss": 0.9791291809082031, "step": 161800 }, { "epoch": 1.8651648362718953, "grad_norm": 0.478515625, "learning_rate": 2.5689017030002474e-05, "loss": 0.9771806335449219, "step": 162000 }, { "epoch": 1.8674675213466103, "grad_norm": 0.7109375, "learning_rate": 2.568174546617996e-05, "loss": 0.9976700592041016, "step": 162200 }, { "epoch": 1.8697702064213253, "grad_norm": 0.435546875, "learning_rate": 2.5674473902357442e-05, "loss": 0.9705537414550781, "step": 162400 }, { "epoch": 1.87207289149604, "grad_norm": 0.9296875, "learning_rate": 2.5667202338534924e-05, "loss": 1.0070448303222657, "step": 162600 }, { "epoch": 1.874375576570755, "grad_norm": 1.0390625, "learning_rate": 2.565993077471241e-05, "loss": 0.96590087890625, "step": 162800 }, { "epoch": 1.87667826164547, "grad_norm": 1.0234375, "learning_rate": 2.5652659210889896e-05, "loss": 0.9896265411376953, "step": 163000 }, { "epoch": 1.8789809467201848, "grad_norm": 0.640625, "learning_rate": 2.564538764706738e-05, "loss": 0.9813925170898438, "step": 163200 }, { "epoch": 1.8812836317948998, "grad_norm": 0.466796875, "learning_rate": 2.5638116083244865e-05, "loss": 0.9730363464355469, "step": 163400 }, { "epoch": 1.8835863168696148, "grad_norm": 0.71484375, "learning_rate": 2.5630844519422347e-05, "loss": 0.9983138275146485, "step": 163600 }, { "epoch": 1.8858890019443297, "grad_norm": 1.0546875, "learning_rate": 2.562357295559983e-05, "loss": 0.9798451232910156, "step": 163800 }, { "epoch": 1.8881916870190447, "grad_norm": 0.671875, "learning_rate": 2.5616301391777316e-05, "loss": 0.9604888916015625, "step": 164000 }, { "epoch": 1.8904943720937597, "grad_norm": 0.67578125, "learning_rate": 2.56090298279548e-05, "loss": 0.9828205871582031, "step": 164200 }, { "epoch": 1.8927970571684745, "grad_norm": 0.62109375, "learning_rate": 2.5601758264132284e-05, "loss": 0.9900843811035156, "step": 164400 }, { "epoch": 1.8950997422431894, "grad_norm": 0.55078125, "learning_rate": 2.559448670030977e-05, "loss": 0.9711660003662109, "step": 164600 }, { "epoch": 1.8974024273179044, "grad_norm": 0.88671875, "learning_rate": 2.5587215136487253e-05, "loss": 0.9848336791992187, "step": 164800 }, { "epoch": 1.8997051123926192, "grad_norm": 0.439453125, "learning_rate": 2.557994357266474e-05, "loss": 1.0130525207519532, "step": 165000 }, { "epoch": 1.9020077974673342, "grad_norm": 0.50390625, "learning_rate": 2.557267200884222e-05, "loss": 0.969343032836914, "step": 165200 }, { "epoch": 1.9043104825420492, "grad_norm": 0.63671875, "learning_rate": 2.5565400445019707e-05, "loss": 0.9901512908935547, "step": 165400 }, { "epoch": 1.9066131676167641, "grad_norm": 0.87109375, "learning_rate": 2.5558128881197193e-05, "loss": 0.966179428100586, "step": 165600 }, { "epoch": 1.9089158526914791, "grad_norm": 0.9140625, "learning_rate": 2.5550857317374675e-05, "loss": 0.983575439453125, "step": 165800 }, { "epoch": 1.911218537766194, "grad_norm": 1.1328125, "learning_rate": 2.554358575355216e-05, "loss": 0.9980619812011718, "step": 166000 }, { "epoch": 1.913521222840909, "grad_norm": 0.53515625, "learning_rate": 2.5536314189729644e-05, "loss": 0.9869134521484375, "step": 166200 }, { "epoch": 1.9158239079156238, "grad_norm": 0.64453125, "learning_rate": 2.5529042625907126e-05, "loss": 0.9981081390380859, "step": 166400 }, { "epoch": 1.9181265929903388, "grad_norm": 0.47265625, "learning_rate": 2.5521771062084612e-05, "loss": 0.9734851837158203, "step": 166600 }, { "epoch": 1.9204292780650536, "grad_norm": 0.75390625, "learning_rate": 2.5514499498262098e-05, "loss": 0.9968444061279297, "step": 166800 }, { "epoch": 1.9227319631397686, "grad_norm": 0.99609375, "learning_rate": 2.550722793443958e-05, "loss": 0.9921951293945312, "step": 167000 }, { "epoch": 1.9250346482144836, "grad_norm": 0.52734375, "learning_rate": 2.5499956370617067e-05, "loss": 0.9820545959472656, "step": 167200 }, { "epoch": 1.9273373332891985, "grad_norm": 0.57421875, "learning_rate": 2.549268480679455e-05, "loss": 0.9863339233398437, "step": 167400 }, { "epoch": 1.9296400183639135, "grad_norm": 0.6171875, "learning_rate": 2.548541324297203e-05, "loss": 0.963076400756836, "step": 167600 }, { "epoch": 1.9319427034386285, "grad_norm": 0.515625, "learning_rate": 2.5478141679149518e-05, "loss": 0.9745853424072266, "step": 167800 }, { "epoch": 1.9342453885133435, "grad_norm": 1.8125, "learning_rate": 2.5470870115327003e-05, "loss": 0.9626667022705078, "step": 168000 }, { "epoch": 1.9365480735880582, "grad_norm": 0.87109375, "learning_rate": 2.546359855150449e-05, "loss": 0.9721767425537109, "step": 168200 }, { "epoch": 1.9388507586627732, "grad_norm": 0.55078125, "learning_rate": 2.5456326987681972e-05, "loss": 0.9810872650146485, "step": 168400 }, { "epoch": 1.941153443737488, "grad_norm": 0.6953125, "learning_rate": 2.5449055423859458e-05, "loss": 0.9774066162109375, "step": 168600 }, { "epoch": 1.943456128812203, "grad_norm": 0.49609375, "learning_rate": 2.544178386003694e-05, "loss": 0.98538818359375, "step": 168800 }, { "epoch": 1.945758813886918, "grad_norm": 0.63671875, "learning_rate": 2.5434512296214423e-05, "loss": 0.9620954895019531, "step": 169000 }, { "epoch": 1.948061498961633, "grad_norm": 0.734375, "learning_rate": 2.542724073239191e-05, "loss": 0.9863482666015625, "step": 169200 }, { "epoch": 1.950364184036348, "grad_norm": 0.71875, "learning_rate": 2.5419969168569395e-05, "loss": 0.9762551879882813, "step": 169400 }, { "epoch": 1.952666869111063, "grad_norm": 0.7265625, "learning_rate": 2.5412697604746877e-05, "loss": 0.966393051147461, "step": 169600 }, { "epoch": 1.954969554185778, "grad_norm": 0.69140625, "learning_rate": 2.5405426040924363e-05, "loss": 1.0133824157714844, "step": 169800 }, { "epoch": 1.9572722392604927, "grad_norm": 0.765625, "learning_rate": 2.5398154477101846e-05, "loss": 0.9961969757080078, "step": 170000 }, { "epoch": 1.9595749243352076, "grad_norm": 0.51171875, "learning_rate": 2.5390882913279328e-05, "loss": 0.9705589294433594, "step": 170200 }, { "epoch": 1.9618776094099224, "grad_norm": 0.76171875, "learning_rate": 2.5383611349456814e-05, "loss": 0.9754343414306641, "step": 170400 }, { "epoch": 1.9641802944846374, "grad_norm": 0.78125, "learning_rate": 2.53763397856343e-05, "loss": 1.0036404418945313, "step": 170600 }, { "epoch": 1.9664829795593524, "grad_norm": 0.78515625, "learning_rate": 2.5369068221811783e-05, "loss": 0.9673897552490235, "step": 170800 }, { "epoch": 1.9687856646340673, "grad_norm": 0.66796875, "learning_rate": 2.536179665798927e-05, "loss": 0.9643704223632813, "step": 171000 }, { "epoch": 1.9710883497087823, "grad_norm": 0.59765625, "learning_rate": 2.535452509416675e-05, "loss": 0.9760980987548828, "step": 171200 }, { "epoch": 1.9733910347834973, "grad_norm": 1.0546875, "learning_rate": 2.5347253530344237e-05, "loss": 1.0071582794189453, "step": 171400 }, { "epoch": 1.9756937198582123, "grad_norm": 0.51171875, "learning_rate": 2.533998196652172e-05, "loss": 0.9611239624023438, "step": 171600 }, { "epoch": 1.977996404932927, "grad_norm": 0.71875, "learning_rate": 2.5332710402699205e-05, "loss": 1.0153284454345703, "step": 171800 }, { "epoch": 1.980299090007642, "grad_norm": 1.5, "learning_rate": 2.532543883887669e-05, "loss": 0.9687615966796875, "step": 172000 }, { "epoch": 1.982601775082357, "grad_norm": 0.71484375, "learning_rate": 2.5318167275054174e-05, "loss": 0.9706464385986329, "step": 172200 }, { "epoch": 1.9849044601570718, "grad_norm": 1.1171875, "learning_rate": 2.531089571123166e-05, "loss": 0.9883045959472656, "step": 172400 }, { "epoch": 1.9872071452317868, "grad_norm": 0.91796875, "learning_rate": 2.5303624147409142e-05, "loss": 1.0035950469970703, "step": 172600 }, { "epoch": 1.9895098303065017, "grad_norm": 0.96484375, "learning_rate": 2.5296352583586625e-05, "loss": 0.9956815338134766, "step": 172800 }, { "epoch": 1.9918125153812167, "grad_norm": 0.7421875, "learning_rate": 2.528908101976411e-05, "loss": 0.9859121704101562, "step": 173000 }, { "epoch": 1.9941152004559317, "grad_norm": 0.859375, "learning_rate": 2.5281809455941597e-05, "loss": 0.9893330383300781, "step": 173200 }, { "epoch": 1.9964178855306467, "grad_norm": 0.68359375, "learning_rate": 2.527453789211908e-05, "loss": 0.9664070892333985, "step": 173400 }, { "epoch": 1.9987205706053617, "grad_norm": 0.5234375, "learning_rate": 2.5267266328296565e-05, "loss": 0.9660589599609375, "step": 173600 }, { "epoch": 2.0, "eval_loss": NaN, "eval_runtime": 429.7683, "eval_samples_per_second": 65.991, "eval_steps_per_second": 32.997, "step": 173712 }, { "epoch": 2.0010131814328744, "grad_norm": 0.71875, "learning_rate": 2.5259994764474048e-05, "loss": 0.9948661804199219, "step": 173800 }, { "epoch": 2.0033158665075894, "grad_norm": 0.65234375, "learning_rate": 2.5252723200651533e-05, "loss": 0.974677505493164, "step": 174000 }, { "epoch": 2.0056185515823044, "grad_norm": 0.68359375, "learning_rate": 2.5245451636829016e-05, "loss": 0.9709995269775391, "step": 174200 }, { "epoch": 2.0079212366570194, "grad_norm": 0.8203125, "learning_rate": 2.5238180073006502e-05, "loss": 0.9784161376953125, "step": 174400 }, { "epoch": 2.0102239217317344, "grad_norm": 0.5703125, "learning_rate": 2.5230908509183988e-05, "loss": 0.9698686218261718, "step": 174600 }, { "epoch": 2.0125266068064493, "grad_norm": 0.65234375, "learning_rate": 2.522363694536147e-05, "loss": 0.9923031616210938, "step": 174800 }, { "epoch": 2.0148292918811643, "grad_norm": 0.72265625, "learning_rate": 2.5216365381538953e-05, "loss": 0.9968160247802734, "step": 175000 }, { "epoch": 2.0171319769558793, "grad_norm": 0.484375, "learning_rate": 2.520909381771644e-05, "loss": 0.986888656616211, "step": 175200 }, { "epoch": 2.019434662030594, "grad_norm": 1.1171875, "learning_rate": 2.520182225389392e-05, "loss": 0.9929759979248047, "step": 175400 }, { "epoch": 2.021737347105309, "grad_norm": 0.75, "learning_rate": 2.5194550690071407e-05, "loss": 0.9717521667480469, "step": 175600 }, { "epoch": 2.024040032180024, "grad_norm": 0.89453125, "learning_rate": 2.5187279126248893e-05, "loss": 0.9931996917724609, "step": 175800 }, { "epoch": 2.026342717254739, "grad_norm": 0.73046875, "learning_rate": 2.5180007562426376e-05, "loss": 0.9702210998535157, "step": 176000 }, { "epoch": 2.028645402329454, "grad_norm": 1.2734375, "learning_rate": 2.517273599860386e-05, "loss": 0.9971956634521484, "step": 176200 }, { "epoch": 2.0309480874041688, "grad_norm": 0.625, "learning_rate": 2.5165464434781344e-05, "loss": 0.971846923828125, "step": 176400 }, { "epoch": 2.0332507724788837, "grad_norm": 0.87890625, "learning_rate": 2.5158192870958827e-05, "loss": 0.9721129608154296, "step": 176600 }, { "epoch": 2.0355534575535987, "grad_norm": 1.109375, "learning_rate": 2.5150921307136313e-05, "loss": 0.9739250183105469, "step": 176800 }, { "epoch": 2.0378561426283137, "grad_norm": 1.578125, "learning_rate": 2.51436497433138e-05, "loss": 0.9803957366943359, "step": 177000 }, { "epoch": 2.0401588277030283, "grad_norm": 0.45703125, "learning_rate": 2.5136378179491284e-05, "loss": 0.9933158874511718, "step": 177200 }, { "epoch": 2.0424615127777432, "grad_norm": 0.5234375, "learning_rate": 2.5129106615668767e-05, "loss": 1.0045361328125, "step": 177400 }, { "epoch": 2.044764197852458, "grad_norm": 0.796875, "learning_rate": 2.512183505184625e-05, "loss": 0.9811223602294922, "step": 177600 }, { "epoch": 2.047066882927173, "grad_norm": 0.65625, "learning_rate": 2.5114563488023735e-05, "loss": 0.9679241943359375, "step": 177800 }, { "epoch": 2.049369568001888, "grad_norm": 1.0703125, "learning_rate": 2.5107291924201218e-05, "loss": 0.9778891754150391, "step": 178000 }, { "epoch": 2.051672253076603, "grad_norm": 0.8828125, "learning_rate": 2.5100020360378704e-05, "loss": 0.9766893768310547, "step": 178200 }, { "epoch": 2.053974938151318, "grad_norm": 0.451171875, "learning_rate": 2.509274879655619e-05, "loss": 0.974738998413086, "step": 178400 }, { "epoch": 2.056277623226033, "grad_norm": 0.609375, "learning_rate": 2.5085477232733672e-05, "loss": 0.9749568176269531, "step": 178600 }, { "epoch": 2.058580308300748, "grad_norm": 1.0859375, "learning_rate": 2.5078205668911158e-05, "loss": 0.9782068634033203, "step": 178800 }, { "epoch": 2.0608829933754627, "grad_norm": 0.59765625, "learning_rate": 2.507093410508864e-05, "loss": 0.9693759155273437, "step": 179000 }, { "epoch": 2.0631856784501776, "grad_norm": 0.62109375, "learning_rate": 2.5063662541266123e-05, "loss": 0.9943150329589844, "step": 179200 }, { "epoch": 2.0654883635248926, "grad_norm": 0.69921875, "learning_rate": 2.505639097744361e-05, "loss": 0.9823705291748047, "step": 179400 }, { "epoch": 2.0677910485996076, "grad_norm": 0.640625, "learning_rate": 2.5049119413621095e-05, "loss": 0.989997787475586, "step": 179600 }, { "epoch": 2.0700937336743226, "grad_norm": 1.25, "learning_rate": 2.504184784979858e-05, "loss": 0.9868365478515625, "step": 179800 }, { "epoch": 2.0723964187490376, "grad_norm": 0.73046875, "learning_rate": 2.5034576285976063e-05, "loss": 0.981561050415039, "step": 180000 }, { "epoch": 2.0746991038237526, "grad_norm": 1.0078125, "learning_rate": 2.5027304722153546e-05, "loss": 0.9862503814697265, "step": 180200 }, { "epoch": 2.0770017888984675, "grad_norm": 0.640625, "learning_rate": 2.5020033158331032e-05, "loss": 0.9771318054199218, "step": 180400 }, { "epoch": 2.0793044739731825, "grad_norm": 0.60546875, "learning_rate": 2.5012761594508514e-05, "loss": 0.9810347747802735, "step": 180600 }, { "epoch": 2.0816071590478975, "grad_norm": 0.59765625, "learning_rate": 2.5005490030686e-05, "loss": 0.9873623657226562, "step": 180800 }, { "epoch": 2.083909844122612, "grad_norm": 0.67578125, "learning_rate": 2.4998218466863486e-05, "loss": 0.9683272552490234, "step": 181000 }, { "epoch": 2.086212529197327, "grad_norm": 0.482421875, "learning_rate": 2.499094690304097e-05, "loss": 0.9873902130126954, "step": 181200 }, { "epoch": 2.088515214272042, "grad_norm": 0.578125, "learning_rate": 2.498367533921845e-05, "loss": 0.966907958984375, "step": 181400 }, { "epoch": 2.090817899346757, "grad_norm": 0.515625, "learning_rate": 2.4976403775395937e-05, "loss": 0.9876545715332031, "step": 181600 }, { "epoch": 2.093120584421472, "grad_norm": 2.8125, "learning_rate": 2.496913221157342e-05, "loss": 0.9763893890380859, "step": 181800 }, { "epoch": 2.095423269496187, "grad_norm": 0.609375, "learning_rate": 2.4961860647750906e-05, "loss": 0.9983731842041016, "step": 182000 }, { "epoch": 2.097725954570902, "grad_norm": 0.74609375, "learning_rate": 2.495458908392839e-05, "loss": 0.978978271484375, "step": 182200 }, { "epoch": 2.100028639645617, "grad_norm": 0.953125, "learning_rate": 2.4947317520105874e-05, "loss": 0.965992431640625, "step": 182400 }, { "epoch": 2.102331324720332, "grad_norm": 0.4609375, "learning_rate": 2.494004595628336e-05, "loss": 0.9818271636962891, "step": 182600 }, { "epoch": 2.1046340097950464, "grad_norm": 0.61328125, "learning_rate": 2.4932774392460842e-05, "loss": 0.9539933013916015, "step": 182800 }, { "epoch": 2.1069366948697614, "grad_norm": 0.65234375, "learning_rate": 2.492550282863833e-05, "loss": 1.0096530151367187, "step": 183000 }, { "epoch": 2.1092393799444764, "grad_norm": 0.73828125, "learning_rate": 2.491823126481581e-05, "loss": 0.9892758178710938, "step": 183200 }, { "epoch": 2.1115420650191914, "grad_norm": 0.6328125, "learning_rate": 2.4910959700993297e-05, "loss": 0.9912564086914063, "step": 183400 }, { "epoch": 2.1138447500939064, "grad_norm": 0.53125, "learning_rate": 2.4903688137170783e-05, "loss": 0.9664544677734375, "step": 183600 }, { "epoch": 2.1161474351686214, "grad_norm": 0.5390625, "learning_rate": 2.4896416573348265e-05, "loss": 0.9713141632080078, "step": 183800 }, { "epoch": 2.1184501202433363, "grad_norm": 0.5546875, "learning_rate": 2.4889145009525748e-05, "loss": 0.9756626892089844, "step": 184000 }, { "epoch": 2.1207528053180513, "grad_norm": 0.408203125, "learning_rate": 2.4881873445703234e-05, "loss": 0.97317626953125, "step": 184200 }, { "epoch": 2.1230554903927663, "grad_norm": 0.921875, "learning_rate": 2.4874601881880716e-05, "loss": 0.9787543487548828, "step": 184400 }, { "epoch": 2.125358175467481, "grad_norm": 0.9453125, "learning_rate": 2.4867330318058202e-05, "loss": 0.9660845184326172, "step": 184600 }, { "epoch": 2.127660860542196, "grad_norm": 0.71484375, "learning_rate": 2.4860058754235688e-05, "loss": 0.9829474639892578, "step": 184800 }, { "epoch": 2.129963545616911, "grad_norm": 0.466796875, "learning_rate": 2.485278719041317e-05, "loss": 0.9686710357666015, "step": 185000 }, { "epoch": 2.132266230691626, "grad_norm": 0.69921875, "learning_rate": 2.4845515626590653e-05, "loss": 0.9558204650878906, "step": 185200 }, { "epoch": 2.134568915766341, "grad_norm": 1.1484375, "learning_rate": 2.483824406276814e-05, "loss": 0.9875593566894532, "step": 185400 }, { "epoch": 2.1368716008410558, "grad_norm": 0.6171875, "learning_rate": 2.4830972498945625e-05, "loss": 1.0049014282226563, "step": 185600 }, { "epoch": 2.1391742859157707, "grad_norm": 0.953125, "learning_rate": 2.4823700935123107e-05, "loss": 0.9857121276855468, "step": 185800 }, { "epoch": 2.1414769709904857, "grad_norm": 0.5, "learning_rate": 2.4816429371300593e-05, "loss": 0.9936911010742188, "step": 186000 }, { "epoch": 2.1437796560652007, "grad_norm": 0.416015625, "learning_rate": 2.480915780747808e-05, "loss": 0.9867401885986328, "step": 186200 }, { "epoch": 2.1460823411399153, "grad_norm": 0.7265625, "learning_rate": 2.4801886243655562e-05, "loss": 0.9839734649658203, "step": 186400 }, { "epoch": 2.1483850262146302, "grad_norm": 0.63671875, "learning_rate": 2.4794614679833044e-05, "loss": 0.9782057189941407, "step": 186600 }, { "epoch": 2.150687711289345, "grad_norm": 3.546875, "learning_rate": 2.478734311601053e-05, "loss": 0.977763671875, "step": 186800 }, { "epoch": 2.15299039636406, "grad_norm": 0.67578125, "learning_rate": 2.4780071552188013e-05, "loss": 0.9595011901855469, "step": 187000 }, { "epoch": 2.155293081438775, "grad_norm": 0.87890625, "learning_rate": 2.47727999883655e-05, "loss": 0.97533203125, "step": 187200 }, { "epoch": 2.15759576651349, "grad_norm": 0.6328125, "learning_rate": 2.4765528424542985e-05, "loss": 0.9841778564453125, "step": 187400 }, { "epoch": 2.159898451588205, "grad_norm": 0.5546875, "learning_rate": 2.4758256860720467e-05, "loss": 1.0073722839355468, "step": 187600 }, { "epoch": 2.16220113666292, "grad_norm": 0.59765625, "learning_rate": 2.475098529689795e-05, "loss": 0.9862171936035157, "step": 187800 }, { "epoch": 2.164503821737635, "grad_norm": 0.90625, "learning_rate": 2.4743713733075436e-05, "loss": 0.9807298278808594, "step": 188000 }, { "epoch": 2.1668065068123497, "grad_norm": 0.86328125, "learning_rate": 2.4736442169252918e-05, "loss": 0.9974630737304687, "step": 188200 }, { "epoch": 2.1691091918870646, "grad_norm": 0.58984375, "learning_rate": 2.4729170605430404e-05, "loss": 0.9857058715820313, "step": 188400 }, { "epoch": 2.1714118769617796, "grad_norm": 0.71484375, "learning_rate": 2.472189904160789e-05, "loss": 0.9878272247314454, "step": 188600 }, { "epoch": 2.1737145620364946, "grad_norm": 0.4765625, "learning_rate": 2.4714627477785376e-05, "loss": 0.9819071960449218, "step": 188800 }, { "epoch": 2.1760172471112096, "grad_norm": 0.64453125, "learning_rate": 2.470735591396286e-05, "loss": 0.9822796630859375, "step": 189000 }, { "epoch": 2.1783199321859246, "grad_norm": 0.53515625, "learning_rate": 2.470008435014034e-05, "loss": 0.9743334197998047, "step": 189200 }, { "epoch": 2.1806226172606396, "grad_norm": 0.58984375, "learning_rate": 2.4692812786317827e-05, "loss": 0.9917398071289063, "step": 189400 }, { "epoch": 2.1829253023353545, "grad_norm": 0.50390625, "learning_rate": 2.468554122249531e-05, "loss": 0.9816542053222657, "step": 189600 }, { "epoch": 2.1852279874100695, "grad_norm": 0.66015625, "learning_rate": 2.4678269658672795e-05, "loss": 0.9726030731201172, "step": 189800 }, { "epoch": 2.187530672484784, "grad_norm": 0.83203125, "learning_rate": 2.467099809485028e-05, "loss": 0.986077880859375, "step": 190000 }, { "epoch": 2.189833357559499, "grad_norm": 0.80078125, "learning_rate": 2.4663726531027764e-05, "loss": 0.991075439453125, "step": 190200 }, { "epoch": 2.192136042634214, "grad_norm": 1.4921875, "learning_rate": 2.4656454967205246e-05, "loss": 0.9752172088623047, "step": 190400 }, { "epoch": 2.194438727708929, "grad_norm": 0.60546875, "learning_rate": 2.4649183403382732e-05, "loss": 1.0028966522216798, "step": 190600 }, { "epoch": 2.196741412783644, "grad_norm": 0.64453125, "learning_rate": 2.4641911839560215e-05, "loss": 0.97932373046875, "step": 190800 }, { "epoch": 2.199044097858359, "grad_norm": 0.6484375, "learning_rate": 2.46346402757377e-05, "loss": 0.9712058258056641, "step": 191000 }, { "epoch": 2.201346782933074, "grad_norm": 1.3515625, "learning_rate": 2.4627368711915186e-05, "loss": 0.985837631225586, "step": 191200 }, { "epoch": 2.203649468007789, "grad_norm": 0.78515625, "learning_rate": 2.462009714809267e-05, "loss": 0.9744161224365234, "step": 191400 }, { "epoch": 2.205952153082504, "grad_norm": 0.68359375, "learning_rate": 2.461282558427015e-05, "loss": 0.9757750701904296, "step": 191600 }, { "epoch": 2.208254838157219, "grad_norm": 0.7265625, "learning_rate": 2.4605554020447637e-05, "loss": 0.9795994567871094, "step": 191800 }, { "epoch": 2.2105575232319334, "grad_norm": 0.453125, "learning_rate": 2.4598282456625123e-05, "loss": 0.9868009948730468, "step": 192000 }, { "epoch": 2.2128602083066484, "grad_norm": 0.5703125, "learning_rate": 2.4591010892802606e-05, "loss": 0.9895838928222657, "step": 192200 }, { "epoch": 2.2151628933813634, "grad_norm": 0.90234375, "learning_rate": 2.4583739328980092e-05, "loss": 0.9988584899902344, "step": 192400 }, { "epoch": 2.2174655784560784, "grad_norm": 0.5625, "learning_rate": 2.4576467765157578e-05, "loss": 0.9978138732910157, "step": 192600 }, { "epoch": 2.2197682635307934, "grad_norm": 0.59375, "learning_rate": 2.456919620133506e-05, "loss": 0.992156982421875, "step": 192800 }, { "epoch": 2.2220709486055084, "grad_norm": 0.828125, "learning_rate": 2.4561924637512543e-05, "loss": 0.9902561187744141, "step": 193000 }, { "epoch": 2.2243736336802233, "grad_norm": 0.671875, "learning_rate": 2.455465307369003e-05, "loss": 0.9733341979980469, "step": 193200 }, { "epoch": 2.2266763187549383, "grad_norm": 1.4609375, "learning_rate": 2.454738150986751e-05, "loss": 0.9912680816650391, "step": 193400 }, { "epoch": 2.2289790038296533, "grad_norm": 0.6484375, "learning_rate": 2.4540109946044997e-05, "loss": 0.9892380523681641, "step": 193600 }, { "epoch": 2.231281688904368, "grad_norm": 0.494140625, "learning_rate": 2.4532838382222483e-05, "loss": 0.9895990753173828, "step": 193800 }, { "epoch": 2.233584373979083, "grad_norm": 0.7109375, "learning_rate": 2.4525566818399966e-05, "loss": 0.9855638885498047, "step": 194000 }, { "epoch": 2.235887059053798, "grad_norm": 0.74609375, "learning_rate": 2.4518295254577448e-05, "loss": 0.9776099395751953, "step": 194200 }, { "epoch": 2.238189744128513, "grad_norm": 0.5546875, "learning_rate": 2.4511023690754934e-05, "loss": 0.9914614868164062, "step": 194400 }, { "epoch": 2.2404924292032278, "grad_norm": 0.58203125, "learning_rate": 2.450375212693242e-05, "loss": 0.9876277160644531, "step": 194600 }, { "epoch": 2.2427951142779428, "grad_norm": 0.609375, "learning_rate": 2.4496480563109902e-05, "loss": 0.9671038055419922, "step": 194800 }, { "epoch": 2.2450977993526577, "grad_norm": 1.0625, "learning_rate": 2.448920899928739e-05, "loss": 0.9613436889648438, "step": 195000 }, { "epoch": 2.2474004844273727, "grad_norm": 1.1953125, "learning_rate": 2.4481937435464874e-05, "loss": 0.9555902099609375, "step": 195200 }, { "epoch": 2.2497031695020877, "grad_norm": 0.50390625, "learning_rate": 2.4474665871642353e-05, "loss": 1.0098719787597656, "step": 195400 }, { "epoch": 2.2520058545768027, "grad_norm": 1.0234375, "learning_rate": 2.446739430781984e-05, "loss": 0.9947319793701171, "step": 195600 }, { "epoch": 2.2543085396515172, "grad_norm": 0.86328125, "learning_rate": 2.4460122743997325e-05, "loss": 0.9614073944091797, "step": 195800 }, { "epoch": 2.256611224726232, "grad_norm": 0.41796875, "learning_rate": 2.4452851180174808e-05, "loss": 0.9944358062744141, "step": 196000 }, { "epoch": 2.258913909800947, "grad_norm": 0.6484375, "learning_rate": 2.4445579616352294e-05, "loss": 0.9826112365722657, "step": 196200 }, { "epoch": 2.261216594875662, "grad_norm": 1.1875, "learning_rate": 2.443830805252978e-05, "loss": 0.9536886596679688, "step": 196400 }, { "epoch": 2.263519279950377, "grad_norm": 0.5390625, "learning_rate": 2.4431036488707262e-05, "loss": 0.9850600433349609, "step": 196600 }, { "epoch": 2.265821965025092, "grad_norm": 1.015625, "learning_rate": 2.4423764924884745e-05, "loss": 0.9687165832519531, "step": 196800 }, { "epoch": 2.268124650099807, "grad_norm": 1.78125, "learning_rate": 2.441649336106223e-05, "loss": 0.9938833618164062, "step": 197000 }, { "epoch": 2.270427335174522, "grad_norm": 0.86328125, "learning_rate": 2.4409221797239713e-05, "loss": 0.9914147186279297, "step": 197200 }, { "epoch": 2.272730020249237, "grad_norm": 0.6796875, "learning_rate": 2.44019502334172e-05, "loss": 0.9896980285644531, "step": 197400 }, { "epoch": 2.2750327053239516, "grad_norm": 0.59375, "learning_rate": 2.4394678669594685e-05, "loss": 1.000285873413086, "step": 197600 }, { "epoch": 2.2773353903986666, "grad_norm": 0.63671875, "learning_rate": 2.438740710577217e-05, "loss": 0.9800799560546875, "step": 197800 }, { "epoch": 2.2796380754733816, "grad_norm": 1.03125, "learning_rate": 2.438013554194965e-05, "loss": 0.9833818054199219, "step": 198000 }, { "epoch": 2.2819407605480966, "grad_norm": 0.482421875, "learning_rate": 2.4372863978127136e-05, "loss": 0.9885999298095703, "step": 198200 }, { "epoch": 2.2842434456228116, "grad_norm": 0.78125, "learning_rate": 2.4365592414304622e-05, "loss": 0.9842572784423829, "step": 198400 }, { "epoch": 2.2865461306975265, "grad_norm": 0.734375, "learning_rate": 2.4358320850482104e-05, "loss": 1.0083957672119142, "step": 198600 }, { "epoch": 2.2888488157722415, "grad_norm": 0.53125, "learning_rate": 2.435104928665959e-05, "loss": 0.9839616394042969, "step": 198800 }, { "epoch": 2.2911515008469565, "grad_norm": 1.5703125, "learning_rate": 2.4343777722837076e-05, "loss": 0.9807469940185547, "step": 199000 }, { "epoch": 2.2934541859216715, "grad_norm": 0.78515625, "learning_rate": 2.433650615901456e-05, "loss": 0.9862178039550781, "step": 199200 }, { "epoch": 2.295756870996386, "grad_norm": 0.69140625, "learning_rate": 2.432923459519204e-05, "loss": 0.9967860412597657, "step": 199400 }, { "epoch": 2.298059556071101, "grad_norm": 0.73046875, "learning_rate": 2.4321963031369527e-05, "loss": 0.9825498199462891, "step": 199600 }, { "epoch": 2.300362241145816, "grad_norm": 0.490234375, "learning_rate": 2.431469146754701e-05, "loss": 0.9612421417236328, "step": 199800 }, { "epoch": 2.302664926220531, "grad_norm": 0.62890625, "learning_rate": 2.4307419903724496e-05, "loss": 0.9812924194335938, "step": 200000 }, { "epoch": 2.304967611295246, "grad_norm": 0.765625, "learning_rate": 2.430014833990198e-05, "loss": 0.9764970397949219, "step": 200200 }, { "epoch": 2.307270296369961, "grad_norm": 0.6015625, "learning_rate": 2.4292876776079467e-05, "loss": 0.983216781616211, "step": 200400 }, { "epoch": 2.309572981444676, "grad_norm": 0.5703125, "learning_rate": 2.4285605212256946e-05, "loss": 0.9808189392089843, "step": 200600 }, { "epoch": 2.311875666519391, "grad_norm": 0.64453125, "learning_rate": 2.4278333648434432e-05, "loss": 0.9695719909667969, "step": 200800 }, { "epoch": 2.314178351594106, "grad_norm": 0.44921875, "learning_rate": 2.427106208461192e-05, "loss": 0.9838567352294922, "step": 201000 }, { "epoch": 2.3164810366688204, "grad_norm": 0.7109375, "learning_rate": 2.42637905207894e-05, "loss": 0.9900138092041015, "step": 201200 }, { "epoch": 2.3187837217435354, "grad_norm": 0.7734375, "learning_rate": 2.4256518956966887e-05, "loss": 0.9634355926513671, "step": 201400 }, { "epoch": 2.3210864068182504, "grad_norm": 1.390625, "learning_rate": 2.4249247393144373e-05, "loss": 0.9662844848632812, "step": 201600 }, { "epoch": 2.3233890918929654, "grad_norm": 0.54296875, "learning_rate": 2.4241975829321852e-05, "loss": 0.9637671661376953, "step": 201800 }, { "epoch": 2.3256917769676804, "grad_norm": 0.8359375, "learning_rate": 2.4234704265499338e-05, "loss": 0.9792532348632812, "step": 202000 }, { "epoch": 2.3279944620423954, "grad_norm": 0.69140625, "learning_rate": 2.4227432701676824e-05, "loss": 0.9898047637939453, "step": 202200 }, { "epoch": 2.3302971471171103, "grad_norm": 0.80078125, "learning_rate": 2.4220161137854306e-05, "loss": 0.974963150024414, "step": 202400 }, { "epoch": 2.3325998321918253, "grad_norm": 1.140625, "learning_rate": 2.4212889574031792e-05, "loss": 0.987943344116211, "step": 202600 }, { "epoch": 2.3349025172665403, "grad_norm": 1.578125, "learning_rate": 2.4205618010209278e-05, "loss": 0.9598580169677734, "step": 202800 }, { "epoch": 2.337205202341255, "grad_norm": 0.953125, "learning_rate": 2.419834644638676e-05, "loss": 0.9809665679931641, "step": 203000 }, { "epoch": 2.33950788741597, "grad_norm": 0.39453125, "learning_rate": 2.4191074882564243e-05, "loss": 0.9566979217529297, "step": 203200 }, { "epoch": 2.341810572490685, "grad_norm": 1.078125, "learning_rate": 2.418380331874173e-05, "loss": 0.979805908203125, "step": 203400 }, { "epoch": 2.3441132575654, "grad_norm": 0.6640625, "learning_rate": 2.4176531754919215e-05, "loss": 0.9806376647949219, "step": 203600 }, { "epoch": 2.3464159426401148, "grad_norm": 0.73046875, "learning_rate": 2.4169260191096697e-05, "loss": 0.9827217864990234, "step": 203800 }, { "epoch": 2.3487186277148298, "grad_norm": 0.90625, "learning_rate": 2.4161988627274183e-05, "loss": 0.9710164642333985, "step": 204000 }, { "epoch": 2.3510213127895447, "grad_norm": 0.84765625, "learning_rate": 2.415471706345167e-05, "loss": 0.9706101989746094, "step": 204200 }, { "epoch": 2.3533239978642597, "grad_norm": 0.453125, "learning_rate": 2.414744549962915e-05, "loss": 0.9726792907714844, "step": 204400 }, { "epoch": 2.3556266829389747, "grad_norm": 0.78125, "learning_rate": 2.4140173935806634e-05, "loss": 0.989774169921875, "step": 204600 }, { "epoch": 2.3579293680136892, "grad_norm": 0.625, "learning_rate": 2.413290237198412e-05, "loss": 0.9620243835449219, "step": 204800 }, { "epoch": 2.3602320530884042, "grad_norm": 0.70703125, "learning_rate": 2.4125630808161603e-05, "loss": 0.9820114135742187, "step": 205000 }, { "epoch": 2.362534738163119, "grad_norm": 0.58203125, "learning_rate": 2.411835924433909e-05, "loss": 0.981342544555664, "step": 205200 }, { "epoch": 2.364837423237834, "grad_norm": 0.51171875, "learning_rate": 2.4111087680516575e-05, "loss": 0.9816950225830078, "step": 205400 }, { "epoch": 2.367140108312549, "grad_norm": 0.95703125, "learning_rate": 2.4103816116694057e-05, "loss": 0.9805652618408203, "step": 205600 }, { "epoch": 2.369442793387264, "grad_norm": 0.466796875, "learning_rate": 2.409654455287154e-05, "loss": 0.9725960540771484, "step": 205800 }, { "epoch": 2.371745478461979, "grad_norm": 0.62890625, "learning_rate": 2.4089272989049025e-05, "loss": 0.9859681701660157, "step": 206000 }, { "epoch": 2.374048163536694, "grad_norm": 0.6328125, "learning_rate": 2.408200142522651e-05, "loss": 0.9848648834228516, "step": 206200 }, { "epoch": 2.376350848611409, "grad_norm": 0.69140625, "learning_rate": 2.4074729861403994e-05, "loss": 0.9847093200683594, "step": 206400 }, { "epoch": 2.3786535336861236, "grad_norm": 0.7109375, "learning_rate": 2.406745829758148e-05, "loss": 0.986251220703125, "step": 206600 }, { "epoch": 2.3809562187608386, "grad_norm": 0.7578125, "learning_rate": 2.4060186733758966e-05, "loss": 0.9802590179443359, "step": 206800 }, { "epoch": 2.3832589038355536, "grad_norm": 0.9765625, "learning_rate": 2.4052915169936445e-05, "loss": 0.9795805358886719, "step": 207000 }, { "epoch": 2.3855615889102686, "grad_norm": 0.5703125, "learning_rate": 2.404564360611393e-05, "loss": 0.9767790985107422, "step": 207200 }, { "epoch": 2.3878642739849836, "grad_norm": 0.482421875, "learning_rate": 2.4038372042291417e-05, "loss": 0.9922294616699219, "step": 207400 }, { "epoch": 2.3901669590596986, "grad_norm": 1.015625, "learning_rate": 2.40311004784689e-05, "loss": 0.9741712951660156, "step": 207600 }, { "epoch": 2.3924696441344135, "grad_norm": 0.73046875, "learning_rate": 2.4023828914646385e-05, "loss": 0.9773464965820312, "step": 207800 }, { "epoch": 2.3947723292091285, "grad_norm": 0.44921875, "learning_rate": 2.401655735082387e-05, "loss": 0.9808747863769531, "step": 208000 }, { "epoch": 2.3970750142838435, "grad_norm": 0.875, "learning_rate": 2.400928578700135e-05, "loss": 0.9907157135009765, "step": 208200 }, { "epoch": 2.399377699358558, "grad_norm": 0.61328125, "learning_rate": 2.4002014223178836e-05, "loss": 0.9853793334960937, "step": 208400 }, { "epoch": 2.401680384433273, "grad_norm": 0.5546875, "learning_rate": 2.3994742659356322e-05, "loss": 0.978099365234375, "step": 208600 }, { "epoch": 2.403983069507988, "grad_norm": 0.5390625, "learning_rate": 2.3987471095533805e-05, "loss": 0.9827703857421874, "step": 208800 }, { "epoch": 2.406285754582703, "grad_norm": 0.73046875, "learning_rate": 2.398019953171129e-05, "loss": 0.9785765838623047, "step": 209000 }, { "epoch": 2.408588439657418, "grad_norm": 0.6953125, "learning_rate": 2.3972927967888776e-05, "loss": 0.9798247528076172, "step": 209200 }, { "epoch": 2.410891124732133, "grad_norm": 0.58984375, "learning_rate": 2.3965656404066262e-05, "loss": 0.9880730438232422, "step": 209400 }, { "epoch": 2.413193809806848, "grad_norm": 0.53515625, "learning_rate": 2.395838484024374e-05, "loss": 0.9864563751220703, "step": 209600 }, { "epoch": 2.415496494881563, "grad_norm": 0.48046875, "learning_rate": 2.3951113276421227e-05, "loss": 0.9851638031005859, "step": 209800 }, { "epoch": 2.417799179956278, "grad_norm": 0.435546875, "learning_rate": 2.3943841712598713e-05, "loss": 0.9939958953857422, "step": 210000 }, { "epoch": 2.420101865030993, "grad_norm": 0.63671875, "learning_rate": 2.3936570148776196e-05, "loss": 0.9842073059082032, "step": 210200 }, { "epoch": 2.422404550105708, "grad_norm": 0.8828125, "learning_rate": 2.3929298584953682e-05, "loss": 0.9827200317382813, "step": 210400 }, { "epoch": 2.4247072351804224, "grad_norm": 0.47265625, "learning_rate": 2.3922027021131168e-05, "loss": 0.9755634307861328, "step": 210600 }, { "epoch": 2.4270099202551374, "grad_norm": 0.48046875, "learning_rate": 2.3914755457308647e-05, "loss": 0.9901658630371094, "step": 210800 }, { "epoch": 2.4293126053298524, "grad_norm": 1.140625, "learning_rate": 2.3907483893486133e-05, "loss": 0.979815444946289, "step": 211000 }, { "epoch": 2.4316152904045674, "grad_norm": 1.078125, "learning_rate": 2.390021232966362e-05, "loss": 0.9816466522216797, "step": 211200 }, { "epoch": 2.4339179754792823, "grad_norm": 2.421875, "learning_rate": 2.38929407658411e-05, "loss": 0.9903483581542969, "step": 211400 }, { "epoch": 2.4362206605539973, "grad_norm": 0.5625, "learning_rate": 2.3885669202018587e-05, "loss": 0.9710890197753906, "step": 211600 }, { "epoch": 2.4385233456287123, "grad_norm": 0.67578125, "learning_rate": 2.3878397638196073e-05, "loss": 0.9668023681640625, "step": 211800 }, { "epoch": 2.4408260307034273, "grad_norm": 0.6796875, "learning_rate": 2.3871126074373552e-05, "loss": 1.0000997161865235, "step": 212000 }, { "epoch": 2.4431287157781423, "grad_norm": 0.64453125, "learning_rate": 2.3863854510551038e-05, "loss": 0.9645013427734375, "step": 212200 }, { "epoch": 2.445431400852857, "grad_norm": 0.53515625, "learning_rate": 2.3856582946728524e-05, "loss": 0.9931552886962891, "step": 212400 }, { "epoch": 2.447734085927572, "grad_norm": 1.109375, "learning_rate": 2.384931138290601e-05, "loss": 0.9747293853759765, "step": 212600 }, { "epoch": 2.450036771002287, "grad_norm": 0.484375, "learning_rate": 2.3842039819083492e-05, "loss": 0.9917967224121094, "step": 212800 }, { "epoch": 2.4523394560770018, "grad_norm": 0.7578125, "learning_rate": 2.3834768255260978e-05, "loss": 0.9693154144287109, "step": 213000 }, { "epoch": 2.4546421411517167, "grad_norm": 1.0546875, "learning_rate": 2.3827496691438464e-05, "loss": 1.0230400848388672, "step": 213200 }, { "epoch": 2.4569448262264317, "grad_norm": 0.734375, "learning_rate": 2.3820225127615943e-05, "loss": 0.9706953430175781, "step": 213400 }, { "epoch": 2.4592475113011467, "grad_norm": 0.59375, "learning_rate": 2.381295356379343e-05, "loss": 1.0089253997802734, "step": 213600 }, { "epoch": 2.4615501963758617, "grad_norm": 0.80078125, "learning_rate": 2.3805681999970915e-05, "loss": 1.0018858337402343, "step": 213800 }, { "epoch": 2.4638528814505767, "grad_norm": 0.8671875, "learning_rate": 2.3798410436148398e-05, "loss": 0.9635964965820313, "step": 214000 }, { "epoch": 2.466155566525291, "grad_norm": 0.7109375, "learning_rate": 2.3791138872325884e-05, "loss": 0.9803479766845703, "step": 214200 }, { "epoch": 2.468458251600006, "grad_norm": 0.447265625, "learning_rate": 2.378386730850337e-05, "loss": 0.9677488708496094, "step": 214400 }, { "epoch": 2.470760936674721, "grad_norm": 0.453125, "learning_rate": 2.377659574468085e-05, "loss": 0.9796437072753906, "step": 214600 }, { "epoch": 2.473063621749436, "grad_norm": 0.82421875, "learning_rate": 2.3769324180858335e-05, "loss": 0.9855581665039063, "step": 214800 }, { "epoch": 2.475366306824151, "grad_norm": 0.7265625, "learning_rate": 2.376205261703582e-05, "loss": 0.9737202453613282, "step": 215000 }, { "epoch": 2.477668991898866, "grad_norm": 0.84375, "learning_rate": 2.3754781053213306e-05, "loss": 0.9882557678222657, "step": 215200 }, { "epoch": 2.479971676973581, "grad_norm": 0.8828125, "learning_rate": 2.374750948939079e-05, "loss": 1.0013471221923829, "step": 215400 }, { "epoch": 2.482274362048296, "grad_norm": 0.65234375, "learning_rate": 2.3740237925568275e-05, "loss": 0.9897122192382812, "step": 215600 }, { "epoch": 2.484577047123011, "grad_norm": 0.65625, "learning_rate": 2.373296636174576e-05, "loss": 0.9997686767578124, "step": 215800 }, { "epoch": 2.4868797321977256, "grad_norm": 0.64453125, "learning_rate": 2.372569479792324e-05, "loss": 0.958477783203125, "step": 216000 }, { "epoch": 2.4891824172724406, "grad_norm": 0.73828125, "learning_rate": 2.3718423234100726e-05, "loss": 0.9921128845214844, "step": 216200 }, { "epoch": 2.4914851023471556, "grad_norm": 0.50390625, "learning_rate": 2.371115167027821e-05, "loss": 0.9742437744140625, "step": 216400 }, { "epoch": 2.4937877874218706, "grad_norm": 0.91015625, "learning_rate": 2.3703880106455694e-05, "loss": 0.9888323211669922, "step": 216600 }, { "epoch": 2.4960904724965856, "grad_norm": 1.078125, "learning_rate": 2.369660854263318e-05, "loss": 0.9792591857910157, "step": 216800 }, { "epoch": 2.4983931575713005, "grad_norm": 0.58984375, "learning_rate": 2.3689336978810666e-05, "loss": 0.9883199310302735, "step": 217000 }, { "epoch": 2.5006958426460155, "grad_norm": 0.703125, "learning_rate": 2.3682065414988145e-05, "loss": 0.9837226867675781, "step": 217200 }, { "epoch": 2.5029985277207305, "grad_norm": 1.0078125, "learning_rate": 2.367479385116563e-05, "loss": 0.9776473999023437, "step": 217400 }, { "epoch": 2.5053012127954455, "grad_norm": 0.74609375, "learning_rate": 2.3667522287343117e-05, "loss": 0.9647300720214844, "step": 217600 }, { "epoch": 2.50760389787016, "grad_norm": 0.5, "learning_rate": 2.36602507235206e-05, "loss": 0.9693010711669922, "step": 217800 }, { "epoch": 2.509906582944875, "grad_norm": 0.52734375, "learning_rate": 2.3652979159698085e-05, "loss": 0.9758069610595703, "step": 218000 }, { "epoch": 2.51220926801959, "grad_norm": 0.64453125, "learning_rate": 2.364570759587557e-05, "loss": 0.9871754455566406, "step": 218200 }, { "epoch": 2.514511953094305, "grad_norm": 0.5546875, "learning_rate": 2.3638436032053054e-05, "loss": 0.9758554840087891, "step": 218400 }, { "epoch": 2.51681463816902, "grad_norm": 0.55078125, "learning_rate": 2.3631164468230536e-05, "loss": 0.9900711822509766, "step": 218600 }, { "epoch": 2.519117323243735, "grad_norm": 0.5625, "learning_rate": 2.3623892904408022e-05, "loss": 0.985194091796875, "step": 218800 }, { "epoch": 2.52142000831845, "grad_norm": 0.55859375, "learning_rate": 2.3616621340585508e-05, "loss": 0.9648825073242188, "step": 219000 }, { "epoch": 2.523722693393165, "grad_norm": 0.451171875, "learning_rate": 2.360934977676299e-05, "loss": 0.9976405334472657, "step": 219200 }, { "epoch": 2.52602537846788, "grad_norm": 0.9375, "learning_rate": 2.3602078212940477e-05, "loss": 0.9568039703369141, "step": 219400 }, { "epoch": 2.5283280635425944, "grad_norm": 1.109375, "learning_rate": 2.3594806649117963e-05, "loss": 1.014922103881836, "step": 219600 }, { "epoch": 2.5306307486173094, "grad_norm": 0.55078125, "learning_rate": 2.3587535085295442e-05, "loss": 0.9895259857177734, "step": 219800 }, { "epoch": 2.5329334336920244, "grad_norm": 0.89453125, "learning_rate": 2.3580263521472928e-05, "loss": 0.9885545349121094, "step": 220000 }, { "epoch": 2.5352361187667394, "grad_norm": 0.65234375, "learning_rate": 2.3572991957650414e-05, "loss": 0.9912796783447265, "step": 220200 }, { "epoch": 2.5375388038414544, "grad_norm": 1.0703125, "learning_rate": 2.3565720393827896e-05, "loss": 0.9948096466064453, "step": 220400 }, { "epoch": 2.5398414889161693, "grad_norm": 0.984375, "learning_rate": 2.3558448830005382e-05, "loss": 0.9950077056884765, "step": 220600 }, { "epoch": 2.5421441739908843, "grad_norm": 1.0859375, "learning_rate": 2.3551177266182868e-05, "loss": 0.9848309326171875, "step": 220800 }, { "epoch": 2.5444468590655993, "grad_norm": 1.9921875, "learning_rate": 2.354390570236035e-05, "loss": 0.9799929809570312, "step": 221000 }, { "epoch": 2.5467495441403143, "grad_norm": 0.5234375, "learning_rate": 2.3536634138537833e-05, "loss": 0.9768532562255859, "step": 221200 }, { "epoch": 2.549052229215029, "grad_norm": 1.5546875, "learning_rate": 2.352936257471532e-05, "loss": 0.9896360015869141, "step": 221400 }, { "epoch": 2.5513549142897443, "grad_norm": 0.75390625, "learning_rate": 2.3522091010892805e-05, "loss": 0.9728896331787109, "step": 221600 }, { "epoch": 2.553657599364459, "grad_norm": 0.734375, "learning_rate": 2.3514819447070287e-05, "loss": 1.011695098876953, "step": 221800 }, { "epoch": 2.555960284439174, "grad_norm": 0.84765625, "learning_rate": 2.3507547883247773e-05, "loss": 1.0155657958984374, "step": 222000 }, { "epoch": 2.5582629695138888, "grad_norm": 0.6875, "learning_rate": 2.3500276319425256e-05, "loss": 0.9898668670654297, "step": 222200 }, { "epoch": 2.5605656545886037, "grad_norm": 0.671875, "learning_rate": 2.3493004755602738e-05, "loss": 0.9848436737060546, "step": 222400 }, { "epoch": 2.5628683396633187, "grad_norm": 0.6875, "learning_rate": 2.3485733191780224e-05, "loss": 0.9848309326171875, "step": 222600 }, { "epoch": 2.5651710247380337, "grad_norm": 0.93359375, "learning_rate": 2.347846162795771e-05, "loss": 0.9747190856933594, "step": 222800 }, { "epoch": 2.5674737098127487, "grad_norm": 0.73046875, "learning_rate": 2.3471190064135193e-05, "loss": 0.9759510803222656, "step": 223000 }, { "epoch": 2.5697763948874632, "grad_norm": 0.61328125, "learning_rate": 2.346391850031268e-05, "loss": 0.9792971038818359, "step": 223200 }, { "epoch": 2.5720790799621787, "grad_norm": 0.89453125, "learning_rate": 2.3456646936490164e-05, "loss": 0.9957722473144531, "step": 223400 }, { "epoch": 2.574381765036893, "grad_norm": 0.67578125, "learning_rate": 2.3449375372667644e-05, "loss": 0.9673760223388672, "step": 223600 }, { "epoch": 2.576684450111608, "grad_norm": 0.98046875, "learning_rate": 2.344210380884513e-05, "loss": 1.0127267456054687, "step": 223800 }, { "epoch": 2.578987135186323, "grad_norm": 0.5703125, "learning_rate": 2.3434832245022615e-05, "loss": 0.9820223236083985, "step": 224000 }, { "epoch": 2.581289820261038, "grad_norm": 0.5703125, "learning_rate": 2.34275606812001e-05, "loss": 0.9654301452636719, "step": 224200 }, { "epoch": 2.583592505335753, "grad_norm": 0.50390625, "learning_rate": 2.3420289117377584e-05, "loss": 0.9646720123291016, "step": 224400 }, { "epoch": 2.585895190410468, "grad_norm": 0.390625, "learning_rate": 2.341301755355507e-05, "loss": 0.9920122528076172, "step": 224600 }, { "epoch": 2.588197875485183, "grad_norm": 0.703125, "learning_rate": 2.3405745989732552e-05, "loss": 0.9855150604248046, "step": 224800 }, { "epoch": 2.5905005605598976, "grad_norm": 0.57421875, "learning_rate": 2.3398474425910035e-05, "loss": 0.9884321594238281, "step": 225000 }, { "epoch": 2.592803245634613, "grad_norm": 0.515625, "learning_rate": 2.339120286208752e-05, "loss": 0.9909938049316406, "step": 225200 }, { "epoch": 2.5951059307093276, "grad_norm": 0.78515625, "learning_rate": 2.3383931298265007e-05, "loss": 0.9761519622802735, "step": 225400 }, { "epoch": 2.5974086157840426, "grad_norm": 1.15625, "learning_rate": 2.337665973444249e-05, "loss": 0.9695050048828125, "step": 225600 }, { "epoch": 2.5997113008587576, "grad_norm": 0.65234375, "learning_rate": 2.3369388170619975e-05, "loss": 0.9951475524902343, "step": 225800 }, { "epoch": 2.6020139859334726, "grad_norm": 0.455078125, "learning_rate": 2.336211660679746e-05, "loss": 0.9993846893310547, "step": 226000 }, { "epoch": 2.6043166710081875, "grad_norm": 1.4296875, "learning_rate": 2.335484504297494e-05, "loss": 0.9837513732910156, "step": 226200 }, { "epoch": 2.6066193560829025, "grad_norm": 0.88671875, "learning_rate": 2.3347573479152426e-05, "loss": 0.9643393707275391, "step": 226400 }, { "epoch": 2.6089220411576175, "grad_norm": 0.51953125, "learning_rate": 2.3340301915329912e-05, "loss": 0.9859303283691406, "step": 226600 }, { "epoch": 2.611224726232332, "grad_norm": 0.65234375, "learning_rate": 2.3333030351507394e-05, "loss": 0.9887308502197265, "step": 226800 }, { "epoch": 2.6135274113070475, "grad_norm": 1.546875, "learning_rate": 2.332575878768488e-05, "loss": 0.9941259002685547, "step": 227000 }, { "epoch": 2.615830096381762, "grad_norm": 0.5390625, "learning_rate": 2.3318487223862366e-05, "loss": 0.9827572631835938, "step": 227200 }, { "epoch": 2.618132781456477, "grad_norm": 1.046875, "learning_rate": 2.331121566003985e-05, "loss": 0.9632863616943359, "step": 227400 }, { "epoch": 2.620435466531192, "grad_norm": 0.52734375, "learning_rate": 2.330394409621733e-05, "loss": 0.9896905517578125, "step": 227600 }, { "epoch": 2.622738151605907, "grad_norm": 0.82421875, "learning_rate": 2.3296672532394817e-05, "loss": 0.9736611938476563, "step": 227800 }, { "epoch": 2.625040836680622, "grad_norm": 2.078125, "learning_rate": 2.3289400968572303e-05, "loss": 0.991059799194336, "step": 228000 }, { "epoch": 2.627343521755337, "grad_norm": 0.55859375, "learning_rate": 2.3282129404749786e-05, "loss": 0.9731089019775391, "step": 228200 }, { "epoch": 2.629646206830052, "grad_norm": 0.80078125, "learning_rate": 2.327485784092727e-05, "loss": 0.9963571166992188, "step": 228400 }, { "epoch": 2.6319488919047664, "grad_norm": 1.03125, "learning_rate": 2.3267586277104754e-05, "loss": 0.9739570617675781, "step": 228600 }, { "epoch": 2.634251576979482, "grad_norm": 0.65234375, "learning_rate": 2.3260314713282237e-05, "loss": 0.9853155517578125, "step": 228800 }, { "epoch": 2.6365542620541964, "grad_norm": 0.55859375, "learning_rate": 2.3253043149459723e-05, "loss": 0.9822714233398437, "step": 229000 }, { "epoch": 2.6388569471289114, "grad_norm": 0.59375, "learning_rate": 2.324577158563721e-05, "loss": 1.0132391357421875, "step": 229200 }, { "epoch": 2.6411596322036264, "grad_norm": 0.55859375, "learning_rate": 2.323850002181469e-05, "loss": 0.9821296691894531, "step": 229400 }, { "epoch": 2.6434623172783414, "grad_norm": 1.0234375, "learning_rate": 2.3231228457992177e-05, "loss": 0.9867617797851562, "step": 229600 }, { "epoch": 2.6457650023530563, "grad_norm": 6.71875, "learning_rate": 2.3223956894169663e-05, "loss": 0.9906488037109376, "step": 229800 }, { "epoch": 2.6480676874277713, "grad_norm": 0.796875, "learning_rate": 2.3216685330347145e-05, "loss": 0.9868508911132813, "step": 230000 }, { "epoch": 2.6503703725024863, "grad_norm": 0.640625, "learning_rate": 2.3209413766524628e-05, "loss": 0.9740293884277343, "step": 230200 }, { "epoch": 2.652673057577201, "grad_norm": 0.8828125, "learning_rate": 2.3202142202702114e-05, "loss": 0.9676800537109375, "step": 230400 }, { "epoch": 2.6549757426519163, "grad_norm": 0.8046875, "learning_rate": 2.31948706388796e-05, "loss": 0.9770725250244141, "step": 230600 }, { "epoch": 2.657278427726631, "grad_norm": 1.28125, "learning_rate": 2.3187599075057082e-05, "loss": 0.9891566467285157, "step": 230800 }, { "epoch": 2.659581112801346, "grad_norm": 0.9140625, "learning_rate": 2.3180327511234568e-05, "loss": 0.9634536743164063, "step": 231000 }, { "epoch": 2.6618837978760608, "grad_norm": 0.421875, "learning_rate": 2.317305594741205e-05, "loss": 0.9817213439941406, "step": 231200 }, { "epoch": 2.6641864829507758, "grad_norm": 0.9296875, "learning_rate": 2.3165784383589533e-05, "loss": 0.9655717468261719, "step": 231400 }, { "epoch": 2.6664891680254907, "grad_norm": 0.65625, "learning_rate": 2.315851281976702e-05, "loss": 1.0008053588867187, "step": 231600 }, { "epoch": 2.6687918531002057, "grad_norm": 0.609375, "learning_rate": 2.3151241255944505e-05, "loss": 1.0027259826660155, "step": 231800 }, { "epoch": 2.6710945381749207, "grad_norm": 0.71875, "learning_rate": 2.3143969692121988e-05, "loss": 0.9779088592529297, "step": 232000 }, { "epoch": 2.6733972232496357, "grad_norm": 0.54296875, "learning_rate": 2.3136698128299473e-05, "loss": 0.9831785583496093, "step": 232200 }, { "epoch": 2.6756999083243507, "grad_norm": 0.5, "learning_rate": 2.3129426564476956e-05, "loss": 0.975287094116211, "step": 232400 }, { "epoch": 2.678002593399065, "grad_norm": 0.5859375, "learning_rate": 2.312215500065444e-05, "loss": 1.011480178833008, "step": 232600 }, { "epoch": 2.68030527847378, "grad_norm": 0.53125, "learning_rate": 2.3114883436831924e-05, "loss": 0.9821878814697266, "step": 232800 }, { "epoch": 2.682607963548495, "grad_norm": 0.60546875, "learning_rate": 2.310761187300941e-05, "loss": 0.9614496612548828, "step": 233000 }, { "epoch": 2.68491064862321, "grad_norm": 0.6953125, "learning_rate": 2.3100340309186896e-05, "loss": 0.9810744476318359, "step": 233200 }, { "epoch": 2.687213333697925, "grad_norm": 0.9609375, "learning_rate": 2.309306874536438e-05, "loss": 0.9930284881591797, "step": 233400 }, { "epoch": 2.68951601877264, "grad_norm": 1.4375, "learning_rate": 2.3085797181541865e-05, "loss": 0.9711058807373046, "step": 233600 }, { "epoch": 2.691818703847355, "grad_norm": 0.73828125, "learning_rate": 2.3078525617719347e-05, "loss": 0.9531632232666015, "step": 233800 }, { "epoch": 2.69412138892207, "grad_norm": 0.5703125, "learning_rate": 2.307125405389683e-05, "loss": 0.9774398040771485, "step": 234000 }, { "epoch": 2.696424073996785, "grad_norm": 0.609375, "learning_rate": 2.3063982490074316e-05, "loss": 0.9752250671386719, "step": 234200 }, { "epoch": 2.6987267590714996, "grad_norm": 1.0703125, "learning_rate": 2.30567109262518e-05, "loss": 0.9602703857421875, "step": 234400 }, { "epoch": 2.7010294441462146, "grad_norm": 0.82421875, "learning_rate": 2.3049439362429284e-05, "loss": 0.9857449340820312, "step": 234600 }, { "epoch": 2.7033321292209296, "grad_norm": 0.671875, "learning_rate": 2.304216779860677e-05, "loss": 0.9743757629394532, "step": 234800 }, { "epoch": 2.7056348142956446, "grad_norm": 0.92578125, "learning_rate": 2.3034896234784253e-05, "loss": 0.9862078857421875, "step": 235000 }, { "epoch": 2.7079374993703595, "grad_norm": 0.80078125, "learning_rate": 2.3027624670961735e-05, "loss": 1.021921615600586, "step": 235200 }, { "epoch": 2.7102401844450745, "grad_norm": 0.65234375, "learning_rate": 2.302035310713922e-05, "loss": 0.9676741790771485, "step": 235400 }, { "epoch": 2.7125428695197895, "grad_norm": 0.7109375, "learning_rate": 2.3013081543316707e-05, "loss": 0.96970947265625, "step": 235600 }, { "epoch": 2.7148455545945045, "grad_norm": 0.6640625, "learning_rate": 2.3005809979494193e-05, "loss": 0.9862263488769532, "step": 235800 }, { "epoch": 2.7171482396692195, "grad_norm": 0.447265625, "learning_rate": 2.2998538415671675e-05, "loss": 0.9895063781738281, "step": 236000 }, { "epoch": 2.719450924743934, "grad_norm": 1.8515625, "learning_rate": 2.299126685184916e-05, "loss": 0.9968424987792969, "step": 236200 }, { "epoch": 2.721753609818649, "grad_norm": 0.96484375, "learning_rate": 2.2983995288026644e-05, "loss": 0.9946724700927735, "step": 236400 }, { "epoch": 2.724056294893364, "grad_norm": 0.5546875, "learning_rate": 2.2976723724204126e-05, "loss": 0.9951986694335937, "step": 236600 }, { "epoch": 2.726358979968079, "grad_norm": 0.5390625, "learning_rate": 2.2969452160381612e-05, "loss": 1.0003690338134765, "step": 236800 }, { "epoch": 2.728661665042794, "grad_norm": 0.5703125, "learning_rate": 2.2962180596559098e-05, "loss": 1.0061814880371094, "step": 237000 }, { "epoch": 2.730964350117509, "grad_norm": 0.7890625, "learning_rate": 2.295490903273658e-05, "loss": 0.9780216217041016, "step": 237200 }, { "epoch": 2.733267035192224, "grad_norm": 0.58984375, "learning_rate": 2.2947637468914067e-05, "loss": 0.9820411682128907, "step": 237400 }, { "epoch": 2.735569720266939, "grad_norm": 0.984375, "learning_rate": 2.294036590509155e-05, "loss": 0.9854095458984375, "step": 237600 }, { "epoch": 2.737872405341654, "grad_norm": 0.86328125, "learning_rate": 2.293309434126903e-05, "loss": 0.9723403167724609, "step": 237800 }, { "epoch": 2.7401750904163684, "grad_norm": 0.78515625, "learning_rate": 2.2925822777446518e-05, "loss": 0.9777320098876953, "step": 238000 }, { "epoch": 2.742477775491084, "grad_norm": 0.6953125, "learning_rate": 2.2918551213624003e-05, "loss": 0.9932432556152344, "step": 238200 }, { "epoch": 2.7447804605657984, "grad_norm": 0.63671875, "learning_rate": 2.2911279649801486e-05, "loss": 0.9813819122314453, "step": 238400 }, { "epoch": 2.7470831456405134, "grad_norm": 1.0078125, "learning_rate": 2.2904008085978972e-05, "loss": 0.9843547821044922, "step": 238600 }, { "epoch": 2.7493858307152284, "grad_norm": 0.95703125, "learning_rate": 2.2896736522156454e-05, "loss": 0.9740335083007813, "step": 238800 }, { "epoch": 2.7516885157899433, "grad_norm": 0.5859375, "learning_rate": 2.288946495833394e-05, "loss": 0.9769838714599609, "step": 239000 }, { "epoch": 2.7539912008646583, "grad_norm": 0.81640625, "learning_rate": 2.2882193394511423e-05, "loss": 0.9714900970458984, "step": 239200 }, { "epoch": 2.7562938859393733, "grad_norm": 1.2265625, "learning_rate": 2.287492183068891e-05, "loss": 0.9776052093505859, "step": 239400 }, { "epoch": 2.7585965710140883, "grad_norm": 0.62109375, "learning_rate": 2.2867650266866395e-05, "loss": 0.9773331451416015, "step": 239600 }, { "epoch": 2.760899256088803, "grad_norm": 0.73828125, "learning_rate": 2.2860378703043877e-05, "loss": 0.9772712707519531, "step": 239800 }, { "epoch": 2.7632019411635182, "grad_norm": 0.6171875, "learning_rate": 2.2853107139221363e-05, "loss": 0.9649584197998047, "step": 240000 }, { "epoch": 2.765504626238233, "grad_norm": 0.74609375, "learning_rate": 2.2845835575398846e-05, "loss": 0.966458969116211, "step": 240200 }, { "epoch": 2.7678073113129478, "grad_norm": 1.0625, "learning_rate": 2.2838564011576328e-05, "loss": 0.986024398803711, "step": 240400 }, { "epoch": 2.7701099963876628, "grad_norm": 0.6640625, "learning_rate": 2.2831292447753814e-05, "loss": 0.9941361236572266, "step": 240600 }, { "epoch": 2.7724126814623777, "grad_norm": 0.44921875, "learning_rate": 2.28240208839313e-05, "loss": 0.9598740386962891, "step": 240800 }, { "epoch": 2.7747153665370927, "grad_norm": 0.64453125, "learning_rate": 2.2816749320108783e-05, "loss": 0.9616059875488281, "step": 241000 }, { "epoch": 2.7770180516118077, "grad_norm": 0.765625, "learning_rate": 2.280947775628627e-05, "loss": 0.9962806701660156, "step": 241200 }, { "epoch": 2.7793207366865227, "grad_norm": 0.63671875, "learning_rate": 2.280220619246375e-05, "loss": 0.9695357513427735, "step": 241400 }, { "epoch": 2.7816234217612372, "grad_norm": 0.53125, "learning_rate": 2.2794934628641237e-05, "loss": 0.9759367370605468, "step": 241600 }, { "epoch": 2.7839261068359527, "grad_norm": 0.546875, "learning_rate": 2.278766306481872e-05, "loss": 0.9805625915527344, "step": 241800 }, { "epoch": 2.786228791910667, "grad_norm": 1.09375, "learning_rate": 2.2780391500996205e-05, "loss": 0.9758683776855469, "step": 242000 }, { "epoch": 2.788531476985382, "grad_norm": 0.6484375, "learning_rate": 2.277311993717369e-05, "loss": 0.9969324493408203, "step": 242200 }, { "epoch": 2.790834162060097, "grad_norm": 0.8515625, "learning_rate": 2.2765848373351174e-05, "loss": 0.9669373321533203, "step": 242400 }, { "epoch": 2.793136847134812, "grad_norm": 0.66015625, "learning_rate": 2.2758576809528656e-05, "loss": 0.9705430603027344, "step": 242600 }, { "epoch": 2.795439532209527, "grad_norm": 0.703125, "learning_rate": 2.2751305245706142e-05, "loss": 0.9699090576171875, "step": 242800 }, { "epoch": 2.797742217284242, "grad_norm": 0.6953125, "learning_rate": 2.2744033681883625e-05, "loss": 0.998017807006836, "step": 243000 }, { "epoch": 2.800044902358957, "grad_norm": 0.546875, "learning_rate": 2.273676211806111e-05, "loss": 0.9731108093261719, "step": 243200 }, { "epoch": 2.8023475874336716, "grad_norm": 0.62109375, "learning_rate": 2.2729490554238597e-05, "loss": 0.9816190338134766, "step": 243400 }, { "epoch": 2.804650272508387, "grad_norm": 1.1015625, "learning_rate": 2.272221899041608e-05, "loss": 0.9914408874511719, "step": 243600 }, { "epoch": 2.8069529575831016, "grad_norm": 0.625, "learning_rate": 2.2714947426593565e-05, "loss": 0.9849854278564453, "step": 243800 }, { "epoch": 2.8092556426578166, "grad_norm": 0.73046875, "learning_rate": 2.2707675862771048e-05, "loss": 1.00310791015625, "step": 244000 }, { "epoch": 2.8115583277325316, "grad_norm": 0.703125, "learning_rate": 2.270040429894853e-05, "loss": 0.9826456451416016, "step": 244200 }, { "epoch": 2.8138610128072465, "grad_norm": 0.42578125, "learning_rate": 2.2693132735126016e-05, "loss": 0.9897075653076172, "step": 244400 }, { "epoch": 2.8161636978819615, "grad_norm": 0.55078125, "learning_rate": 2.2685861171303502e-05, "loss": 0.9984790802001953, "step": 244600 }, { "epoch": 2.8184663829566765, "grad_norm": 1.59375, "learning_rate": 2.2678589607480988e-05, "loss": 0.9899990081787109, "step": 244800 }, { "epoch": 2.8207690680313915, "grad_norm": 0.7109375, "learning_rate": 2.267131804365847e-05, "loss": 0.9996802520751953, "step": 245000 }, { "epoch": 2.823071753106106, "grad_norm": 0.8125, "learning_rate": 2.2664046479835953e-05, "loss": 0.9771870422363281, "step": 245200 }, { "epoch": 2.8253744381808215, "grad_norm": 0.60546875, "learning_rate": 2.265677491601344e-05, "loss": 0.9960012817382813, "step": 245400 }, { "epoch": 2.827677123255536, "grad_norm": 0.50390625, "learning_rate": 2.264950335219092e-05, "loss": 0.9986069488525391, "step": 245600 }, { "epoch": 2.829979808330251, "grad_norm": 0.5703125, "learning_rate": 2.2642231788368407e-05, "loss": 0.9607802581787109, "step": 245800 }, { "epoch": 2.832282493404966, "grad_norm": 0.52734375, "learning_rate": 2.2634960224545893e-05, "loss": 1.0018367767333984, "step": 246000 }, { "epoch": 2.834585178479681, "grad_norm": 0.95703125, "learning_rate": 2.2627688660723376e-05, "loss": 0.9637592315673829, "step": 246200 }, { "epoch": 2.836887863554396, "grad_norm": 0.8828125, "learning_rate": 2.262041709690086e-05, "loss": 0.9718500518798828, "step": 246400 }, { "epoch": 2.839190548629111, "grad_norm": 0.625, "learning_rate": 2.2613145533078344e-05, "loss": 0.9744422912597657, "step": 246600 }, { "epoch": 2.841493233703826, "grad_norm": 0.419921875, "learning_rate": 2.2605873969255827e-05, "loss": 0.9885763549804687, "step": 246800 }, { "epoch": 2.8437959187785404, "grad_norm": 0.51171875, "learning_rate": 2.2598602405433312e-05, "loss": 0.9664224243164062, "step": 247000 }, { "epoch": 2.846098603853256, "grad_norm": 0.80078125, "learning_rate": 2.25913308416108e-05, "loss": 1.005243453979492, "step": 247200 }, { "epoch": 2.8484012889279704, "grad_norm": 0.78515625, "learning_rate": 2.258405927778828e-05, "loss": 0.979427490234375, "step": 247400 }, { "epoch": 2.8507039740026854, "grad_norm": 0.6640625, "learning_rate": 2.2576787713965767e-05, "loss": 0.9953087615966797, "step": 247600 }, { "epoch": 2.8530066590774004, "grad_norm": 1.1015625, "learning_rate": 2.256951615014325e-05, "loss": 0.9799519348144531, "step": 247800 }, { "epoch": 2.8553093441521153, "grad_norm": 0.73828125, "learning_rate": 2.2562244586320735e-05, "loss": 0.9886309051513672, "step": 248000 }, { "epoch": 2.8576120292268303, "grad_norm": 0.9140625, "learning_rate": 2.2554973022498218e-05, "loss": 0.9763843536376953, "step": 248200 }, { "epoch": 2.8599147143015453, "grad_norm": 0.490234375, "learning_rate": 2.2547701458675704e-05, "loss": 0.9831291198730469, "step": 248400 }, { "epoch": 2.8622173993762603, "grad_norm": 0.984375, "learning_rate": 2.254042989485319e-05, "loss": 0.9907274627685547, "step": 248600 }, { "epoch": 2.8645200844509753, "grad_norm": 0.4375, "learning_rate": 2.2533158331030672e-05, "loss": 0.9687870788574219, "step": 248800 }, { "epoch": 2.8668227695256903, "grad_norm": 0.796875, "learning_rate": 2.2525886767208155e-05, "loss": 0.951844482421875, "step": 249000 }, { "epoch": 2.869125454600405, "grad_norm": 0.4296875, "learning_rate": 2.251861520338564e-05, "loss": 0.9599909973144531, "step": 249200 }, { "epoch": 2.87142813967512, "grad_norm": 0.88671875, "learning_rate": 2.2511343639563123e-05, "loss": 0.9898688507080078, "step": 249400 }, { "epoch": 2.8737308247498348, "grad_norm": 0.462890625, "learning_rate": 2.250407207574061e-05, "loss": 0.9829541015625, "step": 249600 }, { "epoch": 2.8760335098245497, "grad_norm": 0.63671875, "learning_rate": 2.2496800511918095e-05, "loss": 0.9819578552246093, "step": 249800 }, { "epoch": 2.8783361948992647, "grad_norm": 0.51953125, "learning_rate": 2.2489528948095577e-05, "loss": 1.0021160125732422, "step": 250000 }, { "epoch": 2.8806388799739797, "grad_norm": 0.7421875, "learning_rate": 2.2482257384273063e-05, "loss": 0.9732303619384766, "step": 250200 }, { "epoch": 2.8829415650486947, "grad_norm": 0.80078125, "learning_rate": 2.2474985820450546e-05, "loss": 0.9762882995605469, "step": 250400 }, { "epoch": 2.8852442501234097, "grad_norm": 1.46875, "learning_rate": 2.2467714256628032e-05, "loss": 0.9967890930175781, "step": 250600 }, { "epoch": 2.8875469351981247, "grad_norm": 0.77734375, "learning_rate": 2.2460442692805514e-05, "loss": 0.9803618621826172, "step": 250800 }, { "epoch": 2.889849620272839, "grad_norm": 1.1015625, "learning_rate": 2.2453171128983e-05, "loss": 0.9854412078857422, "step": 251000 }, { "epoch": 2.892152305347554, "grad_norm": 0.52734375, "learning_rate": 2.2445899565160486e-05, "loss": 0.9635372161865234, "step": 251200 }, { "epoch": 2.894454990422269, "grad_norm": 0.78125, "learning_rate": 2.243862800133797e-05, "loss": 0.9794617462158203, "step": 251400 }, { "epoch": 2.896757675496984, "grad_norm": 0.93359375, "learning_rate": 2.243135643751545e-05, "loss": 0.9850530242919922, "step": 251600 }, { "epoch": 2.899060360571699, "grad_norm": 0.625, "learning_rate": 2.2424084873692937e-05, "loss": 0.9839181518554687, "step": 251800 }, { "epoch": 2.901363045646414, "grad_norm": 0.91015625, "learning_rate": 2.241681330987042e-05, "loss": 1.0048432922363282, "step": 252000 }, { "epoch": 2.903665730721129, "grad_norm": 0.373046875, "learning_rate": 2.2409541746047906e-05, "loss": 0.9703173828125, "step": 252200 }, { "epoch": 2.905968415795844, "grad_norm": 0.54296875, "learning_rate": 2.240227018222539e-05, "loss": 0.9863452911376953, "step": 252400 }, { "epoch": 2.908271100870559, "grad_norm": 1.4375, "learning_rate": 2.2394998618402874e-05, "loss": 0.9932093048095703, "step": 252600 }, { "epoch": 2.9105737859452736, "grad_norm": 0.8828125, "learning_rate": 2.2387727054580357e-05, "loss": 0.9997026062011719, "step": 252800 }, { "epoch": 2.9128764710199886, "grad_norm": 0.6015625, "learning_rate": 2.2380455490757842e-05, "loss": 0.9846231079101563, "step": 253000 }, { "epoch": 2.9151791560947036, "grad_norm": 0.953125, "learning_rate": 2.2373183926935325e-05, "loss": 0.9628493499755859, "step": 253200 }, { "epoch": 2.9174818411694186, "grad_norm": 0.9453125, "learning_rate": 2.236591236311281e-05, "loss": 0.9956505584716797, "step": 253400 }, { "epoch": 2.9197845262441335, "grad_norm": 0.546875, "learning_rate": 2.2358640799290297e-05, "loss": 0.9899761199951171, "step": 253600 }, { "epoch": 2.9220872113188485, "grad_norm": 0.474609375, "learning_rate": 2.2351369235467783e-05, "loss": 0.986265869140625, "step": 253800 }, { "epoch": 2.9243898963935635, "grad_norm": 0.6171875, "learning_rate": 2.2344097671645265e-05, "loss": 0.9733154296875, "step": 254000 }, { "epoch": 2.9266925814682785, "grad_norm": 0.765625, "learning_rate": 2.2336826107822748e-05, "loss": 0.9507086181640625, "step": 254200 }, { "epoch": 2.9289952665429935, "grad_norm": 0.6953125, "learning_rate": 2.2329554544000234e-05, "loss": 0.9880396270751953, "step": 254400 }, { "epoch": 2.931297951617708, "grad_norm": 0.56640625, "learning_rate": 2.2322282980177716e-05, "loss": 0.9833847808837891, "step": 254600 }, { "epoch": 2.9336006366924234, "grad_norm": 0.9765625, "learning_rate": 2.2315011416355202e-05, "loss": 0.9833303833007813, "step": 254800 }, { "epoch": 2.935903321767138, "grad_norm": 0.7109375, "learning_rate": 2.2307739852532688e-05, "loss": 0.9785620880126953, "step": 255000 }, { "epoch": 2.938206006841853, "grad_norm": 0.734375, "learning_rate": 2.230046828871017e-05, "loss": 0.9954475402832031, "step": 255200 }, { "epoch": 2.940508691916568, "grad_norm": 0.92578125, "learning_rate": 2.2293196724887653e-05, "loss": 0.991054916381836, "step": 255400 }, { "epoch": 2.942811376991283, "grad_norm": 0.65625, "learning_rate": 2.228592516106514e-05, "loss": 1.0015912628173829, "step": 255600 }, { "epoch": 2.945114062065998, "grad_norm": 0.70703125, "learning_rate": 2.227865359724262e-05, "loss": 0.983523178100586, "step": 255800 }, { "epoch": 2.947416747140713, "grad_norm": 0.5078125, "learning_rate": 2.2271382033420107e-05, "loss": 0.9683066558837891, "step": 256000 }, { "epoch": 2.949719432215428, "grad_norm": 0.75390625, "learning_rate": 2.2264110469597593e-05, "loss": 0.998266830444336, "step": 256200 }, { "epoch": 2.9520221172901424, "grad_norm": 0.75390625, "learning_rate": 2.225683890577508e-05, "loss": 0.9820155334472657, "step": 256400 }, { "epoch": 2.954324802364858, "grad_norm": 0.71875, "learning_rate": 2.2249567341952562e-05, "loss": 1.0017244720458984, "step": 256600 }, { "epoch": 2.9566274874395724, "grad_norm": 0.90625, "learning_rate": 2.2242295778130044e-05, "loss": 0.9865045166015625, "step": 256800 }, { "epoch": 2.9589301725142874, "grad_norm": 0.75390625, "learning_rate": 2.223502421430753e-05, "loss": 0.9958966827392578, "step": 257000 }, { "epoch": 2.9612328575890023, "grad_norm": 0.82421875, "learning_rate": 2.2227752650485013e-05, "loss": 1.001144561767578, "step": 257200 }, { "epoch": 2.9635355426637173, "grad_norm": 0.73828125, "learning_rate": 2.22204810866625e-05, "loss": 0.9909696197509765, "step": 257400 }, { "epoch": 2.9658382277384323, "grad_norm": 1.015625, "learning_rate": 2.2213209522839985e-05, "loss": 0.9749507141113282, "step": 257600 }, { "epoch": 2.9681409128131473, "grad_norm": 0.71484375, "learning_rate": 2.2205937959017467e-05, "loss": 0.9850035858154297, "step": 257800 }, { "epoch": 2.9704435978878623, "grad_norm": 0.71875, "learning_rate": 2.219866639519495e-05, "loss": 0.99532470703125, "step": 258000 }, { "epoch": 2.972746282962577, "grad_norm": 1.015625, "learning_rate": 2.2191394831372436e-05, "loss": 1.015971450805664, "step": 258200 }, { "epoch": 2.9750489680372922, "grad_norm": 0.55078125, "learning_rate": 2.2184123267549918e-05, "loss": 0.9804122161865234, "step": 258400 }, { "epoch": 2.977351653112007, "grad_norm": 0.52734375, "learning_rate": 2.2176851703727404e-05, "loss": 0.9570524597167969, "step": 258600 }, { "epoch": 2.9796543381867218, "grad_norm": 0.57421875, "learning_rate": 2.216958013990489e-05, "loss": 0.9921315002441407, "step": 258800 }, { "epoch": 2.9819570232614367, "grad_norm": 0.58984375, "learning_rate": 2.2162308576082372e-05, "loss": 0.9853153228759766, "step": 259000 }, { "epoch": 2.9842597083361517, "grad_norm": 0.67578125, "learning_rate": 2.2155037012259855e-05, "loss": 0.9744070434570312, "step": 259200 }, { "epoch": 2.9865623934108667, "grad_norm": 0.77734375, "learning_rate": 2.214776544843734e-05, "loss": 1.001054458618164, "step": 259400 }, { "epoch": 2.9888650784855817, "grad_norm": 1.3984375, "learning_rate": 2.2140493884614827e-05, "loss": 1.0041928100585937, "step": 259600 }, { "epoch": 2.9911677635602967, "grad_norm": 0.515625, "learning_rate": 2.213322232079231e-05, "loss": 0.9652430725097656, "step": 259800 }, { "epoch": 2.993470448635011, "grad_norm": 0.578125, "learning_rate": 2.2125950756969795e-05, "loss": 0.98406982421875, "step": 260000 }, { "epoch": 2.9957731337097266, "grad_norm": 0.470703125, "learning_rate": 2.211867919314728e-05, "loss": 0.9826647186279297, "step": 260200 }, { "epoch": 2.998075818784441, "grad_norm": 0.50390625, "learning_rate": 2.2111407629324764e-05, "loss": 0.9724476623535157, "step": 260400 }, { "epoch": 3.0, "eval_loss": NaN, "eval_runtime": 430.4459, "eval_samples_per_second": 65.887, "eval_steps_per_second": 32.945, "step": 260568 }, { "epoch": 3.0003684296119544, "grad_norm": 0.6953125, "learning_rate": 2.2104136065502246e-05, "loss": 0.9871656036376953, "step": 260600 }, { "epoch": 3.0026711146866694, "grad_norm": 0.470703125, "learning_rate": 2.2096864501679732e-05, "loss": 0.9829486083984375, "step": 260800 }, { "epoch": 3.0049737997613843, "grad_norm": 0.70703125, "learning_rate": 2.2089592937857215e-05, "loss": 0.9937672424316406, "step": 261000 }, { "epoch": 3.0072764848360993, "grad_norm": 0.6796875, "learning_rate": 2.20823213740347e-05, "loss": 0.9738970947265625, "step": 261200 }, { "epoch": 3.0095791699108143, "grad_norm": 0.8203125, "learning_rate": 2.2075049810212186e-05, "loss": 0.9735186004638672, "step": 261400 }, { "epoch": 3.011881854985529, "grad_norm": 0.69140625, "learning_rate": 2.206777824638967e-05, "loss": 1.0058969116210938, "step": 261600 }, { "epoch": 3.014184540060244, "grad_norm": 0.87109375, "learning_rate": 2.206050668256715e-05, "loss": 1.0027965545654296, "step": 261800 }, { "epoch": 3.016487225134959, "grad_norm": 0.79296875, "learning_rate": 2.2053235118744637e-05, "loss": 0.9587387084960938, "step": 262000 }, { "epoch": 3.018789910209674, "grad_norm": 0.60546875, "learning_rate": 2.2045963554922123e-05, "loss": 0.952236557006836, "step": 262200 }, { "epoch": 3.021092595284389, "grad_norm": 1.8984375, "learning_rate": 2.2038691991099606e-05, "loss": 0.9858063507080078, "step": 262400 }, { "epoch": 3.0233952803591038, "grad_norm": 1.0546875, "learning_rate": 2.2031420427277092e-05, "loss": 1.0064692687988281, "step": 262600 }, { "epoch": 3.0256979654338187, "grad_norm": 0.8046875, "learning_rate": 2.2024148863454578e-05, "loss": 0.9844532012939453, "step": 262800 }, { "epoch": 3.0280006505085337, "grad_norm": 1.3359375, "learning_rate": 2.201687729963206e-05, "loss": 0.9752964782714844, "step": 263000 }, { "epoch": 3.0303033355832487, "grad_norm": 0.423828125, "learning_rate": 2.2009605735809543e-05, "loss": 0.970207748413086, "step": 263200 }, { "epoch": 3.0326060206579637, "grad_norm": 1.1484375, "learning_rate": 2.200233417198703e-05, "loss": 0.9757695007324219, "step": 263400 }, { "epoch": 3.0349087057326782, "grad_norm": 1.1875, "learning_rate": 2.199506260816451e-05, "loss": 0.9893525695800781, "step": 263600 }, { "epoch": 3.037211390807393, "grad_norm": 0.66796875, "learning_rate": 2.1987791044341997e-05, "loss": 0.9798577880859375, "step": 263800 }, { "epoch": 3.039514075882108, "grad_norm": 0.53125, "learning_rate": 2.1980519480519483e-05, "loss": 0.9850680541992187, "step": 264000 }, { "epoch": 3.041816760956823, "grad_norm": 0.6171875, "learning_rate": 2.1973247916696966e-05, "loss": 0.958910140991211, "step": 264200 }, { "epoch": 3.044119446031538, "grad_norm": 0.6171875, "learning_rate": 2.1965976352874448e-05, "loss": 0.9847620391845703, "step": 264400 }, { "epoch": 3.046422131106253, "grad_norm": 0.58203125, "learning_rate": 2.1958704789051934e-05, "loss": 0.9931247711181641, "step": 264600 }, { "epoch": 3.048724816180968, "grad_norm": 0.69140625, "learning_rate": 2.1951433225229416e-05, "loss": 0.9987555694580078, "step": 264800 }, { "epoch": 3.051027501255683, "grad_norm": 0.5, "learning_rate": 2.1944161661406902e-05, "loss": 0.9749890899658203, "step": 265000 }, { "epoch": 3.053330186330398, "grad_norm": 0.875, "learning_rate": 2.193689009758439e-05, "loss": 0.9770771026611328, "step": 265200 }, { "epoch": 3.0556328714051126, "grad_norm": 0.87890625, "learning_rate": 2.1929618533761874e-05, "loss": 0.9705675506591797, "step": 265400 }, { "epoch": 3.0579355564798276, "grad_norm": 0.52734375, "learning_rate": 2.1922346969939353e-05, "loss": 0.985162124633789, "step": 265600 }, { "epoch": 3.0602382415545426, "grad_norm": 0.80859375, "learning_rate": 2.191507540611684e-05, "loss": 0.9938688659667969, "step": 265800 }, { "epoch": 3.0625409266292576, "grad_norm": 1.171875, "learning_rate": 2.1907803842294325e-05, "loss": 0.9857105255126953, "step": 266000 }, { "epoch": 3.0648436117039726, "grad_norm": 0.494140625, "learning_rate": 2.1900532278471808e-05, "loss": 0.9707794952392578, "step": 266200 }, { "epoch": 3.0671462967786876, "grad_norm": 0.55859375, "learning_rate": 2.1893260714649294e-05, "loss": 0.9963924407958984, "step": 266400 }, { "epoch": 3.0694489818534025, "grad_norm": 0.69140625, "learning_rate": 2.188598915082678e-05, "loss": 0.98943603515625, "step": 266600 }, { "epoch": 3.0717516669281175, "grad_norm": 2.09375, "learning_rate": 2.1878717587004262e-05, "loss": 0.9711357879638672, "step": 266800 }, { "epoch": 3.0740543520028325, "grad_norm": 0.59375, "learning_rate": 2.1871446023181745e-05, "loss": 1.0122907257080078, "step": 267000 }, { "epoch": 3.076357037077547, "grad_norm": 1.0625, "learning_rate": 2.186417445935923e-05, "loss": 0.9749220275878906, "step": 267200 }, { "epoch": 3.078659722152262, "grad_norm": 0.65625, "learning_rate": 2.1856902895536713e-05, "loss": 0.9898588562011719, "step": 267400 }, { "epoch": 3.080962407226977, "grad_norm": 0.8046875, "learning_rate": 2.18496313317142e-05, "loss": 0.9629341888427735, "step": 267600 }, { "epoch": 3.083265092301692, "grad_norm": 0.92578125, "learning_rate": 2.1842359767891685e-05, "loss": 0.9805014038085937, "step": 267800 }, { "epoch": 3.085567777376407, "grad_norm": 0.58984375, "learning_rate": 2.1835088204069167e-05, "loss": 0.9865693664550781, "step": 268000 }, { "epoch": 3.087870462451122, "grad_norm": 0.392578125, "learning_rate": 2.182781664024665e-05, "loss": 0.957706298828125, "step": 268200 }, { "epoch": 3.090173147525837, "grad_norm": 0.46484375, "learning_rate": 2.1820545076424136e-05, "loss": 0.96357177734375, "step": 268400 }, { "epoch": 3.092475832600552, "grad_norm": 0.5078125, "learning_rate": 2.1813273512601622e-05, "loss": 1.0093704223632813, "step": 268600 }, { "epoch": 3.094778517675267, "grad_norm": 0.6015625, "learning_rate": 2.1806001948779104e-05, "loss": 1.0027647399902344, "step": 268800 }, { "epoch": 3.0970812027499814, "grad_norm": 0.5546875, "learning_rate": 2.179873038495659e-05, "loss": 0.990602798461914, "step": 269000 }, { "epoch": 3.0993838878246964, "grad_norm": 0.6640625, "learning_rate": 2.1791458821134076e-05, "loss": 0.9695339202880859, "step": 269200 }, { "epoch": 3.1016865728994114, "grad_norm": 0.75, "learning_rate": 2.1784187257311555e-05, "loss": 0.9737651062011718, "step": 269400 }, { "epoch": 3.1039892579741264, "grad_norm": 0.78515625, "learning_rate": 2.177691569348904e-05, "loss": 0.9789590454101562, "step": 269600 }, { "epoch": 3.1062919430488414, "grad_norm": 0.68359375, "learning_rate": 2.1769644129666527e-05, "loss": 0.9908535003662109, "step": 269800 }, { "epoch": 3.1085946281235564, "grad_norm": 0.78515625, "learning_rate": 2.176237256584401e-05, "loss": 0.9667711639404297, "step": 270000 }, { "epoch": 3.1108973131982713, "grad_norm": 0.52734375, "learning_rate": 2.1755101002021495e-05, "loss": 0.9762010192871093, "step": 270200 }, { "epoch": 3.1131999982729863, "grad_norm": 0.59765625, "learning_rate": 2.174782943819898e-05, "loss": 0.9766085815429687, "step": 270400 }, { "epoch": 3.1155026833477013, "grad_norm": 0.84375, "learning_rate": 2.1740557874376464e-05, "loss": 0.9565920257568359, "step": 270600 }, { "epoch": 3.117805368422416, "grad_norm": 0.75, "learning_rate": 2.1733286310553946e-05, "loss": 1.0026136016845704, "step": 270800 }, { "epoch": 3.120108053497131, "grad_norm": 0.8125, "learning_rate": 2.1726014746731432e-05, "loss": 0.9930970001220704, "step": 271000 }, { "epoch": 3.122410738571846, "grad_norm": 0.482421875, "learning_rate": 2.1718743182908918e-05, "loss": 0.9859510803222656, "step": 271200 }, { "epoch": 3.124713423646561, "grad_norm": 0.640625, "learning_rate": 2.17114716190864e-05, "loss": 0.9907965087890624, "step": 271400 }, { "epoch": 3.1270161087212758, "grad_norm": 0.76171875, "learning_rate": 2.1704200055263887e-05, "loss": 0.9711041259765625, "step": 271600 }, { "epoch": 3.1293187937959908, "grad_norm": 0.796875, "learning_rate": 2.1696928491441373e-05, "loss": 0.9887767028808594, "step": 271800 }, { "epoch": 3.1316214788707057, "grad_norm": 0.5390625, "learning_rate": 2.1689656927618852e-05, "loss": 0.9776232147216797, "step": 272000 }, { "epoch": 3.1339241639454207, "grad_norm": 0.9453125, "learning_rate": 2.1682385363796338e-05, "loss": 0.9863359069824219, "step": 272200 }, { "epoch": 3.1362268490201357, "grad_norm": 0.80078125, "learning_rate": 2.1675113799973824e-05, "loss": 0.9684203338623046, "step": 272400 }, { "epoch": 3.1385295340948502, "grad_norm": 0.609375, "learning_rate": 2.1667842236151306e-05, "loss": 0.9655731964111328, "step": 272600 }, { "epoch": 3.1408322191695652, "grad_norm": 1.015625, "learning_rate": 2.1660570672328792e-05, "loss": 0.9733708953857422, "step": 272800 }, { "epoch": 3.14313490424428, "grad_norm": 0.77734375, "learning_rate": 2.1653299108506278e-05, "loss": 0.9558826446533203, "step": 273000 }, { "epoch": 3.145437589318995, "grad_norm": 0.56640625, "learning_rate": 2.164602754468376e-05, "loss": 0.9840922546386719, "step": 273200 }, { "epoch": 3.14774027439371, "grad_norm": 0.53515625, "learning_rate": 2.1638755980861243e-05, "loss": 0.9617237854003906, "step": 273400 }, { "epoch": 3.150042959468425, "grad_norm": 0.9296875, "learning_rate": 2.163148441703873e-05, "loss": 0.9859131622314453, "step": 273600 }, { "epoch": 3.15234564454314, "grad_norm": 0.447265625, "learning_rate": 2.162421285321621e-05, "loss": 0.9815999603271485, "step": 273800 }, { "epoch": 3.154648329617855, "grad_norm": 0.75, "learning_rate": 2.1616941289393697e-05, "loss": 0.9714360809326172, "step": 274000 }, { "epoch": 3.15695101469257, "grad_norm": 0.63671875, "learning_rate": 2.1609669725571183e-05, "loss": 0.9890179443359375, "step": 274200 }, { "epoch": 3.159253699767285, "grad_norm": 0.61328125, "learning_rate": 2.160239816174867e-05, "loss": 0.9887825012207031, "step": 274400 }, { "epoch": 3.1615563848419996, "grad_norm": 1.140625, "learning_rate": 2.159512659792615e-05, "loss": 0.9828462219238281, "step": 274600 }, { "epoch": 3.1638590699167146, "grad_norm": 0.89453125, "learning_rate": 2.1587855034103634e-05, "loss": 0.9640022277832031, "step": 274800 }, { "epoch": 3.1661617549914296, "grad_norm": 0.8125, "learning_rate": 2.158058347028112e-05, "loss": 0.9707381439208984, "step": 275000 }, { "epoch": 3.1684644400661446, "grad_norm": 1.1640625, "learning_rate": 2.1573311906458603e-05, "loss": 0.9819551849365235, "step": 275200 }, { "epoch": 3.1707671251408596, "grad_norm": 0.5234375, "learning_rate": 2.156604034263609e-05, "loss": 0.970483169555664, "step": 275400 }, { "epoch": 3.1730698102155745, "grad_norm": 0.54296875, "learning_rate": 2.1558768778813574e-05, "loss": 0.9733103942871094, "step": 275600 }, { "epoch": 3.1753724952902895, "grad_norm": 0.75, "learning_rate": 2.1551497214991054e-05, "loss": 0.9875724029541015, "step": 275800 }, { "epoch": 3.1776751803650045, "grad_norm": 0.6328125, "learning_rate": 2.154422565116854e-05, "loss": 0.9920774078369141, "step": 276000 }, { "epoch": 3.1799778654397195, "grad_norm": 0.93359375, "learning_rate": 2.1536954087346025e-05, "loss": 0.9924172210693359, "step": 276200 }, { "epoch": 3.182280550514434, "grad_norm": 0.6015625, "learning_rate": 2.1529682523523508e-05, "loss": 0.9932424926757812, "step": 276400 }, { "epoch": 3.184583235589149, "grad_norm": 1.1484375, "learning_rate": 2.1522410959700994e-05, "loss": 0.9929659271240234, "step": 276600 }, { "epoch": 3.186885920663864, "grad_norm": 1.1328125, "learning_rate": 2.151513939587848e-05, "loss": 0.9686992645263672, "step": 276800 }, { "epoch": 3.189188605738579, "grad_norm": 0.91796875, "learning_rate": 2.1507867832055966e-05, "loss": 0.9910945129394532, "step": 277000 }, { "epoch": 3.191491290813294, "grad_norm": 0.65625, "learning_rate": 2.1500596268233445e-05, "loss": 0.9778562164306641, "step": 277200 }, { "epoch": 3.193793975888009, "grad_norm": 1.4765625, "learning_rate": 2.149332470441093e-05, "loss": 0.9815302276611328, "step": 277400 }, { "epoch": 3.196096660962724, "grad_norm": 1.4375, "learning_rate": 2.1486053140588417e-05, "loss": 0.9855834197998047, "step": 277600 }, { "epoch": 3.198399346037439, "grad_norm": 0.6484375, "learning_rate": 2.14787815767659e-05, "loss": 0.9841216278076171, "step": 277800 }, { "epoch": 3.200702031112154, "grad_norm": 0.56640625, "learning_rate": 2.1471510012943385e-05, "loss": 0.9852655029296875, "step": 278000 }, { "epoch": 3.203004716186869, "grad_norm": 0.69140625, "learning_rate": 2.146423844912087e-05, "loss": 0.9748995971679687, "step": 278200 }, { "epoch": 3.2053074012615834, "grad_norm": 0.79296875, "learning_rate": 2.145696688529835e-05, "loss": 0.9632807922363281, "step": 278400 }, { "epoch": 3.2076100863362984, "grad_norm": 0.671875, "learning_rate": 2.1449695321475836e-05, "loss": 0.9814723205566406, "step": 278600 }, { "epoch": 3.2099127714110134, "grad_norm": 0.6640625, "learning_rate": 2.1442423757653322e-05, "loss": 0.9979678344726562, "step": 278800 }, { "epoch": 3.2122154564857284, "grad_norm": 0.77734375, "learning_rate": 2.1435152193830805e-05, "loss": 0.9872224426269531, "step": 279000 }, { "epoch": 3.2145181415604434, "grad_norm": 0.59375, "learning_rate": 2.142788063000829e-05, "loss": 0.987719497680664, "step": 279200 }, { "epoch": 3.2168208266351583, "grad_norm": 0.73828125, "learning_rate": 2.1420609066185776e-05, "loss": 0.9706076049804687, "step": 279400 }, { "epoch": 3.2191235117098733, "grad_norm": 0.8984375, "learning_rate": 2.1413337502363255e-05, "loss": 1.0041499328613281, "step": 279600 }, { "epoch": 3.2214261967845883, "grad_norm": 0.875, "learning_rate": 2.140606593854074e-05, "loss": 0.9960893249511719, "step": 279800 }, { "epoch": 3.2237288818593033, "grad_norm": 0.83984375, "learning_rate": 2.1398794374718227e-05, "loss": 0.9895648956298828, "step": 280000 }, { "epoch": 3.226031566934018, "grad_norm": 0.66015625, "learning_rate": 2.1391522810895713e-05, "loss": 0.9820411682128907, "step": 280200 }, { "epoch": 3.228334252008733, "grad_norm": 1.125, "learning_rate": 2.1384251247073196e-05, "loss": 0.993807144165039, "step": 280400 }, { "epoch": 3.230636937083448, "grad_norm": 0.7578125, "learning_rate": 2.137697968325068e-05, "loss": 0.9687660980224609, "step": 280600 }, { "epoch": 3.2329396221581628, "grad_norm": 1.7265625, "learning_rate": 2.1369708119428168e-05, "loss": 0.9756636810302735, "step": 280800 }, { "epoch": 3.2352423072328778, "grad_norm": 0.6875, "learning_rate": 2.1362436555605647e-05, "loss": 0.9740959167480469, "step": 281000 }, { "epoch": 3.2375449923075927, "grad_norm": 0.58984375, "learning_rate": 2.1355164991783133e-05, "loss": 0.9740967559814453, "step": 281200 }, { "epoch": 3.2398476773823077, "grad_norm": 0.828125, "learning_rate": 2.134789342796062e-05, "loss": 0.9790853881835937, "step": 281400 }, { "epoch": 3.2421503624570227, "grad_norm": 0.95703125, "learning_rate": 2.13406218641381e-05, "loss": 0.9897017669677735, "step": 281600 }, { "epoch": 3.2444530475317377, "grad_norm": 1.046875, "learning_rate": 2.1333350300315587e-05, "loss": 0.9742921447753906, "step": 281800 }, { "epoch": 3.2467557326064522, "grad_norm": 0.91015625, "learning_rate": 2.1326078736493073e-05, "loss": 0.9642566680908203, "step": 282000 }, { "epoch": 3.249058417681167, "grad_norm": 1.0078125, "learning_rate": 2.1318807172670552e-05, "loss": 0.9810607147216797, "step": 282200 }, { "epoch": 3.251361102755882, "grad_norm": 0.63671875, "learning_rate": 2.1311535608848038e-05, "loss": 0.9737554168701172, "step": 282400 }, { "epoch": 3.253663787830597, "grad_norm": 0.5859375, "learning_rate": 2.1304264045025524e-05, "loss": 0.9845205688476563, "step": 282600 }, { "epoch": 3.255966472905312, "grad_norm": 0.439453125, "learning_rate": 2.129699248120301e-05, "loss": 0.974234619140625, "step": 282800 }, { "epoch": 3.258269157980027, "grad_norm": 0.84375, "learning_rate": 2.1289720917380492e-05, "loss": 0.9663818359375, "step": 283000 }, { "epoch": 3.260571843054742, "grad_norm": 0.9375, "learning_rate": 2.1282449353557978e-05, "loss": 0.988833236694336, "step": 283200 }, { "epoch": 3.262874528129457, "grad_norm": 0.77734375, "learning_rate": 2.1275177789735464e-05, "loss": 0.9499282836914062, "step": 283400 }, { "epoch": 3.265177213204172, "grad_norm": 0.462890625, "learning_rate": 2.1267906225912943e-05, "loss": 0.9761683654785156, "step": 283600 }, { "epoch": 3.2674798982788866, "grad_norm": 0.7265625, "learning_rate": 2.126063466209043e-05, "loss": 0.9818894195556641, "step": 283800 }, { "epoch": 3.2697825833536016, "grad_norm": 1.4765625, "learning_rate": 2.1253363098267915e-05, "loss": 0.99319091796875, "step": 284000 }, { "epoch": 3.2720852684283166, "grad_norm": 0.44921875, "learning_rate": 2.1246091534445398e-05, "loss": 0.992230453491211, "step": 284200 }, { "epoch": 3.2743879535030316, "grad_norm": 0.431640625, "learning_rate": 2.1238819970622884e-05, "loss": 0.9897457122802734, "step": 284400 }, { "epoch": 3.2766906385777466, "grad_norm": 0.921875, "learning_rate": 2.123154840680037e-05, "loss": 0.9627342224121094, "step": 284600 }, { "epoch": 3.2789933236524615, "grad_norm": 0.6640625, "learning_rate": 2.122427684297785e-05, "loss": 0.9894837951660156, "step": 284800 }, { "epoch": 3.2812960087271765, "grad_norm": 0.62109375, "learning_rate": 2.1217005279155334e-05, "loss": 0.9815957641601563, "step": 285000 }, { "epoch": 3.2835986938018915, "grad_norm": 1.09375, "learning_rate": 2.120973371533282e-05, "loss": 0.9799363708496094, "step": 285200 }, { "epoch": 3.2859013788766065, "grad_norm": 0.76171875, "learning_rate": 2.1202462151510303e-05, "loss": 0.9863890075683593, "step": 285400 }, { "epoch": 3.288204063951321, "grad_norm": 0.4453125, "learning_rate": 2.119519058768779e-05, "loss": 0.9854249572753906, "step": 285600 }, { "epoch": 3.290506749026036, "grad_norm": 0.90625, "learning_rate": 2.1187919023865275e-05, "loss": 0.9754698944091796, "step": 285800 }, { "epoch": 3.292809434100751, "grad_norm": 0.62109375, "learning_rate": 2.1180647460042757e-05, "loss": 0.9730270385742188, "step": 286000 }, { "epoch": 3.295112119175466, "grad_norm": 0.7109375, "learning_rate": 2.117337589622024e-05, "loss": 0.9700435638427735, "step": 286200 }, { "epoch": 3.297414804250181, "grad_norm": 1.3984375, "learning_rate": 2.1166104332397726e-05, "loss": 0.9972874450683594, "step": 286400 }, { "epoch": 3.299717489324896, "grad_norm": 0.65625, "learning_rate": 2.115883276857521e-05, "loss": 0.9965068054199219, "step": 286600 }, { "epoch": 3.302020174399611, "grad_norm": 1.09375, "learning_rate": 2.1151561204752694e-05, "loss": 0.9861847686767579, "step": 286800 }, { "epoch": 3.304322859474326, "grad_norm": 0.8046875, "learning_rate": 2.114428964093018e-05, "loss": 0.9861808013916016, "step": 287000 }, { "epoch": 3.306625544549041, "grad_norm": 0.70703125, "learning_rate": 2.1137018077107666e-05, "loss": 0.9840087127685547, "step": 287200 }, { "epoch": 3.3089282296237554, "grad_norm": 0.51171875, "learning_rate": 2.1129746513285145e-05, "loss": 0.979336166381836, "step": 287400 }, { "epoch": 3.3112309146984704, "grad_norm": 0.62109375, "learning_rate": 2.112247494946263e-05, "loss": 0.9942705535888672, "step": 287600 }, { "epoch": 3.3135335997731854, "grad_norm": 0.609375, "learning_rate": 2.1115203385640117e-05, "loss": 0.9899281311035156, "step": 287800 }, { "epoch": 3.3158362848479004, "grad_norm": 0.69921875, "learning_rate": 2.11079318218176e-05, "loss": 0.9654022216796875, "step": 288000 }, { "epoch": 3.3181389699226154, "grad_norm": 1.4140625, "learning_rate": 2.1100660257995085e-05, "loss": 0.9817692565917969, "step": 288200 }, { "epoch": 3.3204416549973303, "grad_norm": 0.89453125, "learning_rate": 2.109338869417257e-05, "loss": 0.9879948425292969, "step": 288400 }, { "epoch": 3.3227443400720453, "grad_norm": 0.62890625, "learning_rate": 2.1086117130350054e-05, "loss": 0.9916354370117187, "step": 288600 }, { "epoch": 3.3250470251467603, "grad_norm": 0.7265625, "learning_rate": 2.1078845566527536e-05, "loss": 0.9782781982421875, "step": 288800 }, { "epoch": 3.3273497102214753, "grad_norm": 0.50390625, "learning_rate": 2.1071574002705022e-05, "loss": 0.9925672912597656, "step": 289000 }, { "epoch": 3.32965239529619, "grad_norm": 0.5625, "learning_rate": 2.1064302438882508e-05, "loss": 0.971702651977539, "step": 289200 }, { "epoch": 3.331955080370905, "grad_norm": 0.77734375, "learning_rate": 2.105703087505999e-05, "loss": 1.0004792022705078, "step": 289400 }, { "epoch": 3.33425776544562, "grad_norm": 0.65625, "learning_rate": 2.1049759311237477e-05, "loss": 0.9968527221679687, "step": 289600 }, { "epoch": 3.336560450520335, "grad_norm": 0.6875, "learning_rate": 2.104248774741496e-05, "loss": 0.983421630859375, "step": 289800 }, { "epoch": 3.3388631355950498, "grad_norm": 0.859375, "learning_rate": 2.103521618359244e-05, "loss": 0.9886469268798828, "step": 290000 }, { "epoch": 3.3411658206697648, "grad_norm": 0.83203125, "learning_rate": 2.1027944619769928e-05, "loss": 0.9767284393310547, "step": 290200 }, { "epoch": 3.3434685057444797, "grad_norm": 0.75390625, "learning_rate": 2.1020673055947414e-05, "loss": 0.9893907165527344, "step": 290400 }, { "epoch": 3.3457711908191947, "grad_norm": 0.54296875, "learning_rate": 2.1013401492124896e-05, "loss": 0.9892060852050781, "step": 290600 }, { "epoch": 3.3480738758939097, "grad_norm": 0.447265625, "learning_rate": 2.1006129928302382e-05, "loss": 0.9863589477539062, "step": 290800 }, { "epoch": 3.3503765609686242, "grad_norm": 0.59375, "learning_rate": 2.0998858364479868e-05, "loss": 0.9872593688964844, "step": 291000 }, { "epoch": 3.3526792460433392, "grad_norm": 0.5078125, "learning_rate": 2.0991586800657347e-05, "loss": 0.9884869384765625, "step": 291200 }, { "epoch": 3.354981931118054, "grad_norm": 0.97265625, "learning_rate": 2.0984315236834833e-05, "loss": 0.9901111602783204, "step": 291400 }, { "epoch": 3.357284616192769, "grad_norm": 0.5078125, "learning_rate": 2.097704367301232e-05, "loss": 0.9891106414794922, "step": 291600 }, { "epoch": 3.359587301267484, "grad_norm": 0.65625, "learning_rate": 2.0969772109189805e-05, "loss": 0.9849647521972656, "step": 291800 }, { "epoch": 3.361889986342199, "grad_norm": 0.49609375, "learning_rate": 2.0962500545367287e-05, "loss": 0.9863345336914062, "step": 292000 }, { "epoch": 3.364192671416914, "grad_norm": 0.6640625, "learning_rate": 2.0955228981544773e-05, "loss": 1.0030756378173828, "step": 292200 }, { "epoch": 3.366495356491629, "grad_norm": 1.109375, "learning_rate": 2.0947957417722256e-05, "loss": 0.9938818359375, "step": 292400 }, { "epoch": 3.368798041566344, "grad_norm": 0.64453125, "learning_rate": 2.0940685853899738e-05, "loss": 0.9862526702880859, "step": 292600 }, { "epoch": 3.3711007266410586, "grad_norm": 0.58984375, "learning_rate": 2.0933414290077224e-05, "loss": 0.9963729095458984, "step": 292800 }, { "epoch": 3.373403411715774, "grad_norm": 0.76953125, "learning_rate": 2.092614272625471e-05, "loss": 0.9868894195556641, "step": 293000 }, { "epoch": 3.3757060967904886, "grad_norm": 1.078125, "learning_rate": 2.0918871162432193e-05, "loss": 0.992561264038086, "step": 293200 }, { "epoch": 3.3780087818652036, "grad_norm": 0.67578125, "learning_rate": 2.091159959860968e-05, "loss": 0.9652907562255859, "step": 293400 }, { "epoch": 3.3803114669399186, "grad_norm": 0.59375, "learning_rate": 2.0904328034787164e-05, "loss": 0.9668193817138672, "step": 293600 }, { "epoch": 3.3826141520146336, "grad_norm": 0.74609375, "learning_rate": 2.0897056470964644e-05, "loss": 0.962864990234375, "step": 293800 }, { "epoch": 3.3849168370893485, "grad_norm": 0.796875, "learning_rate": 2.088978490714213e-05, "loss": 0.9714779663085937, "step": 294000 }, { "epoch": 3.3872195221640635, "grad_norm": 0.8125, "learning_rate": 2.0882513343319615e-05, "loss": 0.9760708618164062, "step": 294200 }, { "epoch": 3.3895222072387785, "grad_norm": 0.62109375, "learning_rate": 2.0875241779497098e-05, "loss": 0.9788286590576172, "step": 294400 }, { "epoch": 3.3918248923134935, "grad_norm": 0.8046875, "learning_rate": 2.0867970215674584e-05, "loss": 0.9956980133056641, "step": 294600 }, { "epoch": 3.3941275773882085, "grad_norm": 0.8828125, "learning_rate": 2.086069865185207e-05, "loss": 0.9827316284179688, "step": 294800 }, { "epoch": 3.396430262462923, "grad_norm": 0.80078125, "learning_rate": 2.0853427088029552e-05, "loss": 0.9808500671386718, "step": 295000 }, { "epoch": 3.398732947537638, "grad_norm": 0.63671875, "learning_rate": 2.0846155524207035e-05, "loss": 0.9899409484863281, "step": 295200 }, { "epoch": 3.401035632612353, "grad_norm": 0.84765625, "learning_rate": 2.083888396038452e-05, "loss": 0.9769796752929687, "step": 295400 }, { "epoch": 3.403338317687068, "grad_norm": 0.55078125, "learning_rate": 2.0831612396562007e-05, "loss": 0.9801354217529297, "step": 295600 }, { "epoch": 3.405641002761783, "grad_norm": 0.58984375, "learning_rate": 2.082434083273949e-05, "loss": 1.0167056274414064, "step": 295800 }, { "epoch": 3.407943687836498, "grad_norm": 0.953125, "learning_rate": 2.0817069268916975e-05, "loss": 0.981565933227539, "step": 296000 }, { "epoch": 3.410246372911213, "grad_norm": 0.83984375, "learning_rate": 2.0809797705094458e-05, "loss": 0.9864985656738281, "step": 296200 }, { "epoch": 3.412549057985928, "grad_norm": 0.62109375, "learning_rate": 2.080252614127194e-05, "loss": 0.9858273315429688, "step": 296400 }, { "epoch": 3.414851743060643, "grad_norm": 0.8359375, "learning_rate": 2.0795254577449426e-05, "loss": 0.9845752716064453, "step": 296600 }, { "epoch": 3.4171544281353574, "grad_norm": 0.59375, "learning_rate": 2.0787983013626912e-05, "loss": 0.979270248413086, "step": 296800 }, { "epoch": 3.4194571132100724, "grad_norm": 0.671875, "learning_rate": 2.0780711449804394e-05, "loss": 1.0109344482421876, "step": 297000 }, { "epoch": 3.4217597982847874, "grad_norm": 0.671875, "learning_rate": 2.077343988598188e-05, "loss": 0.9867710876464844, "step": 297200 }, { "epoch": 3.4240624833595024, "grad_norm": 0.435546875, "learning_rate": 2.0766168322159366e-05, "loss": 0.9730811309814453, "step": 297400 }, { "epoch": 3.4263651684342173, "grad_norm": 0.609375, "learning_rate": 2.075889675833685e-05, "loss": 0.9847515869140625, "step": 297600 }, { "epoch": 3.4286678535089323, "grad_norm": 0.44140625, "learning_rate": 2.075162519451433e-05, "loss": 0.9762758636474609, "step": 297800 }, { "epoch": 3.4309705385836473, "grad_norm": 0.8359375, "learning_rate": 2.0744353630691817e-05, "loss": 0.9684622192382812, "step": 298000 }, { "epoch": 3.4332732236583623, "grad_norm": 0.4453125, "learning_rate": 2.0737082066869303e-05, "loss": 0.9942131042480469, "step": 298200 }, { "epoch": 3.4355759087330773, "grad_norm": 0.6875, "learning_rate": 2.0729810503046786e-05, "loss": 0.9833889770507812, "step": 298400 }, { "epoch": 3.437878593807792, "grad_norm": 0.71484375, "learning_rate": 2.072253893922427e-05, "loss": 0.9864968109130859, "step": 298600 }, { "epoch": 3.440181278882507, "grad_norm": 1.0234375, "learning_rate": 2.0715267375401754e-05, "loss": 0.9911534881591797, "step": 298800 }, { "epoch": 3.442483963957222, "grad_norm": 0.458984375, "learning_rate": 2.0707995811579237e-05, "loss": 0.9858901977539063, "step": 299000 }, { "epoch": 3.4447866490319368, "grad_norm": 1.3671875, "learning_rate": 2.0700724247756723e-05, "loss": 0.9796755981445312, "step": 299200 }, { "epoch": 3.4470893341066517, "grad_norm": 0.875, "learning_rate": 2.069345268393421e-05, "loss": 0.981687240600586, "step": 299400 }, { "epoch": 3.4493920191813667, "grad_norm": 0.89453125, "learning_rate": 2.068618112011169e-05, "loss": 0.9910392761230469, "step": 299600 }, { "epoch": 3.4516947042560817, "grad_norm": 0.6015625, "learning_rate": 2.0678909556289177e-05, "loss": 0.9705625915527344, "step": 299800 }, { "epoch": 3.4539973893307967, "grad_norm": 0.75, "learning_rate": 2.067163799246666e-05, "loss": 0.9778738403320313, "step": 300000 }, { "epoch": 3.4563000744055117, "grad_norm": 0.71484375, "learning_rate": 2.0664366428644142e-05, "loss": 0.9827516937255859, "step": 300200 }, { "epoch": 3.458602759480226, "grad_norm": 1.0234375, "learning_rate": 2.0657094864821628e-05, "loss": 0.9912580108642578, "step": 300400 }, { "epoch": 3.460905444554941, "grad_norm": 0.494140625, "learning_rate": 2.0649823300999114e-05, "loss": 1.0024603271484376, "step": 300600 }, { "epoch": 3.463208129629656, "grad_norm": 0.71484375, "learning_rate": 2.06425517371766e-05, "loss": 0.9889586639404296, "step": 300800 }, { "epoch": 3.465510814704371, "grad_norm": 0.70703125, "learning_rate": 2.0635280173354082e-05, "loss": 0.97587158203125, "step": 301000 }, { "epoch": 3.467813499779086, "grad_norm": 1.1875, "learning_rate": 2.0628008609531568e-05, "loss": 0.9978359985351563, "step": 301200 }, { "epoch": 3.470116184853801, "grad_norm": 0.9375, "learning_rate": 2.062073704570905e-05, "loss": 0.9813436889648437, "step": 301400 }, { "epoch": 3.472418869928516, "grad_norm": 0.53515625, "learning_rate": 2.0613465481886533e-05, "loss": 0.9656988525390625, "step": 301600 }, { "epoch": 3.474721555003231, "grad_norm": 1.0703125, "learning_rate": 2.060619391806402e-05, "loss": 0.9734279632568359, "step": 301800 }, { "epoch": 3.477024240077946, "grad_norm": 0.53125, "learning_rate": 2.0598922354241505e-05, "loss": 0.9843352508544921, "step": 302000 }, { "epoch": 3.4793269251526606, "grad_norm": 0.609375, "learning_rate": 2.0591650790418988e-05, "loss": 0.9777169036865234, "step": 302200 }, { "epoch": 3.4816296102273756, "grad_norm": 0.5390625, "learning_rate": 2.0584379226596473e-05, "loss": 0.9745001220703124, "step": 302400 }, { "epoch": 3.4839322953020906, "grad_norm": 0.64453125, "learning_rate": 2.0577107662773956e-05, "loss": 0.9934710693359375, "step": 302600 }, { "epoch": 3.4862349803768056, "grad_norm": 0.69140625, "learning_rate": 2.056983609895144e-05, "loss": 1.0010362243652344, "step": 302800 }, { "epoch": 3.4885376654515206, "grad_norm": 0.77734375, "learning_rate": 2.0562564535128924e-05, "loss": 0.9597031402587891, "step": 303000 }, { "epoch": 3.4908403505262355, "grad_norm": 0.5625, "learning_rate": 2.055529297130641e-05, "loss": 0.9741526031494141, "step": 303200 }, { "epoch": 3.4931430356009505, "grad_norm": 0.8515625, "learning_rate": 2.0548021407483896e-05, "loss": 0.9581996917724609, "step": 303400 }, { "epoch": 3.4954457206756655, "grad_norm": 0.640625, "learning_rate": 2.054074984366138e-05, "loss": 0.982119369506836, "step": 303600 }, { "epoch": 3.4977484057503805, "grad_norm": 0.84375, "learning_rate": 2.0533478279838865e-05, "loss": 0.9806587219238281, "step": 303800 }, { "epoch": 3.500051090825095, "grad_norm": 0.7109375, "learning_rate": 2.0526206716016347e-05, "loss": 0.989941635131836, "step": 304000 }, { "epoch": 3.50235377589981, "grad_norm": 0.78515625, "learning_rate": 2.051893515219383e-05, "loss": 1.0165106201171874, "step": 304200 }, { "epoch": 3.504656460974525, "grad_norm": 1.0, "learning_rate": 2.0511663588371316e-05, "loss": 0.9855970764160156, "step": 304400 }, { "epoch": 3.50695914604924, "grad_norm": 0.73046875, "learning_rate": 2.05043920245488e-05, "loss": 0.9602165222167969, "step": 304600 }, { "epoch": 3.509261831123955, "grad_norm": 0.515625, "learning_rate": 2.0497120460726284e-05, "loss": 0.976239013671875, "step": 304800 }, { "epoch": 3.51156451619867, "grad_norm": 0.64453125, "learning_rate": 2.048984889690377e-05, "loss": 0.9843711853027344, "step": 305000 }, { "epoch": 3.513867201273385, "grad_norm": 0.48046875, "learning_rate": 2.0482577333081253e-05, "loss": 0.9723324584960937, "step": 305200 }, { "epoch": 3.5161698863481, "grad_norm": 0.57421875, "learning_rate": 2.0475305769258735e-05, "loss": 0.9799480438232422, "step": 305400 }, { "epoch": 3.518472571422815, "grad_norm": 0.7421875, "learning_rate": 2.046803420543622e-05, "loss": 1.0050213623046875, "step": 305600 }, { "epoch": 3.5207752564975294, "grad_norm": 1.125, "learning_rate": 2.0460762641613707e-05, "loss": 0.969159164428711, "step": 305800 }, { "epoch": 3.523077941572245, "grad_norm": 0.56640625, "learning_rate": 2.045349107779119e-05, "loss": 0.9573507690429688, "step": 306000 }, { "epoch": 3.5253806266469594, "grad_norm": 0.75, "learning_rate": 2.0446219513968675e-05, "loss": 1.0036588287353516, "step": 306200 }, { "epoch": 3.5276833117216744, "grad_norm": 0.7734375, "learning_rate": 2.0438947950146158e-05, "loss": 0.9807686614990234, "step": 306400 }, { "epoch": 3.5299859967963894, "grad_norm": 0.98046875, "learning_rate": 2.0431676386323644e-05, "loss": 0.9778697204589843, "step": 306600 }, { "epoch": 3.5322886818711043, "grad_norm": 0.78125, "learning_rate": 2.0424404822501126e-05, "loss": 0.9704287719726562, "step": 306800 }, { "epoch": 3.5345913669458193, "grad_norm": 0.6328125, "learning_rate": 2.0417133258678612e-05, "loss": 0.9505149841308593, "step": 307000 }, { "epoch": 3.5368940520205343, "grad_norm": 0.83203125, "learning_rate": 2.0409861694856098e-05, "loss": 0.9952140045166016, "step": 307200 }, { "epoch": 3.5391967370952493, "grad_norm": 0.46875, "learning_rate": 2.040259013103358e-05, "loss": 0.9753850555419922, "step": 307400 }, { "epoch": 3.541499422169964, "grad_norm": 0.8125, "learning_rate": 2.0395318567211067e-05, "loss": 0.9734141540527343, "step": 307600 }, { "epoch": 3.5438021072446793, "grad_norm": 0.51171875, "learning_rate": 2.038804700338855e-05, "loss": 0.9796247100830078, "step": 307800 }, { "epoch": 3.546104792319394, "grad_norm": 0.546875, "learning_rate": 2.038077543956603e-05, "loss": 0.984339599609375, "step": 308000 }, { "epoch": 3.5484074773941088, "grad_norm": 0.578125, "learning_rate": 2.0373503875743517e-05, "loss": 0.9877261352539063, "step": 308200 }, { "epoch": 3.5507101624688238, "grad_norm": 0.7109375, "learning_rate": 2.0366232311921003e-05, "loss": 0.9739342498779296, "step": 308400 }, { "epoch": 3.5530128475435387, "grad_norm": 0.484375, "learning_rate": 2.0358960748098486e-05, "loss": 0.9697119140625, "step": 308600 }, { "epoch": 3.5553155326182537, "grad_norm": 0.44921875, "learning_rate": 2.0351689184275972e-05, "loss": 0.9906707763671875, "step": 308800 }, { "epoch": 3.5576182176929687, "grad_norm": 0.76171875, "learning_rate": 2.0344417620453454e-05, "loss": 0.986513671875, "step": 309000 }, { "epoch": 3.5599209027676837, "grad_norm": 0.6796875, "learning_rate": 2.033714605663094e-05, "loss": 0.9764996337890625, "step": 309200 }, { "epoch": 3.5622235878423982, "grad_norm": 0.66015625, "learning_rate": 2.0329874492808423e-05, "loss": 0.990147705078125, "step": 309400 }, { "epoch": 3.5645262729171137, "grad_norm": 0.79296875, "learning_rate": 2.032260292898591e-05, "loss": 0.9730393981933594, "step": 309600 }, { "epoch": 3.566828957991828, "grad_norm": 0.478515625, "learning_rate": 2.0315331365163395e-05, "loss": 0.9966936492919922, "step": 309800 }, { "epoch": 3.569131643066543, "grad_norm": 0.515625, "learning_rate": 2.0308059801340877e-05, "loss": 0.9686882781982422, "step": 310000 }, { "epoch": 3.571434328141258, "grad_norm": 0.83203125, "learning_rate": 2.030078823751836e-05, "loss": 0.9749455261230469, "step": 310200 }, { "epoch": 3.573737013215973, "grad_norm": 0.5859375, "learning_rate": 2.0293516673695846e-05, "loss": 0.9812612152099609, "step": 310400 }, { "epoch": 3.576039698290688, "grad_norm": 0.81640625, "learning_rate": 2.0286245109873328e-05, "loss": 0.9691918182373047, "step": 310600 }, { "epoch": 3.578342383365403, "grad_norm": 0.6484375, "learning_rate": 2.0278973546050814e-05, "loss": 0.9892355346679688, "step": 310800 }, { "epoch": 3.580645068440118, "grad_norm": 0.5390625, "learning_rate": 2.02717019822283e-05, "loss": 0.9764984130859375, "step": 311000 }, { "epoch": 3.5829477535148326, "grad_norm": 0.64453125, "learning_rate": 2.0264430418405782e-05, "loss": 0.9705098724365234, "step": 311200 }, { "epoch": 3.585250438589548, "grad_norm": 0.67578125, "learning_rate": 2.025715885458327e-05, "loss": 0.9755960845947266, "step": 311400 }, { "epoch": 3.5875531236642626, "grad_norm": 0.546875, "learning_rate": 2.024988729076075e-05, "loss": 0.9599433898925781, "step": 311600 }, { "epoch": 3.5898558087389776, "grad_norm": 0.515625, "learning_rate": 2.0242615726938233e-05, "loss": 0.9769892883300781, "step": 311800 }, { "epoch": 3.5921584938136926, "grad_norm": 0.515625, "learning_rate": 2.023534416311572e-05, "loss": 1.0197854614257813, "step": 312000 }, { "epoch": 3.5944611788884075, "grad_norm": 0.58984375, "learning_rate": 2.0228072599293205e-05, "loss": 0.9848535919189453, "step": 312200 }, { "epoch": 3.5967638639631225, "grad_norm": 0.73046875, "learning_rate": 2.022080103547069e-05, "loss": 0.9727433776855469, "step": 312400 }, { "epoch": 3.5990665490378375, "grad_norm": 0.7890625, "learning_rate": 2.0213529471648174e-05, "loss": 0.9948325347900391, "step": 312600 }, { "epoch": 3.6013692341125525, "grad_norm": 0.640625, "learning_rate": 2.0206257907825656e-05, "loss": 0.9774640655517578, "step": 312800 }, { "epoch": 3.603671919187267, "grad_norm": 1.765625, "learning_rate": 2.0198986344003142e-05, "loss": 0.9790972900390625, "step": 313000 }, { "epoch": 3.6059746042619825, "grad_norm": 0.421875, "learning_rate": 2.0191714780180625e-05, "loss": 0.9803644561767578, "step": 313200 }, { "epoch": 3.608277289336697, "grad_norm": 0.7109375, "learning_rate": 2.018444321635811e-05, "loss": 0.9680404663085938, "step": 313400 }, { "epoch": 3.610579974411412, "grad_norm": 0.48046875, "learning_rate": 2.0177171652535597e-05, "loss": 0.9820728302001953, "step": 313600 }, { "epoch": 3.612882659486127, "grad_norm": 0.65234375, "learning_rate": 2.016990008871308e-05, "loss": 1.0057897186279297, "step": 313800 }, { "epoch": 3.615185344560842, "grad_norm": 0.40234375, "learning_rate": 2.0162628524890565e-05, "loss": 0.9696613311767578, "step": 314000 }, { "epoch": 3.617488029635557, "grad_norm": 0.7421875, "learning_rate": 2.0155356961068047e-05, "loss": 0.9803009033203125, "step": 314200 }, { "epoch": 3.619790714710272, "grad_norm": 0.890625, "learning_rate": 2.014808539724553e-05, "loss": 0.9822318267822265, "step": 314400 }, { "epoch": 3.622093399784987, "grad_norm": 0.8828125, "learning_rate": 2.0140813833423016e-05, "loss": 0.985562744140625, "step": 314600 }, { "epoch": 3.6243960848597014, "grad_norm": 1.1015625, "learning_rate": 2.0133542269600502e-05, "loss": 0.9913748168945312, "step": 314800 }, { "epoch": 3.626698769934417, "grad_norm": 0.41015625, "learning_rate": 2.0126270705777984e-05, "loss": 0.974439697265625, "step": 315000 }, { "epoch": 3.6290014550091314, "grad_norm": 0.66015625, "learning_rate": 2.011899914195547e-05, "loss": 0.972523193359375, "step": 315200 }, { "epoch": 3.6313041400838464, "grad_norm": 0.6015625, "learning_rate": 2.0111727578132953e-05, "loss": 0.9973404693603516, "step": 315400 }, { "epoch": 3.6336068251585614, "grad_norm": 0.921875, "learning_rate": 2.010445601431044e-05, "loss": 0.9800202941894531, "step": 315600 }, { "epoch": 3.6359095102332764, "grad_norm": 0.470703125, "learning_rate": 2.009718445048792e-05, "loss": 0.9633809661865235, "step": 315800 }, { "epoch": 3.6382121953079913, "grad_norm": 0.57421875, "learning_rate": 2.0089912886665407e-05, "loss": 0.9927108001708984, "step": 316000 }, { "epoch": 3.6405148803827063, "grad_norm": 0.53515625, "learning_rate": 2.0082641322842893e-05, "loss": 0.9627687072753907, "step": 316200 }, { "epoch": 3.6428175654574213, "grad_norm": 0.69140625, "learning_rate": 2.0075369759020376e-05, "loss": 0.9577132415771484, "step": 316400 }, { "epoch": 3.6451202505321363, "grad_norm": 0.7109375, "learning_rate": 2.0068098195197858e-05, "loss": 0.9758236694335938, "step": 316600 }, { "epoch": 3.6474229356068513, "grad_norm": 1.046875, "learning_rate": 2.0060826631375344e-05, "loss": 0.9763569641113281, "step": 316800 }, { "epoch": 3.649725620681566, "grad_norm": 0.80859375, "learning_rate": 2.0053555067552827e-05, "loss": 0.9699946594238281, "step": 317000 }, { "epoch": 3.652028305756281, "grad_norm": 0.55078125, "learning_rate": 2.0046283503730312e-05, "loss": 0.988985824584961, "step": 317200 }, { "epoch": 3.6543309908309958, "grad_norm": 0.859375, "learning_rate": 2.00390119399078e-05, "loss": 0.9836240386962891, "step": 317400 }, { "epoch": 3.6566336759057108, "grad_norm": 0.57421875, "learning_rate": 2.003174037608528e-05, "loss": 0.9703248596191406, "step": 317600 }, { "epoch": 3.6589363609804257, "grad_norm": 0.9453125, "learning_rate": 2.0024468812262767e-05, "loss": 0.9764913940429687, "step": 317800 }, { "epoch": 3.6612390460551407, "grad_norm": 0.73046875, "learning_rate": 2.001719724844025e-05, "loss": 0.9827780914306641, "step": 318000 }, { "epoch": 3.6635417311298557, "grad_norm": 0.69921875, "learning_rate": 2.0009925684617735e-05, "loss": 0.9800835418701171, "step": 318200 }, { "epoch": 3.6658444162045707, "grad_norm": 0.51171875, "learning_rate": 2.0002654120795218e-05, "loss": 0.9786171722412109, "step": 318400 }, { "epoch": 3.6681471012792857, "grad_norm": 0.578125, "learning_rate": 1.9995382556972704e-05, "loss": 0.99401611328125, "step": 318600 }, { "epoch": 3.670449786354, "grad_norm": 0.9296875, "learning_rate": 1.998811099315019e-05, "loss": 0.9821390533447265, "step": 318800 }, { "epoch": 3.672752471428715, "grad_norm": 0.671875, "learning_rate": 1.9980839429327672e-05, "loss": 0.9792152404785156, "step": 319000 }, { "epoch": 3.67505515650343, "grad_norm": 0.55078125, "learning_rate": 1.9973567865505155e-05, "loss": 0.9921223449707032, "step": 319200 }, { "epoch": 3.677357841578145, "grad_norm": 0.78515625, "learning_rate": 1.996629630168264e-05, "loss": 0.984896011352539, "step": 319400 }, { "epoch": 3.67966052665286, "grad_norm": 1.125, "learning_rate": 1.9959024737860123e-05, "loss": 0.9692173004150391, "step": 319600 }, { "epoch": 3.681963211727575, "grad_norm": 0.546875, "learning_rate": 1.995175317403761e-05, "loss": 0.9897268676757812, "step": 319800 }, { "epoch": 3.68426589680229, "grad_norm": 0.44140625, "learning_rate": 1.9944481610215095e-05, "loss": 0.9933697509765625, "step": 320000 }, { "epoch": 3.686568581877005, "grad_norm": 0.7265625, "learning_rate": 1.9937210046392577e-05, "loss": 0.9815640258789062, "step": 320200 }, { "epoch": 3.68887126695172, "grad_norm": 0.431640625, "learning_rate": 1.9929938482570063e-05, "loss": 0.9922060394287109, "step": 320400 }, { "epoch": 3.6911739520264346, "grad_norm": 1.03125, "learning_rate": 1.9922666918747546e-05, "loss": 1.0016986083984376, "step": 320600 }, { "epoch": 3.6934766371011496, "grad_norm": 1.1953125, "learning_rate": 1.991539535492503e-05, "loss": 0.9736055755615234, "step": 320800 }, { "epoch": 3.6957793221758646, "grad_norm": 1.109375, "learning_rate": 1.9908123791102514e-05, "loss": 0.9745178985595703, "step": 321000 }, { "epoch": 3.6980820072505796, "grad_norm": 0.6484375, "learning_rate": 1.990085222728e-05, "loss": 0.9692243194580078, "step": 321200 }, { "epoch": 3.7003846923252945, "grad_norm": 0.84765625, "learning_rate": 1.9893580663457486e-05, "loss": 0.9790972137451172, "step": 321400 }, { "epoch": 3.7026873774000095, "grad_norm": 0.486328125, "learning_rate": 1.988630909963497e-05, "loss": 0.9805580139160156, "step": 321600 }, { "epoch": 3.7049900624747245, "grad_norm": 0.578125, "learning_rate": 1.987903753581245e-05, "loss": 0.9620713806152343, "step": 321800 }, { "epoch": 3.7072927475494395, "grad_norm": 0.79296875, "learning_rate": 1.9871765971989937e-05, "loss": 0.9783279418945312, "step": 322000 }, { "epoch": 3.7095954326241545, "grad_norm": 0.5390625, "learning_rate": 1.986449440816742e-05, "loss": 0.9842681884765625, "step": 322200 }, { "epoch": 3.711898117698869, "grad_norm": 0.73046875, "learning_rate": 1.9857222844344906e-05, "loss": 0.9877159881591797, "step": 322400 }, { "epoch": 3.7142008027735844, "grad_norm": 0.69140625, "learning_rate": 1.984995128052239e-05, "loss": 0.9558129119873047, "step": 322600 }, { "epoch": 3.716503487848299, "grad_norm": 0.6328125, "learning_rate": 1.9842679716699874e-05, "loss": 0.964300537109375, "step": 322800 }, { "epoch": 3.718806172923014, "grad_norm": 0.4140625, "learning_rate": 1.9835408152877357e-05, "loss": 0.9851215362548829, "step": 323000 }, { "epoch": 3.721108857997729, "grad_norm": 0.8203125, "learning_rate": 1.9828136589054842e-05, "loss": 0.9854248046875, "step": 323200 }, { "epoch": 3.723411543072444, "grad_norm": 0.55859375, "learning_rate": 1.9820865025232325e-05, "loss": 0.981217041015625, "step": 323400 }, { "epoch": 3.725714228147159, "grad_norm": 0.69140625, "learning_rate": 1.981359346140981e-05, "loss": 0.9648824310302735, "step": 323600 }, { "epoch": 3.728016913221874, "grad_norm": 0.8359375, "learning_rate": 1.9806321897587297e-05, "loss": 0.9728410339355469, "step": 323800 }, { "epoch": 3.730319598296589, "grad_norm": 0.404296875, "learning_rate": 1.9799050333764783e-05, "loss": 0.9918624114990234, "step": 324000 }, { "epoch": 3.7326222833713034, "grad_norm": 0.85546875, "learning_rate": 1.9791778769942265e-05, "loss": 0.9825603485107421, "step": 324200 }, { "epoch": 3.734924968446019, "grad_norm": 0.98828125, "learning_rate": 1.9784507206119748e-05, "loss": 0.987041015625, "step": 324400 }, { "epoch": 3.7372276535207334, "grad_norm": 0.62109375, "learning_rate": 1.9777235642297234e-05, "loss": 0.9773162841796875, "step": 324600 }, { "epoch": 3.7395303385954484, "grad_norm": 0.451171875, "learning_rate": 1.9769964078474716e-05, "loss": 0.980873031616211, "step": 324800 }, { "epoch": 3.7418330236701633, "grad_norm": 0.953125, "learning_rate": 1.9762692514652202e-05, "loss": 0.9816900634765625, "step": 325000 }, { "epoch": 3.7441357087448783, "grad_norm": 0.69140625, "learning_rate": 1.9755420950829688e-05, "loss": 0.9802275085449219, "step": 325200 }, { "epoch": 3.7464383938195933, "grad_norm": 0.734375, "learning_rate": 1.974814938700717e-05, "loss": 0.9866002655029297, "step": 325400 }, { "epoch": 3.7487410788943083, "grad_norm": 0.8359375, "learning_rate": 1.9740877823184653e-05, "loss": 0.9880412292480468, "step": 325600 }, { "epoch": 3.7510437639690233, "grad_norm": 0.462890625, "learning_rate": 1.973360625936214e-05, "loss": 0.9862410736083984, "step": 325800 }, { "epoch": 3.753346449043738, "grad_norm": 0.66015625, "learning_rate": 1.972633469553962e-05, "loss": 0.9755754852294922, "step": 326000 }, { "epoch": 3.7556491341184532, "grad_norm": 0.64453125, "learning_rate": 1.9719063131717107e-05, "loss": 1.0151551055908203, "step": 326200 }, { "epoch": 3.757951819193168, "grad_norm": 0.63671875, "learning_rate": 1.9711791567894593e-05, "loss": 0.9837895202636718, "step": 326400 }, { "epoch": 3.7602545042678828, "grad_norm": 0.59375, "learning_rate": 1.9704520004072076e-05, "loss": 0.9870108795166016, "step": 326600 }, { "epoch": 3.7625571893425978, "grad_norm": 0.78125, "learning_rate": 1.969724844024956e-05, "loss": 0.9984638977050782, "step": 326800 }, { "epoch": 3.7648598744173127, "grad_norm": 0.515625, "learning_rate": 1.9689976876427044e-05, "loss": 0.9689566040039063, "step": 327000 }, { "epoch": 3.7671625594920277, "grad_norm": 0.98828125, "learning_rate": 1.968270531260453e-05, "loss": 0.9929909515380859, "step": 327200 }, { "epoch": 3.7694652445667427, "grad_norm": 0.8984375, "learning_rate": 1.9675433748782013e-05, "loss": 1.0006656646728516, "step": 327400 }, { "epoch": 3.7717679296414577, "grad_norm": 0.79296875, "learning_rate": 1.96681621849595e-05, "loss": 0.9882119750976562, "step": 327600 }, { "epoch": 3.7740706147161722, "grad_norm": 0.73046875, "learning_rate": 1.9660890621136985e-05, "loss": 0.9780780029296875, "step": 327800 }, { "epoch": 3.7763732997908876, "grad_norm": 0.98828125, "learning_rate": 1.9653619057314467e-05, "loss": 0.9838511657714843, "step": 328000 }, { "epoch": 3.778675984865602, "grad_norm": 0.7578125, "learning_rate": 1.964634749349195e-05, "loss": 0.9679155731201172, "step": 328200 }, { "epoch": 3.780978669940317, "grad_norm": 0.86328125, "learning_rate": 1.9639075929669436e-05, "loss": 0.9874655151367188, "step": 328400 }, { "epoch": 3.783281355015032, "grad_norm": 0.94921875, "learning_rate": 1.9631804365846918e-05, "loss": 0.9853670501708984, "step": 328600 }, { "epoch": 3.785584040089747, "grad_norm": 0.93359375, "learning_rate": 1.9624532802024404e-05, "loss": 0.973040771484375, "step": 328800 }, { "epoch": 3.787886725164462, "grad_norm": 0.65625, "learning_rate": 1.961726123820189e-05, "loss": 1.0069470977783204, "step": 329000 }, { "epoch": 3.790189410239177, "grad_norm": 0.59375, "learning_rate": 1.9609989674379372e-05, "loss": 1.0185445404052735, "step": 329200 }, { "epoch": 3.792492095313892, "grad_norm": 0.53515625, "learning_rate": 1.9602718110556855e-05, "loss": 0.9744924926757812, "step": 329400 }, { "epoch": 3.7947947803886066, "grad_norm": 0.49609375, "learning_rate": 1.959544654673434e-05, "loss": 0.955069808959961, "step": 329600 }, { "epoch": 3.797097465463322, "grad_norm": 0.5625, "learning_rate": 1.9588174982911827e-05, "loss": 0.9998871612548829, "step": 329800 }, { "epoch": 3.7994001505380366, "grad_norm": 0.4765625, "learning_rate": 1.958090341908931e-05, "loss": 0.9712278747558594, "step": 330000 }, { "epoch": 3.8017028356127516, "grad_norm": 0.68359375, "learning_rate": 1.9573631855266795e-05, "loss": 0.9825238037109375, "step": 330200 }, { "epoch": 3.8040055206874666, "grad_norm": 0.41796875, "learning_rate": 1.956636029144428e-05, "loss": 0.9737995910644531, "step": 330400 }, { "epoch": 3.8063082057621815, "grad_norm": 0.57421875, "learning_rate": 1.9559088727621764e-05, "loss": 0.9713996124267578, "step": 330600 }, { "epoch": 3.8086108908368965, "grad_norm": 0.55859375, "learning_rate": 1.9551817163799246e-05, "loss": 0.9742137145996094, "step": 330800 }, { "epoch": 3.8109135759116115, "grad_norm": 0.51171875, "learning_rate": 1.9544545599976732e-05, "loss": 0.9718436431884766, "step": 331000 }, { "epoch": 3.8132162609863265, "grad_norm": 0.53125, "learning_rate": 1.9537274036154215e-05, "loss": 0.9649051666259766, "step": 331200 }, { "epoch": 3.815518946061041, "grad_norm": 0.68359375, "learning_rate": 1.95300024723317e-05, "loss": 0.9786886596679687, "step": 331400 }, { "epoch": 3.8178216311357565, "grad_norm": 1.3203125, "learning_rate": 1.9522730908509186e-05, "loss": 0.9678800964355468, "step": 331600 }, { "epoch": 3.820124316210471, "grad_norm": 0.5, "learning_rate": 1.951545934468667e-05, "loss": 0.9907022094726563, "step": 331800 }, { "epoch": 3.822427001285186, "grad_norm": 0.49609375, "learning_rate": 1.950818778086415e-05, "loss": 0.9843609619140625, "step": 332000 }, { "epoch": 3.824729686359901, "grad_norm": 0.6484375, "learning_rate": 1.9500916217041637e-05, "loss": 0.9689896392822266, "step": 332200 }, { "epoch": 3.827032371434616, "grad_norm": 0.451171875, "learning_rate": 1.949364465321912e-05, "loss": 0.9918228149414062, "step": 332400 }, { "epoch": 3.829335056509331, "grad_norm": 0.53125, "learning_rate": 1.9486373089396606e-05, "loss": 0.9822836303710938, "step": 332600 }, { "epoch": 3.831637741584046, "grad_norm": 0.796875, "learning_rate": 1.9479101525574092e-05, "loss": 0.9748810577392578, "step": 332800 }, { "epoch": 3.833940426658761, "grad_norm": 0.8515625, "learning_rate": 1.9471829961751578e-05, "loss": 0.9820301055908203, "step": 333000 }, { "epoch": 3.836243111733476, "grad_norm": 1.0546875, "learning_rate": 1.9464558397929057e-05, "loss": 0.9797927856445312, "step": 333200 }, { "epoch": 3.838545796808191, "grad_norm": 0.4921875, "learning_rate": 1.9457286834106543e-05, "loss": 0.9862161254882813, "step": 333400 }, { "epoch": 3.8408484818829054, "grad_norm": 0.51953125, "learning_rate": 1.945001527028403e-05, "loss": 0.9810741424560547, "step": 333600 }, { "epoch": 3.8431511669576204, "grad_norm": 0.45703125, "learning_rate": 1.944274370646151e-05, "loss": 0.9708782196044922, "step": 333800 }, { "epoch": 3.8454538520323354, "grad_norm": 1.0, "learning_rate": 1.9435472142638997e-05, "loss": 0.9710533905029297, "step": 334000 }, { "epoch": 3.8477565371070503, "grad_norm": 1.140625, "learning_rate": 1.9428200578816483e-05, "loss": 0.9628467559814453, "step": 334200 }, { "epoch": 3.8500592221817653, "grad_norm": 0.6171875, "learning_rate": 1.9420929014993965e-05, "loss": 1.0163386535644532, "step": 334400 }, { "epoch": 3.8523619072564803, "grad_norm": 0.94140625, "learning_rate": 1.9413657451171448e-05, "loss": 0.9830091857910156, "step": 334600 }, { "epoch": 3.8546645923311953, "grad_norm": 0.7890625, "learning_rate": 1.9406385887348934e-05, "loss": 0.9770928192138671, "step": 334800 }, { "epoch": 3.8569672774059103, "grad_norm": 0.87890625, "learning_rate": 1.9399114323526416e-05, "loss": 0.9688341522216797, "step": 335000 }, { "epoch": 3.8592699624806253, "grad_norm": 0.396484375, "learning_rate": 1.9391842759703902e-05, "loss": 0.977500991821289, "step": 335200 }, { "epoch": 3.86157264755534, "grad_norm": 0.6796875, "learning_rate": 1.9384571195881388e-05, "loss": 0.9860353088378906, "step": 335400 }, { "epoch": 3.863875332630055, "grad_norm": 0.65625, "learning_rate": 1.937729963205887e-05, "loss": 0.9698558807373047, "step": 335600 }, { "epoch": 3.8661780177047698, "grad_norm": 0.546875, "learning_rate": 1.9370028068236353e-05, "loss": 0.974271469116211, "step": 335800 }, { "epoch": 3.8684807027794847, "grad_norm": 0.67578125, "learning_rate": 1.936275650441384e-05, "loss": 0.9913460540771485, "step": 336000 }, { "epoch": 3.8707833878541997, "grad_norm": 0.984375, "learning_rate": 1.9355484940591325e-05, "loss": 0.9814734649658203, "step": 336200 }, { "epoch": 3.8730860729289147, "grad_norm": 0.83984375, "learning_rate": 1.9348213376768808e-05, "loss": 0.9771896362304687, "step": 336400 }, { "epoch": 3.8753887580036297, "grad_norm": 0.46484375, "learning_rate": 1.9340941812946294e-05, "loss": 0.9758899688720704, "step": 336600 }, { "epoch": 3.8776914430783447, "grad_norm": 0.435546875, "learning_rate": 1.933367024912378e-05, "loss": 0.9744023895263672, "step": 336800 }, { "epoch": 3.8799941281530597, "grad_norm": 0.83984375, "learning_rate": 1.932639868530126e-05, "loss": 0.9712601470947265, "step": 337000 }, { "epoch": 3.882296813227774, "grad_norm": 1.0078125, "learning_rate": 1.9319127121478745e-05, "loss": 0.9955208587646485, "step": 337200 }, { "epoch": 3.884599498302489, "grad_norm": 0.5703125, "learning_rate": 1.931185555765623e-05, "loss": 0.9782139587402344, "step": 337400 }, { "epoch": 3.886902183377204, "grad_norm": 0.8671875, "learning_rate": 1.9304583993833713e-05, "loss": 0.9548270416259765, "step": 337600 }, { "epoch": 3.889204868451919, "grad_norm": 0.98046875, "learning_rate": 1.92973124300112e-05, "loss": 0.9846508026123046, "step": 337800 }, { "epoch": 3.891507553526634, "grad_norm": 0.59375, "learning_rate": 1.9290040866188685e-05, "loss": 0.9758512878417969, "step": 338000 }, { "epoch": 3.893810238601349, "grad_norm": 1.1484375, "learning_rate": 1.9282769302366167e-05, "loss": 0.9999530029296875, "step": 338200 }, { "epoch": 3.896112923676064, "grad_norm": 0.578125, "learning_rate": 1.927549773854365e-05, "loss": 0.9721403503417969, "step": 338400 }, { "epoch": 3.898415608750779, "grad_norm": 0.7734375, "learning_rate": 1.9268226174721136e-05, "loss": 0.9728392791748047, "step": 338600 }, { "epoch": 3.900718293825494, "grad_norm": 0.83984375, "learning_rate": 1.9260954610898622e-05, "loss": 0.9802152252197266, "step": 338800 }, { "epoch": 3.9030209789002086, "grad_norm": 0.94921875, "learning_rate": 1.9253683047076104e-05, "loss": 0.9853790283203125, "step": 339000 }, { "epoch": 3.905323663974924, "grad_norm": 0.7890625, "learning_rate": 1.924641148325359e-05, "loss": 0.9751505279541015, "step": 339200 }, { "epoch": 3.9076263490496386, "grad_norm": 0.8671875, "learning_rate": 1.9239139919431076e-05, "loss": 0.9823059844970703, "step": 339400 }, { "epoch": 3.9099290341243536, "grad_norm": 0.6015625, "learning_rate": 1.9231868355608555e-05, "loss": 0.9839841461181641, "step": 339600 }, { "epoch": 3.9122317191990685, "grad_norm": 0.55078125, "learning_rate": 1.922459679178604e-05, "loss": 0.9967166137695312, "step": 339800 }, { "epoch": 3.9145344042737835, "grad_norm": 0.53125, "learning_rate": 1.9217325227963527e-05, "loss": 0.9998323822021484, "step": 340000 }, { "epoch": 3.9168370893484985, "grad_norm": 0.58984375, "learning_rate": 1.921005366414101e-05, "loss": 0.992779541015625, "step": 340200 }, { "epoch": 3.9191397744232135, "grad_norm": 0.78515625, "learning_rate": 1.9202782100318495e-05, "loss": 1.0167972564697265, "step": 340400 }, { "epoch": 3.9214424594979285, "grad_norm": 0.94140625, "learning_rate": 1.919551053649598e-05, "loss": 0.9844973754882812, "step": 340600 }, { "epoch": 3.923745144572643, "grad_norm": 0.62109375, "learning_rate": 1.9188238972673464e-05, "loss": 0.9800909423828125, "step": 340800 }, { "epoch": 3.9260478296473584, "grad_norm": 0.78515625, "learning_rate": 1.9180967408850946e-05, "loss": 0.9858707427978516, "step": 341000 }, { "epoch": 3.928350514722073, "grad_norm": 0.60546875, "learning_rate": 1.9173695845028432e-05, "loss": 0.9715339660644531, "step": 341200 }, { "epoch": 3.930653199796788, "grad_norm": 0.7421875, "learning_rate": 1.9166424281205915e-05, "loss": 0.9722483825683593, "step": 341400 }, { "epoch": 3.932955884871503, "grad_norm": 1.0390625, "learning_rate": 1.91591527173834e-05, "loss": 0.9885195159912109, "step": 341600 }, { "epoch": 3.935258569946218, "grad_norm": 0.7421875, "learning_rate": 1.9151881153560887e-05, "loss": 0.9816614532470703, "step": 341800 }, { "epoch": 3.937561255020933, "grad_norm": 0.6015625, "learning_rate": 1.9144609589738373e-05, "loss": 0.9931729125976563, "step": 342000 }, { "epoch": 3.939863940095648, "grad_norm": 1.3359375, "learning_rate": 1.9137338025915852e-05, "loss": 0.9719671630859374, "step": 342200 }, { "epoch": 3.942166625170363, "grad_norm": 0.69921875, "learning_rate": 1.9130066462093338e-05, "loss": 0.9845899963378906, "step": 342400 }, { "epoch": 3.9444693102450774, "grad_norm": 0.640625, "learning_rate": 1.9122794898270824e-05, "loss": 1.0178986358642579, "step": 342600 }, { "epoch": 3.946771995319793, "grad_norm": 0.90625, "learning_rate": 1.9115523334448306e-05, "loss": 0.9837549591064453, "step": 342800 }, { "epoch": 3.9490746803945074, "grad_norm": 0.76171875, "learning_rate": 1.9108251770625792e-05, "loss": 0.9918838500976562, "step": 343000 }, { "epoch": 3.9513773654692224, "grad_norm": 0.625, "learning_rate": 1.9100980206803278e-05, "loss": 0.9758218383789062, "step": 343200 }, { "epoch": 3.9536800505439373, "grad_norm": 0.494140625, "learning_rate": 1.9093708642980757e-05, "loss": 0.9743316650390625, "step": 343400 }, { "epoch": 3.9559827356186523, "grad_norm": 0.64453125, "learning_rate": 1.9086437079158243e-05, "loss": 0.9659014129638672, "step": 343600 }, { "epoch": 3.9582854206933673, "grad_norm": 0.52734375, "learning_rate": 1.907916551533573e-05, "loss": 0.9813739776611328, "step": 343800 }, { "epoch": 3.9605881057680823, "grad_norm": 0.408203125, "learning_rate": 1.907189395151321e-05, "loss": 0.9784278106689454, "step": 344000 }, { "epoch": 3.9628907908427973, "grad_norm": 0.5703125, "learning_rate": 1.9064622387690697e-05, "loss": 0.9834820556640625, "step": 344200 }, { "epoch": 3.965193475917512, "grad_norm": 0.404296875, "learning_rate": 1.9057350823868183e-05, "loss": 0.9798778533935547, "step": 344400 }, { "epoch": 3.9674961609922272, "grad_norm": 0.7890625, "learning_rate": 1.905007926004567e-05, "loss": 0.9758098602294922, "step": 344600 }, { "epoch": 3.9697988460669418, "grad_norm": 0.9296875, "learning_rate": 1.9042807696223148e-05, "loss": 0.9676461029052734, "step": 344800 }, { "epoch": 3.9721015311416568, "grad_norm": 0.6171875, "learning_rate": 1.9035536132400634e-05, "loss": 0.9825784301757813, "step": 345000 }, { "epoch": 3.9744042162163717, "grad_norm": 0.65234375, "learning_rate": 1.902826456857812e-05, "loss": 0.9833172607421875, "step": 345200 }, { "epoch": 3.9767069012910867, "grad_norm": 1.234375, "learning_rate": 1.9020993004755603e-05, "loss": 0.9863948059082032, "step": 345400 }, { "epoch": 3.9790095863658017, "grad_norm": 0.4375, "learning_rate": 1.901372144093309e-05, "loss": 1.005031509399414, "step": 345600 }, { "epoch": 3.9813122714405167, "grad_norm": 1.03125, "learning_rate": 1.9006449877110574e-05, "loss": 0.9735250091552734, "step": 345800 }, { "epoch": 3.9836149565152317, "grad_norm": 0.515625, "learning_rate": 1.8999178313288054e-05, "loss": 0.9725241851806641, "step": 346000 }, { "epoch": 3.985917641589946, "grad_norm": 0.56640625, "learning_rate": 1.899190674946554e-05, "loss": 0.9731990814208984, "step": 346200 }, { "epoch": 3.9882203266646616, "grad_norm": 0.546875, "learning_rate": 1.8984635185643025e-05, "loss": 0.9702101135253907, "step": 346400 }, { "epoch": 3.990523011739376, "grad_norm": 0.609375, "learning_rate": 1.8977363621820508e-05, "loss": 0.9851368713378906, "step": 346600 }, { "epoch": 3.992825696814091, "grad_norm": 0.482421875, "learning_rate": 1.8970092057997994e-05, "loss": 0.977271728515625, "step": 346800 }, { "epoch": 3.995128381888806, "grad_norm": 0.63671875, "learning_rate": 1.896282049417548e-05, "loss": 0.9866420745849609, "step": 347000 }, { "epoch": 3.997431066963521, "grad_norm": 0.61328125, "learning_rate": 1.895554893035296e-05, "loss": 0.9789151763916015, "step": 347200 }, { "epoch": 3.999733752038236, "grad_norm": 0.40234375, "learning_rate": 1.8948277366530445e-05, "loss": 0.9966899108886719, "step": 347400 }, { "epoch": 4.0, "eval_loss": NaN, "eval_runtime": 431.4871, "eval_samples_per_second": 65.728, "eval_steps_per_second": 32.865, "step": 347424 }, { "epoch": 4.002026362865749, "grad_norm": 0.921875, "learning_rate": 1.894100580270793e-05, "loss": 0.9862317657470703, "step": 347600 }, { "epoch": 4.004329047940464, "grad_norm": 0.87109375, "learning_rate": 1.8933734238885417e-05, "loss": 0.9764509582519532, "step": 347800 }, { "epoch": 4.006631733015179, "grad_norm": 0.85546875, "learning_rate": 1.89264626750629e-05, "loss": 1.006572265625, "step": 348000 }, { "epoch": 4.008934418089894, "grad_norm": 0.7890625, "learning_rate": 1.8919191111240385e-05, "loss": 0.9794659423828125, "step": 348200 }, { "epoch": 4.011237103164609, "grad_norm": 0.59765625, "learning_rate": 1.891191954741787e-05, "loss": 0.9678721618652344, "step": 348400 }, { "epoch": 4.013539788239324, "grad_norm": 0.9921875, "learning_rate": 1.890464798359535e-05, "loss": 0.9642930603027344, "step": 348600 }, { "epoch": 4.015842473314039, "grad_norm": 0.578125, "learning_rate": 1.8897376419772836e-05, "loss": 0.9878228759765625, "step": 348800 }, { "epoch": 4.018145158388753, "grad_norm": 0.67578125, "learning_rate": 1.8890104855950322e-05, "loss": 0.9811653900146484, "step": 349000 }, { "epoch": 4.020447843463469, "grad_norm": 0.80078125, "learning_rate": 1.8882833292127804e-05, "loss": 0.9771403503417969, "step": 349200 }, { "epoch": 4.022750528538183, "grad_norm": 1.015625, "learning_rate": 1.887556172830529e-05, "loss": 1.0004103088378906, "step": 349400 }, { "epoch": 4.025053213612899, "grad_norm": 0.9140625, "learning_rate": 1.8868290164482776e-05, "loss": 1.0042034912109374, "step": 349600 }, { "epoch": 4.027355898687613, "grad_norm": 0.61328125, "learning_rate": 1.8861018600660255e-05, "loss": 0.9859686279296875, "step": 349800 }, { "epoch": 4.029658583762329, "grad_norm": 0.9921875, "learning_rate": 1.885374703683774e-05, "loss": 0.9745539855957032, "step": 350000 }, { "epoch": 4.031961268837043, "grad_norm": 0.86328125, "learning_rate": 1.8846475473015227e-05, "loss": 0.9789989471435547, "step": 350200 }, { "epoch": 4.034263953911759, "grad_norm": 0.66796875, "learning_rate": 1.8839203909192713e-05, "loss": 0.9792119598388672, "step": 350400 }, { "epoch": 4.036566638986473, "grad_norm": 0.77734375, "learning_rate": 1.8831932345370196e-05, "loss": 1.007418441772461, "step": 350600 }, { "epoch": 4.038869324061188, "grad_norm": 0.71484375, "learning_rate": 1.882466078154768e-05, "loss": 0.988331298828125, "step": 350800 }, { "epoch": 4.041172009135903, "grad_norm": 0.8125, "learning_rate": 1.8817389217725168e-05, "loss": 0.9866494750976562, "step": 351000 }, { "epoch": 4.043474694210618, "grad_norm": 0.98046875, "learning_rate": 1.8810117653902647e-05, "loss": 0.9749382781982422, "step": 351200 }, { "epoch": 4.045777379285333, "grad_norm": 0.73046875, "learning_rate": 1.8802846090080133e-05, "loss": 0.969979019165039, "step": 351400 }, { "epoch": 4.048080064360048, "grad_norm": 0.49609375, "learning_rate": 1.879557452625762e-05, "loss": 0.9858515167236328, "step": 351600 }, { "epoch": 4.050382749434763, "grad_norm": 0.51953125, "learning_rate": 1.87883029624351e-05, "loss": 0.9740243530273438, "step": 351800 }, { "epoch": 4.052685434509478, "grad_norm": 0.56640625, "learning_rate": 1.8781031398612587e-05, "loss": 0.9444357299804688, "step": 352000 }, { "epoch": 4.054988119584193, "grad_norm": 0.578125, "learning_rate": 1.8773759834790073e-05, "loss": 0.9807145690917969, "step": 352200 }, { "epoch": 4.057290804658908, "grad_norm": 1.015625, "learning_rate": 1.8766488270967552e-05, "loss": 0.9957177734375, "step": 352400 }, { "epoch": 4.059593489733622, "grad_norm": 0.83984375, "learning_rate": 1.8759216707145038e-05, "loss": 0.9883721160888672, "step": 352600 }, { "epoch": 4.0618961748083375, "grad_norm": 0.46484375, "learning_rate": 1.8751945143322524e-05, "loss": 0.9880260467529297, "step": 352800 }, { "epoch": 4.064198859883052, "grad_norm": 0.70703125, "learning_rate": 1.8744673579500006e-05, "loss": 0.9933139038085937, "step": 353000 }, { "epoch": 4.0665015449577675, "grad_norm": 0.6875, "learning_rate": 1.8737402015677492e-05, "loss": 0.9660495758056641, "step": 353200 }, { "epoch": 4.068804230032482, "grad_norm": 1.234375, "learning_rate": 1.8730130451854978e-05, "loss": 0.991396713256836, "step": 353400 }, { "epoch": 4.0711069151071975, "grad_norm": 1.046875, "learning_rate": 1.872285888803246e-05, "loss": 0.9717893981933594, "step": 353600 }, { "epoch": 4.073409600181912, "grad_norm": 0.73828125, "learning_rate": 1.8715587324209943e-05, "loss": 0.9627035522460937, "step": 353800 }, { "epoch": 4.075712285256627, "grad_norm": 0.51953125, "learning_rate": 1.870831576038743e-05, "loss": 1.0016319274902343, "step": 354000 }, { "epoch": 4.078014970331342, "grad_norm": 0.6171875, "learning_rate": 1.8701044196564915e-05, "loss": 0.9791947937011719, "step": 354200 }, { "epoch": 4.0803176554060565, "grad_norm": 0.486328125, "learning_rate": 1.8693772632742398e-05, "loss": 0.9732559204101563, "step": 354400 }, { "epoch": 4.082620340480772, "grad_norm": 1.0546875, "learning_rate": 1.8686501068919884e-05, "loss": 0.9835048675537109, "step": 354600 }, { "epoch": 4.0849230255554865, "grad_norm": 0.578125, "learning_rate": 1.867922950509737e-05, "loss": 0.9886447143554687, "step": 354800 }, { "epoch": 4.087225710630202, "grad_norm": 0.7265625, "learning_rate": 1.867195794127485e-05, "loss": 0.9782583618164062, "step": 355000 }, { "epoch": 4.089528395704916, "grad_norm": 0.890625, "learning_rate": 1.8664686377452334e-05, "loss": 0.9842738342285157, "step": 355200 }, { "epoch": 4.091831080779632, "grad_norm": 0.8359375, "learning_rate": 1.865741481362982e-05, "loss": 0.980291976928711, "step": 355400 }, { "epoch": 4.094133765854346, "grad_norm": 0.625, "learning_rate": 1.8650143249807303e-05, "loss": 0.978897705078125, "step": 355600 }, { "epoch": 4.096436450929062, "grad_norm": 0.546875, "learning_rate": 1.864287168598479e-05, "loss": 0.9819556427001953, "step": 355800 }, { "epoch": 4.098739136003776, "grad_norm": 0.81640625, "learning_rate": 1.8635600122162275e-05, "loss": 0.9883599853515626, "step": 356000 }, { "epoch": 4.101041821078491, "grad_norm": 0.62890625, "learning_rate": 1.8628328558339757e-05, "loss": 0.9936543273925781, "step": 356200 }, { "epoch": 4.103344506153206, "grad_norm": 0.68359375, "learning_rate": 1.862105699451724e-05, "loss": 0.9793272399902344, "step": 356400 }, { "epoch": 4.105647191227921, "grad_norm": 0.63671875, "learning_rate": 1.8613785430694726e-05, "loss": 0.9574286651611328, "step": 356600 }, { "epoch": 4.107949876302636, "grad_norm": 0.90234375, "learning_rate": 1.860651386687221e-05, "loss": 0.9973934173583985, "step": 356800 }, { "epoch": 4.110252561377351, "grad_norm": 1.2421875, "learning_rate": 1.8599242303049694e-05, "loss": 0.9751262664794922, "step": 357000 }, { "epoch": 4.112555246452066, "grad_norm": 0.4453125, "learning_rate": 1.859197073922718e-05, "loss": 0.9817977142333985, "step": 357200 }, { "epoch": 4.114857931526781, "grad_norm": 0.83203125, "learning_rate": 1.8584699175404663e-05, "loss": 0.9779124450683594, "step": 357400 }, { "epoch": 4.117160616601496, "grad_norm": 1.2109375, "learning_rate": 1.8577427611582145e-05, "loss": 0.9914723205566406, "step": 357600 }, { "epoch": 4.119463301676211, "grad_norm": 0.9296875, "learning_rate": 1.857015604775963e-05, "loss": 0.9791415405273437, "step": 357800 }, { "epoch": 4.121765986750925, "grad_norm": 0.72265625, "learning_rate": 1.8562884483937117e-05, "loss": 0.9917333984375, "step": 358000 }, { "epoch": 4.124068671825641, "grad_norm": 0.5703125, "learning_rate": 1.85556129201146e-05, "loss": 0.978380126953125, "step": 358200 }, { "epoch": 4.126371356900355, "grad_norm": 0.404296875, "learning_rate": 1.8548341356292085e-05, "loss": 0.9702176666259765, "step": 358400 }, { "epoch": 4.128674041975071, "grad_norm": 1.1640625, "learning_rate": 1.854106979246957e-05, "loss": 1.0004293060302734, "step": 358600 }, { "epoch": 4.130976727049785, "grad_norm": 0.76171875, "learning_rate": 1.853379822864705e-05, "loss": 0.9715544128417969, "step": 358800 }, { "epoch": 4.133279412124501, "grad_norm": 0.546875, "learning_rate": 1.8526526664824536e-05, "loss": 0.9909072875976562, "step": 359000 }, { "epoch": 4.135582097199215, "grad_norm": 0.625, "learning_rate": 1.8519255101002022e-05, "loss": 0.9791348266601563, "step": 359200 }, { "epoch": 4.137884782273931, "grad_norm": 0.8671875, "learning_rate": 1.8511983537179508e-05, "loss": 1.0011709594726563, "step": 359400 }, { "epoch": 4.140187467348645, "grad_norm": 0.80078125, "learning_rate": 1.850471197335699e-05, "loss": 0.994935302734375, "step": 359600 }, { "epoch": 4.14249015242336, "grad_norm": 0.734375, "learning_rate": 1.8497440409534477e-05, "loss": 0.9711431121826172, "step": 359800 }, { "epoch": 4.144792837498075, "grad_norm": 0.70703125, "learning_rate": 1.849016884571196e-05, "loss": 0.9803479766845703, "step": 360000 }, { "epoch": 4.14709552257279, "grad_norm": 0.96484375, "learning_rate": 1.848289728188944e-05, "loss": 0.9712246704101563, "step": 360200 }, { "epoch": 4.149398207647505, "grad_norm": 0.61328125, "learning_rate": 1.8475625718066928e-05, "loss": 0.9849492645263672, "step": 360400 }, { "epoch": 4.15170089272222, "grad_norm": 0.640625, "learning_rate": 1.8468354154244413e-05, "loss": 1.0022724151611329, "step": 360600 }, { "epoch": 4.154003577796935, "grad_norm": 0.57421875, "learning_rate": 1.8461082590421896e-05, "loss": 0.9713355255126953, "step": 360800 }, { "epoch": 4.15630626287165, "grad_norm": 0.6953125, "learning_rate": 1.8453811026599382e-05, "loss": 1.0081776428222655, "step": 361000 }, { "epoch": 4.158608947946365, "grad_norm": 0.61328125, "learning_rate": 1.8446539462776868e-05, "loss": 0.9850017547607421, "step": 361200 }, { "epoch": 4.16091163302108, "grad_norm": 0.73046875, "learning_rate": 1.8439267898954347e-05, "loss": 0.9687409210205078, "step": 361400 }, { "epoch": 4.163214318095795, "grad_norm": 0.7578125, "learning_rate": 1.8431996335131833e-05, "loss": 0.9744286346435547, "step": 361600 }, { "epoch": 4.1655170031705095, "grad_norm": 0.5390625, "learning_rate": 1.842472477130932e-05, "loss": 0.9651099395751953, "step": 361800 }, { "epoch": 4.167819688245224, "grad_norm": 0.79296875, "learning_rate": 1.84174532074868e-05, "loss": 0.9873933410644531, "step": 362000 }, { "epoch": 4.1701223733199395, "grad_norm": 0.57421875, "learning_rate": 1.8410181643664287e-05, "loss": 0.9850807952880859, "step": 362200 }, { "epoch": 4.172425058394654, "grad_norm": 0.498046875, "learning_rate": 1.8402910079841773e-05, "loss": 0.9752694702148438, "step": 362400 }, { "epoch": 4.1747277434693695, "grad_norm": 0.466796875, "learning_rate": 1.8395638516019256e-05, "loss": 0.9639392852783203, "step": 362600 }, { "epoch": 4.177030428544084, "grad_norm": 0.73046875, "learning_rate": 1.8388366952196738e-05, "loss": 0.9980973052978516, "step": 362800 }, { "epoch": 4.1793331136187994, "grad_norm": 0.80078125, "learning_rate": 1.8381095388374224e-05, "loss": 0.9663079833984375, "step": 363000 }, { "epoch": 4.181635798693514, "grad_norm": 1.015625, "learning_rate": 1.837382382455171e-05, "loss": 0.9786151123046875, "step": 363200 }, { "epoch": 4.183938483768229, "grad_norm": 1.375, "learning_rate": 1.8366552260729193e-05, "loss": 0.9864177703857422, "step": 363400 }, { "epoch": 4.186241168842944, "grad_norm": 0.51171875, "learning_rate": 1.835928069690668e-05, "loss": 0.9760264587402344, "step": 363600 }, { "epoch": 4.1885438539176585, "grad_norm": 0.6328125, "learning_rate": 1.835200913308416e-05, "loss": 0.9764144134521484, "step": 363800 }, { "epoch": 4.190846538992374, "grad_norm": 1.2578125, "learning_rate": 1.8344737569261644e-05, "loss": 0.9865864562988281, "step": 364000 }, { "epoch": 4.1931492240670885, "grad_norm": 0.6484375, "learning_rate": 1.833746600543913e-05, "loss": 0.962984848022461, "step": 364200 }, { "epoch": 4.195451909141804, "grad_norm": 0.625, "learning_rate": 1.8330194441616615e-05, "loss": 0.9840062713623047, "step": 364400 }, { "epoch": 4.197754594216518, "grad_norm": 0.70703125, "learning_rate": 1.8322922877794098e-05, "loss": 0.9727967834472656, "step": 364600 }, { "epoch": 4.200057279291234, "grad_norm": 0.44140625, "learning_rate": 1.8315651313971584e-05, "loss": 0.9823301696777343, "step": 364800 }, { "epoch": 4.202359964365948, "grad_norm": 0.72265625, "learning_rate": 1.830837975014907e-05, "loss": 0.9683138275146485, "step": 365000 }, { "epoch": 4.204662649440664, "grad_norm": 0.470703125, "learning_rate": 1.8301108186326552e-05, "loss": 0.9668745422363281, "step": 365200 }, { "epoch": 4.206965334515378, "grad_norm": 0.55859375, "learning_rate": 1.8293836622504035e-05, "loss": 0.978956069946289, "step": 365400 }, { "epoch": 4.209268019590093, "grad_norm": 0.8359375, "learning_rate": 1.828656505868152e-05, "loss": 1.00272216796875, "step": 365600 }, { "epoch": 4.211570704664808, "grad_norm": 0.58203125, "learning_rate": 1.8279293494859007e-05, "loss": 0.9836425018310547, "step": 365800 }, { "epoch": 4.213873389739523, "grad_norm": 0.52734375, "learning_rate": 1.827202193103649e-05, "loss": 0.9879397583007813, "step": 366000 }, { "epoch": 4.216176074814238, "grad_norm": 0.609375, "learning_rate": 1.8264750367213975e-05, "loss": 0.9587268829345703, "step": 366200 }, { "epoch": 4.218478759888953, "grad_norm": 0.79296875, "learning_rate": 1.8257478803391458e-05, "loss": 0.9883473205566407, "step": 366400 }, { "epoch": 4.220781444963668, "grad_norm": 0.6171875, "learning_rate": 1.825020723956894e-05, "loss": 0.9879270172119141, "step": 366600 }, { "epoch": 4.223084130038383, "grad_norm": 0.64453125, "learning_rate": 1.8242935675746426e-05, "loss": 0.9905947875976563, "step": 366800 }, { "epoch": 4.225386815113098, "grad_norm": 0.73828125, "learning_rate": 1.8235664111923912e-05, "loss": 0.9815054321289063, "step": 367000 }, { "epoch": 4.227689500187813, "grad_norm": 0.703125, "learning_rate": 1.8228392548101394e-05, "loss": 0.9851663208007813, "step": 367200 }, { "epoch": 4.229992185262527, "grad_norm": 0.58203125, "learning_rate": 1.822112098427888e-05, "loss": 0.9802882385253906, "step": 367400 }, { "epoch": 4.232294870337243, "grad_norm": 1.0390625, "learning_rate": 1.8213849420456363e-05, "loss": 0.9949236297607422, "step": 367600 }, { "epoch": 4.234597555411957, "grad_norm": 0.671875, "learning_rate": 1.8206577856633845e-05, "loss": 0.9930872344970703, "step": 367800 }, { "epoch": 4.236900240486673, "grad_norm": 0.640625, "learning_rate": 1.819930629281133e-05, "loss": 0.9888762664794922, "step": 368000 }, { "epoch": 4.239202925561387, "grad_norm": 0.7421875, "learning_rate": 1.8192034728988817e-05, "loss": 0.9819789886474609, "step": 368200 }, { "epoch": 4.241505610636103, "grad_norm": 0.54296875, "learning_rate": 1.8184763165166303e-05, "loss": 0.99475341796875, "step": 368400 }, { "epoch": 4.243808295710817, "grad_norm": 0.625, "learning_rate": 1.8177491601343786e-05, "loss": 0.9711346435546875, "step": 368600 }, { "epoch": 4.246110980785533, "grad_norm": 0.44921875, "learning_rate": 1.817022003752127e-05, "loss": 0.9897885894775391, "step": 368800 }, { "epoch": 4.248413665860247, "grad_norm": 0.640625, "learning_rate": 1.8162948473698754e-05, "loss": 0.9859911346435547, "step": 369000 }, { "epoch": 4.250716350934962, "grad_norm": 0.5078125, "learning_rate": 1.8155676909876237e-05, "loss": 0.9784740447998047, "step": 369200 }, { "epoch": 4.253019036009677, "grad_norm": 1.3203125, "learning_rate": 1.8148405346053723e-05, "loss": 1.0029774475097657, "step": 369400 }, { "epoch": 4.255321721084392, "grad_norm": 0.57421875, "learning_rate": 1.814113378223121e-05, "loss": 0.9826509857177734, "step": 369600 }, { "epoch": 4.257624406159107, "grad_norm": 0.75390625, "learning_rate": 1.813386221840869e-05, "loss": 0.9854049682617188, "step": 369800 }, { "epoch": 4.259927091233822, "grad_norm": 0.76953125, "learning_rate": 1.8126590654586177e-05, "loss": 0.9904918670654297, "step": 370000 }, { "epoch": 4.262229776308537, "grad_norm": 0.87890625, "learning_rate": 1.811931909076366e-05, "loss": 0.978302001953125, "step": 370200 }, { "epoch": 4.264532461383252, "grad_norm": 0.515625, "learning_rate": 1.8112047526941142e-05, "loss": 0.9758035278320313, "step": 370400 }, { "epoch": 4.266835146457967, "grad_norm": 0.609375, "learning_rate": 1.8104775963118628e-05, "loss": 0.9813452911376953, "step": 370600 }, { "epoch": 4.269137831532682, "grad_norm": 0.953125, "learning_rate": 1.8097504399296114e-05, "loss": 0.9689815521240235, "step": 370800 }, { "epoch": 4.271440516607396, "grad_norm": 0.55859375, "learning_rate": 1.80902328354736e-05, "loss": 0.985603256225586, "step": 371000 }, { "epoch": 4.2737432016821115, "grad_norm": 0.7109375, "learning_rate": 1.8082961271651082e-05, "loss": 0.9839646148681641, "step": 371200 }, { "epoch": 4.276045886756826, "grad_norm": 0.58203125, "learning_rate": 1.8075689707828568e-05, "loss": 0.9936179351806641, "step": 371400 }, { "epoch": 4.2783485718315415, "grad_norm": 0.65625, "learning_rate": 1.806841814400605e-05, "loss": 0.981746826171875, "step": 371600 }, { "epoch": 4.280651256906256, "grad_norm": 0.61328125, "learning_rate": 1.8061146580183533e-05, "loss": 0.954793701171875, "step": 371800 }, { "epoch": 4.2829539419809715, "grad_norm": 0.6484375, "learning_rate": 1.805387501636102e-05, "loss": 0.9726139068603515, "step": 372000 }, { "epoch": 4.285256627055686, "grad_norm": 0.60546875, "learning_rate": 1.8046603452538505e-05, "loss": 0.985401382446289, "step": 372200 }, { "epoch": 4.287559312130401, "grad_norm": 0.5546875, "learning_rate": 1.8039331888715987e-05, "loss": 0.9654906463623046, "step": 372400 }, { "epoch": 4.289861997205116, "grad_norm": 1.6875, "learning_rate": 1.8032060324893473e-05, "loss": 0.9556643676757812, "step": 372600 }, { "epoch": 4.2921646822798305, "grad_norm": 0.46875, "learning_rate": 1.8024788761070956e-05, "loss": 0.9781275939941406, "step": 372800 }, { "epoch": 4.294467367354546, "grad_norm": 0.5703125, "learning_rate": 1.801751719724844e-05, "loss": 0.9931547546386719, "step": 373000 }, { "epoch": 4.2967700524292605, "grad_norm": 0.56640625, "learning_rate": 1.8010245633425924e-05, "loss": 0.9784978485107422, "step": 373200 }, { "epoch": 4.299072737503976, "grad_norm": 0.65234375, "learning_rate": 1.800297406960341e-05, "loss": 0.9716792297363281, "step": 373400 }, { "epoch": 4.30137542257869, "grad_norm": 0.83984375, "learning_rate": 1.7995702505780893e-05, "loss": 0.976788330078125, "step": 373600 }, { "epoch": 4.303678107653406, "grad_norm": 1.375, "learning_rate": 1.798843094195838e-05, "loss": 0.9814914703369141, "step": 373800 }, { "epoch": 4.30598079272812, "grad_norm": 0.671875, "learning_rate": 1.798115937813586e-05, "loss": 0.9726478576660156, "step": 374000 }, { "epoch": 4.308283477802836, "grad_norm": 0.69921875, "learning_rate": 1.7973887814313347e-05, "loss": 0.996259765625, "step": 374200 }, { "epoch": 4.31058616287755, "grad_norm": 0.53125, "learning_rate": 1.796661625049083e-05, "loss": 0.9984632873535156, "step": 374400 }, { "epoch": 4.312888847952266, "grad_norm": 1.1171875, "learning_rate": 1.7959344686668316e-05, "loss": 0.988074722290039, "step": 374600 }, { "epoch": 4.31519153302698, "grad_norm": 1.1796875, "learning_rate": 1.79520731228458e-05, "loss": 0.9838126373291015, "step": 374800 }, { "epoch": 4.317494218101695, "grad_norm": 1.5859375, "learning_rate": 1.7944801559023284e-05, "loss": 0.9583352661132812, "step": 375000 }, { "epoch": 4.31979690317641, "grad_norm": 0.703125, "learning_rate": 1.793752999520077e-05, "loss": 0.988289794921875, "step": 375200 }, { "epoch": 4.322099588251125, "grad_norm": 0.95703125, "learning_rate": 1.7930258431378252e-05, "loss": 0.9876296234130859, "step": 375400 }, { "epoch": 4.32440227332584, "grad_norm": 0.953125, "learning_rate": 1.7922986867555735e-05, "loss": 0.9777294921875, "step": 375600 }, { "epoch": 4.326704958400555, "grad_norm": 0.53125, "learning_rate": 1.791571530373322e-05, "loss": 0.9797138977050781, "step": 375800 }, { "epoch": 4.32900764347527, "grad_norm": 0.55859375, "learning_rate": 1.7908443739910707e-05, "loss": 0.9727606964111328, "step": 376000 }, { "epoch": 4.331310328549985, "grad_norm": 0.6328125, "learning_rate": 1.790117217608819e-05, "loss": 0.9707086944580078, "step": 376200 }, { "epoch": 4.333613013624699, "grad_norm": 0.57421875, "learning_rate": 1.7893900612265675e-05, "loss": 0.9848200225830078, "step": 376400 }, { "epoch": 4.335915698699415, "grad_norm": 0.63671875, "learning_rate": 1.7886629048443158e-05, "loss": 0.9899727630615235, "step": 376600 }, { "epoch": 4.338218383774129, "grad_norm": 0.58984375, "learning_rate": 1.787935748462064e-05, "loss": 1.0073524475097657, "step": 376800 }, { "epoch": 4.340521068848845, "grad_norm": 0.72265625, "learning_rate": 1.7872085920798126e-05, "loss": 0.9903134155273438, "step": 377000 }, { "epoch": 4.342823753923559, "grad_norm": 0.62890625, "learning_rate": 1.7864814356975612e-05, "loss": 0.9808146667480468, "step": 377200 }, { "epoch": 4.345126438998275, "grad_norm": 0.62109375, "learning_rate": 1.7857542793153098e-05, "loss": 0.989017105102539, "step": 377400 }, { "epoch": 4.347429124072989, "grad_norm": 0.70703125, "learning_rate": 1.785027122933058e-05, "loss": 0.95684326171875, "step": 377600 }, { "epoch": 4.349731809147705, "grad_norm": 0.76953125, "learning_rate": 1.7842999665508067e-05, "loss": 0.9856446075439453, "step": 377800 }, { "epoch": 4.352034494222419, "grad_norm": 0.421875, "learning_rate": 1.783572810168555e-05, "loss": 0.9768900299072265, "step": 378000 }, { "epoch": 4.354337179297135, "grad_norm": 0.8828125, "learning_rate": 1.782845653786303e-05, "loss": 0.9693342590332031, "step": 378200 }, { "epoch": 4.356639864371849, "grad_norm": 0.890625, "learning_rate": 1.7821184974040517e-05, "loss": 0.9808509826660157, "step": 378400 }, { "epoch": 4.358942549446564, "grad_norm": 0.578125, "learning_rate": 1.7813913410218003e-05, "loss": 1.0005860137939453, "step": 378600 }, { "epoch": 4.361245234521279, "grad_norm": 0.56640625, "learning_rate": 1.7806641846395486e-05, "loss": 1.0117581176757813, "step": 378800 }, { "epoch": 4.363547919595994, "grad_norm": 0.71875, "learning_rate": 1.7799370282572972e-05, "loss": 0.9801927185058594, "step": 379000 }, { "epoch": 4.365850604670709, "grad_norm": 0.5, "learning_rate": 1.7792098718750454e-05, "loss": 0.9840756225585937, "step": 379200 }, { "epoch": 4.368153289745424, "grad_norm": 0.8203125, "learning_rate": 1.7784827154927937e-05, "loss": 0.9926817321777344, "step": 379400 }, { "epoch": 4.370455974820139, "grad_norm": 0.9765625, "learning_rate": 1.7777555591105423e-05, "loss": 0.9944758605957031, "step": 379600 }, { "epoch": 4.372758659894854, "grad_norm": 0.9609375, "learning_rate": 1.777028402728291e-05, "loss": 0.9793479919433594, "step": 379800 }, { "epoch": 4.375061344969568, "grad_norm": 0.62890625, "learning_rate": 1.7763012463460395e-05, "loss": 0.9661212921142578, "step": 380000 }, { "epoch": 4.3773640300442835, "grad_norm": 0.52734375, "learning_rate": 1.7755740899637877e-05, "loss": 0.9963236999511719, "step": 380200 }, { "epoch": 4.379666715118998, "grad_norm": 0.494140625, "learning_rate": 1.774846933581536e-05, "loss": 0.9838841247558594, "step": 380400 }, { "epoch": 4.3819694001937135, "grad_norm": 0.765625, "learning_rate": 1.7741197771992846e-05, "loss": 0.9869212341308594, "step": 380600 }, { "epoch": 4.384272085268428, "grad_norm": 0.56640625, "learning_rate": 1.7733926208170328e-05, "loss": 0.9717589569091797, "step": 380800 }, { "epoch": 4.3865747703431435, "grad_norm": 0.6796875, "learning_rate": 1.7726654644347814e-05, "loss": 0.9582798767089844, "step": 381000 }, { "epoch": 4.388877455417858, "grad_norm": 0.498046875, "learning_rate": 1.77193830805253e-05, "loss": 0.9778752899169922, "step": 381200 }, { "epoch": 4.391180140492573, "grad_norm": 0.55859375, "learning_rate": 1.7712111516702782e-05, "loss": 1.0042454528808593, "step": 381400 }, { "epoch": 4.393482825567288, "grad_norm": 0.6796875, "learning_rate": 1.770483995288027e-05, "loss": 0.9691288757324219, "step": 381600 }, { "epoch": 4.395785510642003, "grad_norm": 1.09375, "learning_rate": 1.769756838905775e-05, "loss": 0.9935425567626953, "step": 381800 }, { "epoch": 4.398088195716718, "grad_norm": 0.765625, "learning_rate": 1.7690296825235233e-05, "loss": 0.9775373840332031, "step": 382000 }, { "epoch": 4.4003908807914325, "grad_norm": 0.5625, "learning_rate": 1.768302526141272e-05, "loss": 0.9748054504394531, "step": 382200 }, { "epoch": 4.402693565866148, "grad_norm": 0.62890625, "learning_rate": 1.7675753697590205e-05, "loss": 0.9840547943115234, "step": 382400 }, { "epoch": 4.4049962509408624, "grad_norm": 0.7890625, "learning_rate": 1.7668482133767688e-05, "loss": 0.9826657867431641, "step": 382600 }, { "epoch": 4.407298936015578, "grad_norm": 0.609375, "learning_rate": 1.7661210569945174e-05, "loss": 0.9580550384521485, "step": 382800 }, { "epoch": 4.409601621090292, "grad_norm": 0.578125, "learning_rate": 1.7653939006122656e-05, "loss": 0.963132553100586, "step": 383000 }, { "epoch": 4.411904306165008, "grad_norm": 0.78515625, "learning_rate": 1.7646667442300142e-05, "loss": 0.9853313446044922, "step": 383200 }, { "epoch": 4.414206991239722, "grad_norm": 0.72265625, "learning_rate": 1.7639395878477625e-05, "loss": 0.9874549865722656, "step": 383400 }, { "epoch": 4.416509676314438, "grad_norm": 0.498046875, "learning_rate": 1.763212431465511e-05, "loss": 0.9777555847167969, "step": 383600 }, { "epoch": 4.418812361389152, "grad_norm": 0.6328125, "learning_rate": 1.7624852750832596e-05, "loss": 0.974601058959961, "step": 383800 }, { "epoch": 4.421115046463867, "grad_norm": 0.50390625, "learning_rate": 1.761758118701008e-05, "loss": 0.9725660705566406, "step": 384000 }, { "epoch": 4.423417731538582, "grad_norm": 0.58203125, "learning_rate": 1.761030962318756e-05, "loss": 0.9747721862792968, "step": 384200 }, { "epoch": 4.425720416613297, "grad_norm": 0.94140625, "learning_rate": 1.7603038059365047e-05, "loss": 0.98368896484375, "step": 384400 }, { "epoch": 4.428023101688012, "grad_norm": 0.56640625, "learning_rate": 1.759576649554253e-05, "loss": 0.9807275390625, "step": 384600 }, { "epoch": 4.430325786762727, "grad_norm": 0.6484375, "learning_rate": 1.7588494931720016e-05, "loss": 0.9803495788574219, "step": 384800 }, { "epoch": 4.432628471837442, "grad_norm": 0.734375, "learning_rate": 1.7581223367897502e-05, "loss": 0.9786897277832032, "step": 385000 }, { "epoch": 4.434931156912157, "grad_norm": 0.498046875, "learning_rate": 1.7573951804074984e-05, "loss": 1.00064453125, "step": 385200 }, { "epoch": 4.437233841986872, "grad_norm": 0.72265625, "learning_rate": 1.756668024025247e-05, "loss": 0.9689328002929688, "step": 385400 }, { "epoch": 4.439536527061587, "grad_norm": 0.62109375, "learning_rate": 1.7559408676429953e-05, "loss": 0.9944960021972656, "step": 385600 }, { "epoch": 4.441839212136301, "grad_norm": 0.7109375, "learning_rate": 1.755213711260744e-05, "loss": 0.9811604309082032, "step": 385800 }, { "epoch": 4.444141897211017, "grad_norm": 0.703125, "learning_rate": 1.754486554878492e-05, "loss": 0.9793187713623047, "step": 386000 }, { "epoch": 4.446444582285731, "grad_norm": 0.890625, "learning_rate": 1.7537593984962407e-05, "loss": 1.0037923431396485, "step": 386200 }, { "epoch": 4.448747267360447, "grad_norm": 1.1015625, "learning_rate": 1.7530322421139893e-05, "loss": 0.9684130096435547, "step": 386400 }, { "epoch": 4.451049952435161, "grad_norm": 1.140625, "learning_rate": 1.7523050857317376e-05, "loss": 0.9824868774414063, "step": 386600 }, { "epoch": 4.453352637509877, "grad_norm": 0.46875, "learning_rate": 1.7515779293494858e-05, "loss": 0.9914022827148438, "step": 386800 }, { "epoch": 4.455655322584591, "grad_norm": 0.89453125, "learning_rate": 1.7508507729672344e-05, "loss": 0.9939438629150391, "step": 387000 }, { "epoch": 4.457958007659307, "grad_norm": 0.72265625, "learning_rate": 1.7501236165849827e-05, "loss": 0.978121109008789, "step": 387200 }, { "epoch": 4.460260692734021, "grad_norm": 1.828125, "learning_rate": 1.7493964602027312e-05, "loss": 1.0017222595214843, "step": 387400 }, { "epoch": 4.462563377808736, "grad_norm": 0.58984375, "learning_rate": 1.74866930382048e-05, "loss": 1.0084938049316405, "step": 387600 }, { "epoch": 4.464866062883451, "grad_norm": 0.73828125, "learning_rate": 1.747942147438228e-05, "loss": 0.9803755187988281, "step": 387800 }, { "epoch": 4.467168747958166, "grad_norm": 0.66015625, "learning_rate": 1.7472149910559767e-05, "loss": 0.9992539978027344, "step": 388000 }, { "epoch": 4.469471433032881, "grad_norm": 0.48828125, "learning_rate": 1.746487834673725e-05, "loss": 0.9823341369628906, "step": 388200 }, { "epoch": 4.471774118107596, "grad_norm": 0.74609375, "learning_rate": 1.7457606782914732e-05, "loss": 0.9724301147460938, "step": 388400 }, { "epoch": 4.474076803182311, "grad_norm": 0.5234375, "learning_rate": 1.7450335219092218e-05, "loss": 0.98064697265625, "step": 388600 }, { "epoch": 4.476379488257026, "grad_norm": 0.6015625, "learning_rate": 1.7443063655269704e-05, "loss": 0.9858995056152344, "step": 388800 }, { "epoch": 4.478682173331741, "grad_norm": 1.109375, "learning_rate": 1.743579209144719e-05, "loss": 0.9684735870361328, "step": 389000 }, { "epoch": 4.4809848584064556, "grad_norm": 0.9140625, "learning_rate": 1.7428520527624672e-05, "loss": 0.982616195678711, "step": 389200 }, { "epoch": 4.48328754348117, "grad_norm": 0.65625, "learning_rate": 1.7421248963802155e-05, "loss": 0.9835112762451171, "step": 389400 }, { "epoch": 4.4855902285558855, "grad_norm": 0.74609375, "learning_rate": 1.741397739997964e-05, "loss": 0.9883460998535156, "step": 389600 }, { "epoch": 4.4878929136306, "grad_norm": 0.71875, "learning_rate": 1.7406705836157123e-05, "loss": 0.9911152648925782, "step": 389800 }, { "epoch": 4.4901955987053155, "grad_norm": 0.9140625, "learning_rate": 1.739943427233461e-05, "loss": 0.9605591583251953, "step": 390000 }, { "epoch": 4.49249828378003, "grad_norm": 0.482421875, "learning_rate": 1.7392162708512095e-05, "loss": 0.9712622833251953, "step": 390200 }, { "epoch": 4.4948009688547454, "grad_norm": 0.486328125, "learning_rate": 1.7384891144689577e-05, "loss": 0.9833880615234375, "step": 390400 }, { "epoch": 4.49710365392946, "grad_norm": 0.61328125, "learning_rate": 1.737761958086706e-05, "loss": 0.9929757690429688, "step": 390600 }, { "epoch": 4.499406339004175, "grad_norm": 0.76953125, "learning_rate": 1.7370348017044546e-05, "loss": 0.9671168518066406, "step": 390800 }, { "epoch": 4.50170902407889, "grad_norm": 0.63671875, "learning_rate": 1.736307645322203e-05, "loss": 0.9829707336425781, "step": 391000 }, { "epoch": 4.504011709153605, "grad_norm": 0.7109375, "learning_rate": 1.7355804889399514e-05, "loss": 0.9815752410888672, "step": 391200 }, { "epoch": 4.50631439422832, "grad_norm": 0.60546875, "learning_rate": 1.7348533325577e-05, "loss": 0.9918634796142578, "step": 391400 }, { "epoch": 4.5086170793030345, "grad_norm": 0.734375, "learning_rate": 1.7341261761754483e-05, "loss": 0.993114013671875, "step": 391600 }, { "epoch": 4.51091976437775, "grad_norm": 0.79296875, "learning_rate": 1.733399019793197e-05, "loss": 0.9865582275390625, "step": 391800 }, { "epoch": 4.513222449452464, "grad_norm": 0.76953125, "learning_rate": 1.732671863410945e-05, "loss": 0.9887853240966797, "step": 392000 }, { "epoch": 4.51552513452718, "grad_norm": 1.3984375, "learning_rate": 1.7319447070286937e-05, "loss": 0.987093734741211, "step": 392200 }, { "epoch": 4.517827819601894, "grad_norm": 0.578125, "learning_rate": 1.731217550646442e-05, "loss": 0.9806004333496093, "step": 392400 }, { "epoch": 4.52013050467661, "grad_norm": 0.8984375, "learning_rate": 1.7304903942641906e-05, "loss": 0.9670136260986328, "step": 392600 }, { "epoch": 4.522433189751324, "grad_norm": 0.6484375, "learning_rate": 1.729763237881939e-05, "loss": 0.9552702331542968, "step": 392800 }, { "epoch": 4.524735874826039, "grad_norm": 0.90625, "learning_rate": 1.7290360814996874e-05, "loss": 0.9844831085205078, "step": 393000 }, { "epoch": 4.527038559900754, "grad_norm": 0.58203125, "learning_rate": 1.7283089251174356e-05, "loss": 0.9598838806152343, "step": 393200 }, { "epoch": 4.529341244975469, "grad_norm": 0.83203125, "learning_rate": 1.7275817687351842e-05, "loss": 0.9726866912841797, "step": 393400 }, { "epoch": 4.531643930050184, "grad_norm": 0.71484375, "learning_rate": 1.7268546123529325e-05, "loss": 0.9710126495361329, "step": 393600 }, { "epoch": 4.533946615124899, "grad_norm": 1.0390625, "learning_rate": 1.726127455970681e-05, "loss": 0.9930452728271484, "step": 393800 }, { "epoch": 4.536249300199614, "grad_norm": 0.71484375, "learning_rate": 1.7254002995884297e-05, "loss": 0.9848808288574219, "step": 394000 }, { "epoch": 4.538551985274329, "grad_norm": 0.8203125, "learning_rate": 1.724673143206178e-05, "loss": 0.9978121185302734, "step": 394200 }, { "epoch": 4.540854670349044, "grad_norm": 0.56640625, "learning_rate": 1.7239459868239262e-05, "loss": 0.9887928009033203, "step": 394400 }, { "epoch": 4.543157355423759, "grad_norm": 0.5, "learning_rate": 1.7232188304416748e-05, "loss": 0.9775355529785156, "step": 394600 }, { "epoch": 4.545460040498474, "grad_norm": 0.8046875, "learning_rate": 1.7224916740594234e-05, "loss": 0.9925399017333985, "step": 394800 }, { "epoch": 4.547762725573189, "grad_norm": 0.5625, "learning_rate": 1.7217645176771716e-05, "loss": 0.9753104400634766, "step": 395000 }, { "epoch": 4.550065410647903, "grad_norm": 0.68359375, "learning_rate": 1.7210373612949202e-05, "loss": 0.9818225860595703, "step": 395200 }, { "epoch": 4.552368095722619, "grad_norm": 0.5625, "learning_rate": 1.7203102049126688e-05, "loss": 0.9720571899414062, "step": 395400 }, { "epoch": 4.554670780797333, "grad_norm": 0.90625, "learning_rate": 1.719583048530417e-05, "loss": 0.9696012115478516, "step": 395600 }, { "epoch": 4.556973465872049, "grad_norm": 0.6328125, "learning_rate": 1.7188558921481653e-05, "loss": 0.9840654754638671, "step": 395800 }, { "epoch": 4.559276150946763, "grad_norm": 1.0, "learning_rate": 1.718128735765914e-05, "loss": 0.9878695678710937, "step": 396000 }, { "epoch": 4.561578836021479, "grad_norm": 0.44140625, "learning_rate": 1.717401579383662e-05, "loss": 0.9655953216552734, "step": 396200 }, { "epoch": 4.563881521096193, "grad_norm": 0.84375, "learning_rate": 1.7166744230014107e-05, "loss": 0.9800299835205079, "step": 396400 }, { "epoch": 4.566184206170908, "grad_norm": 0.62890625, "learning_rate": 1.7159472666191593e-05, "loss": 0.971158447265625, "step": 396600 }, { "epoch": 4.568486891245623, "grad_norm": 0.9296875, "learning_rate": 1.7152201102369076e-05, "loss": 0.9807333374023437, "step": 396800 }, { "epoch": 4.570789576320338, "grad_norm": 0.57421875, "learning_rate": 1.714492953854656e-05, "loss": 0.9847396087646484, "step": 397000 }, { "epoch": 4.573092261395053, "grad_norm": 0.54296875, "learning_rate": 1.7137657974724044e-05, "loss": 0.9942626190185547, "step": 397200 }, { "epoch": 4.575394946469768, "grad_norm": 0.83203125, "learning_rate": 1.7130386410901527e-05, "loss": 0.9864826965332031, "step": 397400 }, { "epoch": 4.577697631544483, "grad_norm": 0.58203125, "learning_rate": 1.7123114847079013e-05, "loss": 0.9885680389404297, "step": 397600 }, { "epoch": 4.580000316619198, "grad_norm": 0.5, "learning_rate": 1.71158432832565e-05, "loss": 1.004285888671875, "step": 397800 }, { "epoch": 4.582303001693913, "grad_norm": 0.97265625, "learning_rate": 1.7108571719433985e-05, "loss": 0.9720408630371093, "step": 398000 }, { "epoch": 4.584605686768628, "grad_norm": 0.57421875, "learning_rate": 1.7101300155611467e-05, "loss": 0.982972412109375, "step": 398200 }, { "epoch": 4.586908371843343, "grad_norm": 1.4609375, "learning_rate": 1.709402859178895e-05, "loss": 0.9912247467041015, "step": 398400 }, { "epoch": 4.5892110569180575, "grad_norm": 1.328125, "learning_rate": 1.7086757027966435e-05, "loss": 0.9738587188720703, "step": 398600 }, { "epoch": 4.591513741992772, "grad_norm": 0.83984375, "learning_rate": 1.7079485464143918e-05, "loss": 0.9671392059326172, "step": 398800 }, { "epoch": 4.5938164270674875, "grad_norm": 0.68359375, "learning_rate": 1.7072213900321404e-05, "loss": 0.9823818206787109, "step": 399000 }, { "epoch": 4.596119112142202, "grad_norm": 0.71875, "learning_rate": 1.706494233649889e-05, "loss": 0.9794180297851562, "step": 399200 }, { "epoch": 4.5984217972169175, "grad_norm": 0.44921875, "learning_rate": 1.7057670772676372e-05, "loss": 0.9763394927978516, "step": 399400 }, { "epoch": 4.600724482291632, "grad_norm": 0.59375, "learning_rate": 1.7050399208853855e-05, "loss": 0.9823768615722657, "step": 399600 }, { "epoch": 4.603027167366347, "grad_norm": 0.70703125, "learning_rate": 1.704312764503134e-05, "loss": 0.9815471649169922, "step": 399800 }, { "epoch": 4.605329852441062, "grad_norm": 0.484375, "learning_rate": 1.7035856081208823e-05, "loss": 1.0154531860351563, "step": 400000 }, { "epoch": 4.6076325375157765, "grad_norm": 0.58203125, "learning_rate": 1.702858451738631e-05, "loss": 0.9649147796630859, "step": 400200 }, { "epoch": 4.609935222590492, "grad_norm": 0.92578125, "learning_rate": 1.7021312953563795e-05, "loss": 0.9521435546875, "step": 400400 }, { "epoch": 4.612237907665207, "grad_norm": 0.6640625, "learning_rate": 1.701404138974128e-05, "loss": 0.9710287475585937, "step": 400600 }, { "epoch": 4.614540592739922, "grad_norm": 0.9609375, "learning_rate": 1.700676982591876e-05, "loss": 0.9978025817871093, "step": 400800 }, { "epoch": 4.616843277814636, "grad_norm": 0.73046875, "learning_rate": 1.6999498262096246e-05, "loss": 0.9523931121826172, "step": 401000 }, { "epoch": 4.619145962889352, "grad_norm": 0.6796875, "learning_rate": 1.6992226698273732e-05, "loss": 0.968920669555664, "step": 401200 }, { "epoch": 4.621448647964066, "grad_norm": 0.54296875, "learning_rate": 1.6984955134451215e-05, "loss": 0.9653475952148437, "step": 401400 }, { "epoch": 4.623751333038782, "grad_norm": 0.53125, "learning_rate": 1.69776835706287e-05, "loss": 1.0043842315673828, "step": 401600 }, { "epoch": 4.626054018113496, "grad_norm": 0.6953125, "learning_rate": 1.6970412006806186e-05, "loss": 0.9865167236328125, "step": 401800 }, { "epoch": 4.628356703188212, "grad_norm": 0.86328125, "learning_rate": 1.696314044298367e-05, "loss": 0.9743873596191406, "step": 402000 }, { "epoch": 4.630659388262926, "grad_norm": 0.6171875, "learning_rate": 1.695586887916115e-05, "loss": 0.972658920288086, "step": 402200 }, { "epoch": 4.632962073337641, "grad_norm": 0.61328125, "learning_rate": 1.6948597315338637e-05, "loss": 0.9776019287109375, "step": 402400 }, { "epoch": 4.635264758412356, "grad_norm": 0.5546875, "learning_rate": 1.694132575151612e-05, "loss": 1.0061843872070313, "step": 402600 }, { "epoch": 4.637567443487071, "grad_norm": 1.515625, "learning_rate": 1.6934054187693606e-05, "loss": 0.9649028015136719, "step": 402800 }, { "epoch": 4.639870128561786, "grad_norm": 0.66796875, "learning_rate": 1.6926782623871092e-05, "loss": 0.9808583068847656, "step": 403000 }, { "epoch": 4.642172813636501, "grad_norm": 0.451171875, "learning_rate": 1.6919511060048574e-05, "loss": 0.9756576538085937, "step": 403200 }, { "epoch": 4.644475498711216, "grad_norm": 0.66015625, "learning_rate": 1.6912239496226057e-05, "loss": 0.9983255767822266, "step": 403400 }, { "epoch": 4.646778183785931, "grad_norm": 0.69921875, "learning_rate": 1.6904967932403543e-05, "loss": 0.964236068725586, "step": 403600 }, { "epoch": 4.649080868860646, "grad_norm": 4.03125, "learning_rate": 1.689769636858103e-05, "loss": 0.9836663818359375, "step": 403800 }, { "epoch": 4.651383553935361, "grad_norm": 0.87890625, "learning_rate": 1.689042480475851e-05, "loss": 0.9943917083740235, "step": 404000 }, { "epoch": 4.653686239010076, "grad_norm": 0.6796875, "learning_rate": 1.6883153240935997e-05, "loss": 0.988160400390625, "step": 404200 }, { "epoch": 4.655988924084791, "grad_norm": 0.76953125, "learning_rate": 1.6875881677113483e-05, "loss": 0.9667311096191407, "step": 404400 }, { "epoch": 4.658291609159505, "grad_norm": 0.6171875, "learning_rate": 1.6868610113290962e-05, "loss": 0.9998202514648438, "step": 404600 }, { "epoch": 4.660594294234221, "grad_norm": 0.890625, "learning_rate": 1.6861338549468448e-05, "loss": 0.9816936492919922, "step": 404800 }, { "epoch": 4.662896979308935, "grad_norm": 0.671875, "learning_rate": 1.6854066985645934e-05, "loss": 0.9878934478759765, "step": 405000 }, { "epoch": 4.665199664383651, "grad_norm": 1.1171875, "learning_rate": 1.6846795421823416e-05, "loss": 0.9956065368652344, "step": 405200 }, { "epoch": 4.667502349458365, "grad_norm": 0.83203125, "learning_rate": 1.6839523858000902e-05, "loss": 0.9837393951416016, "step": 405400 }, { "epoch": 4.669805034533081, "grad_norm": 0.44140625, "learning_rate": 1.6832252294178388e-05, "loss": 0.9827626800537109, "step": 405600 }, { "epoch": 4.672107719607795, "grad_norm": 0.640625, "learning_rate": 1.682498073035587e-05, "loss": 0.9554264831542969, "step": 405800 }, { "epoch": 4.67441040468251, "grad_norm": 0.58203125, "learning_rate": 1.6817709166533353e-05, "loss": 0.9837741851806641, "step": 406000 }, { "epoch": 4.676713089757225, "grad_norm": 0.50390625, "learning_rate": 1.681043760271084e-05, "loss": 0.9775701141357422, "step": 406200 }, { "epoch": 4.67901577483194, "grad_norm": 0.6171875, "learning_rate": 1.6803166038888325e-05, "loss": 0.9809413146972656, "step": 406400 }, { "epoch": 4.681318459906655, "grad_norm": 0.9765625, "learning_rate": 1.6795894475065808e-05, "loss": 0.9923878479003906, "step": 406600 }, { "epoch": 4.68362114498137, "grad_norm": 0.49609375, "learning_rate": 1.6788622911243294e-05, "loss": 0.9792401885986328, "step": 406800 }, { "epoch": 4.685923830056085, "grad_norm": 0.77734375, "learning_rate": 1.678135134742078e-05, "loss": 0.9748235321044922, "step": 407000 }, { "epoch": 4.6882265151308, "grad_norm": 0.921875, "learning_rate": 1.677407978359826e-05, "loss": 0.9866321563720704, "step": 407200 }, { "epoch": 4.690529200205515, "grad_norm": 0.51171875, "learning_rate": 1.6766808219775745e-05, "loss": 1.0059503173828126, "step": 407400 }, { "epoch": 4.6928318852802295, "grad_norm": 0.65234375, "learning_rate": 1.675953665595323e-05, "loss": 0.9742549896240235, "step": 407600 }, { "epoch": 4.695134570354945, "grad_norm": 0.82421875, "learning_rate": 1.6752265092130713e-05, "loss": 0.988902587890625, "step": 407800 }, { "epoch": 4.6974372554296595, "grad_norm": 1.1171875, "learning_rate": 1.67449935283082e-05, "loss": 1.0010816192626952, "step": 408000 }, { "epoch": 4.699739940504374, "grad_norm": 0.68359375, "learning_rate": 1.6737721964485685e-05, "loss": 0.9866725158691406, "step": 408200 }, { "epoch": 4.7020426255790895, "grad_norm": 0.75, "learning_rate": 1.6730450400663167e-05, "loss": 0.9774224090576172, "step": 408400 }, { "epoch": 4.704345310653804, "grad_norm": 0.6015625, "learning_rate": 1.672317883684065e-05, "loss": 0.9602320098876953, "step": 408600 }, { "epoch": 4.706647995728519, "grad_norm": 7.4375, "learning_rate": 1.6715907273018136e-05, "loss": 0.9782334899902344, "step": 408800 }, { "epoch": 4.708950680803234, "grad_norm": 0.5, "learning_rate": 1.6708635709195618e-05, "loss": 0.9678709411621094, "step": 409000 }, { "epoch": 4.711253365877949, "grad_norm": 0.56640625, "learning_rate": 1.6701364145373104e-05, "loss": 1.002803192138672, "step": 409200 }, { "epoch": 4.713556050952664, "grad_norm": 0.69921875, "learning_rate": 1.669409258155059e-05, "loss": 0.9881256866455078, "step": 409400 }, { "epoch": 4.7158587360273785, "grad_norm": 0.84375, "learning_rate": 1.6686821017728076e-05, "loss": 0.9696332550048828, "step": 409600 }, { "epoch": 4.718161421102094, "grad_norm": 0.828125, "learning_rate": 1.6679549453905555e-05, "loss": 0.976830825805664, "step": 409800 }, { "epoch": 4.7204641061768084, "grad_norm": 0.7890625, "learning_rate": 1.667227789008304e-05, "loss": 1.0149959564208983, "step": 410000 }, { "epoch": 4.722766791251524, "grad_norm": 0.671875, "learning_rate": 1.6665006326260527e-05, "loss": 1.0042466735839843, "step": 410200 }, { "epoch": 4.725069476326238, "grad_norm": 1.0859375, "learning_rate": 1.665773476243801e-05, "loss": 0.9852333831787109, "step": 410400 }, { "epoch": 4.727372161400954, "grad_norm": 0.68359375, "learning_rate": 1.6650463198615495e-05, "loss": 0.9823546600341797, "step": 410600 }, { "epoch": 4.729674846475668, "grad_norm": 0.78125, "learning_rate": 1.664319163479298e-05, "loss": 0.9931096649169922, "step": 410800 }, { "epoch": 4.731977531550384, "grad_norm": 0.79296875, "learning_rate": 1.663592007097046e-05, "loss": 0.9812409210205079, "step": 411000 }, { "epoch": 4.734280216625098, "grad_norm": 0.578125, "learning_rate": 1.6628648507147946e-05, "loss": 0.9841607666015625, "step": 411200 }, { "epoch": 4.736582901699814, "grad_norm": 0.5625, "learning_rate": 1.6621376943325432e-05, "loss": 0.9859600067138672, "step": 411400 }, { "epoch": 4.738885586774528, "grad_norm": 0.50390625, "learning_rate": 1.6614105379502915e-05, "loss": 0.9925346374511719, "step": 411600 }, { "epoch": 4.741188271849243, "grad_norm": 0.55078125, "learning_rate": 1.66068338156804e-05, "loss": 0.9583389282226562, "step": 411800 }, { "epoch": 4.743490956923958, "grad_norm": 0.5625, "learning_rate": 1.6599562251857887e-05, "loss": 0.9840799713134766, "step": 412000 }, { "epoch": 4.745793641998673, "grad_norm": 0.5625, "learning_rate": 1.659229068803537e-05, "loss": 0.9803349304199219, "step": 412200 }, { "epoch": 4.748096327073388, "grad_norm": 0.392578125, "learning_rate": 1.6585019124212852e-05, "loss": 0.9900364685058594, "step": 412400 }, { "epoch": 4.750399012148103, "grad_norm": 0.546875, "learning_rate": 1.6577747560390338e-05, "loss": 0.9938496398925781, "step": 412600 }, { "epoch": 4.752701697222818, "grad_norm": 0.5546875, "learning_rate": 1.6570475996567824e-05, "loss": 0.971194076538086, "step": 412800 }, { "epoch": 4.755004382297533, "grad_norm": 0.5078125, "learning_rate": 1.6563204432745306e-05, "loss": 0.9769140625, "step": 413000 }, { "epoch": 4.757307067372247, "grad_norm": 1.0390625, "learning_rate": 1.6555932868922792e-05, "loss": 0.9798918151855469, "step": 413200 }, { "epoch": 4.759609752446963, "grad_norm": 0.828125, "learning_rate": 1.6548661305100278e-05, "loss": 1.015190887451172, "step": 413400 }, { "epoch": 4.761912437521677, "grad_norm": 0.578125, "learning_rate": 1.6541389741277757e-05, "loss": 0.9922569274902344, "step": 413600 }, { "epoch": 4.764215122596393, "grad_norm": 0.431640625, "learning_rate": 1.6534118177455243e-05, "loss": 0.9750289916992188, "step": 413800 }, { "epoch": 4.766517807671107, "grad_norm": 1.3359375, "learning_rate": 1.652684661363273e-05, "loss": 0.9908672332763672, "step": 414000 }, { "epoch": 4.768820492745823, "grad_norm": 1.09375, "learning_rate": 1.651957504981021e-05, "loss": 0.982567138671875, "step": 414200 }, { "epoch": 4.771123177820537, "grad_norm": 0.5703125, "learning_rate": 1.6512303485987697e-05, "loss": 1.0064954376220703, "step": 414400 }, { "epoch": 4.773425862895253, "grad_norm": 0.9375, "learning_rate": 1.6505031922165183e-05, "loss": 0.9864546966552734, "step": 414600 }, { "epoch": 4.775728547969967, "grad_norm": 0.71875, "learning_rate": 1.6497760358342662e-05, "loss": 0.9798056030273438, "step": 414800 }, { "epoch": 4.778031233044683, "grad_norm": 0.458984375, "learning_rate": 1.6490488794520148e-05, "loss": 1.0037300872802735, "step": 415000 }, { "epoch": 4.780333918119397, "grad_norm": 0.7890625, "learning_rate": 1.6483217230697634e-05, "loss": 1.0045165252685546, "step": 415200 }, { "epoch": 4.782636603194112, "grad_norm": 0.6796875, "learning_rate": 1.647594566687512e-05, "loss": 0.9751959991455078, "step": 415400 }, { "epoch": 4.784939288268827, "grad_norm": 0.47265625, "learning_rate": 1.6468674103052603e-05, "loss": 0.995721435546875, "step": 415600 }, { "epoch": 4.787241973343542, "grad_norm": 0.66015625, "learning_rate": 1.646140253923009e-05, "loss": 0.9940896606445313, "step": 415800 }, { "epoch": 4.789544658418257, "grad_norm": 0.78125, "learning_rate": 1.6454130975407574e-05, "loss": 0.9893470764160156, "step": 416000 }, { "epoch": 4.791847343492972, "grad_norm": 0.6484375, "learning_rate": 1.6446859411585054e-05, "loss": 0.9823805236816406, "step": 416200 }, { "epoch": 4.794150028567687, "grad_norm": 0.71875, "learning_rate": 1.643958784776254e-05, "loss": 0.9910964965820312, "step": 416400 }, { "epoch": 4.7964527136424016, "grad_norm": 0.85546875, "learning_rate": 1.6432316283940025e-05, "loss": 0.9669364929199219, "step": 416600 }, { "epoch": 4.798755398717116, "grad_norm": 0.6796875, "learning_rate": 1.6425044720117508e-05, "loss": 0.9694680023193359, "step": 416800 }, { "epoch": 4.8010580837918315, "grad_norm": 1.265625, "learning_rate": 1.6417773156294994e-05, "loss": 0.993616943359375, "step": 417000 }, { "epoch": 4.803360768866546, "grad_norm": 0.44921875, "learning_rate": 1.641050159247248e-05, "loss": 0.987774658203125, "step": 417200 }, { "epoch": 4.8056634539412615, "grad_norm": 0.7109375, "learning_rate": 1.640323002864996e-05, "loss": 0.9848440551757812, "step": 417400 }, { "epoch": 4.807966139015976, "grad_norm": 0.57421875, "learning_rate": 1.6395958464827445e-05, "loss": 0.9658927154541016, "step": 417600 }, { "epoch": 4.8102688240906915, "grad_norm": 2.109375, "learning_rate": 1.638868690100493e-05, "loss": 0.9894432830810547, "step": 417800 }, { "epoch": 4.812571509165406, "grad_norm": 1.328125, "learning_rate": 1.6381415337182413e-05, "loss": 0.9847721099853516, "step": 418000 }, { "epoch": 4.814874194240121, "grad_norm": 1.3828125, "learning_rate": 1.63741437733599e-05, "loss": 0.9953361511230469, "step": 418200 }, { "epoch": 4.817176879314836, "grad_norm": 0.7421875, "learning_rate": 1.6366872209537385e-05, "loss": 0.9875911712646485, "step": 418400 }, { "epoch": 4.819479564389551, "grad_norm": 0.6640625, "learning_rate": 1.635960064571487e-05, "loss": 0.9725639343261718, "step": 418600 }, { "epoch": 4.821782249464266, "grad_norm": 0.6640625, "learning_rate": 1.635232908189235e-05, "loss": 0.9967562866210937, "step": 418800 }, { "epoch": 4.8240849345389805, "grad_norm": 1.296875, "learning_rate": 1.6345057518069836e-05, "loss": 0.9764330291748047, "step": 419000 }, { "epoch": 4.826387619613696, "grad_norm": 1.09375, "learning_rate": 1.6337785954247322e-05, "loss": 0.9936328125, "step": 419200 }, { "epoch": 4.82869030468841, "grad_norm": 0.55859375, "learning_rate": 1.6330514390424804e-05, "loss": 0.9871342468261719, "step": 419400 }, { "epoch": 4.830992989763126, "grad_norm": 0.75, "learning_rate": 1.632324282660229e-05, "loss": 0.9947419738769532, "step": 419600 }, { "epoch": 4.83329567483784, "grad_norm": 0.73046875, "learning_rate": 1.6315971262779776e-05, "loss": 0.9876214599609375, "step": 419800 }, { "epoch": 4.835598359912556, "grad_norm": 1.0859375, "learning_rate": 1.6308699698957255e-05, "loss": 0.9614956665039063, "step": 420000 }, { "epoch": 4.83790104498727, "grad_norm": 0.6328125, "learning_rate": 1.630142813513474e-05, "loss": 0.981507797241211, "step": 420200 }, { "epoch": 4.840203730061986, "grad_norm": 0.69921875, "learning_rate": 1.6294156571312227e-05, "loss": 0.9904711151123047, "step": 420400 }, { "epoch": 4.8425064151367, "grad_norm": 0.76953125, "learning_rate": 1.628688500748971e-05, "loss": 0.981631851196289, "step": 420600 }, { "epoch": 4.844809100211416, "grad_norm": 0.67578125, "learning_rate": 1.6279613443667196e-05, "loss": 0.9610891723632813, "step": 420800 }, { "epoch": 4.84711178528613, "grad_norm": 0.6484375, "learning_rate": 1.627234187984468e-05, "loss": 1.0071526336669923, "step": 421000 }, { "epoch": 4.849414470360845, "grad_norm": 0.98828125, "learning_rate": 1.6265070316022164e-05, "loss": 0.9685559844970704, "step": 421200 }, { "epoch": 4.85171715543556, "grad_norm": 0.62109375, "learning_rate": 1.6257798752199647e-05, "loss": 0.9827532196044921, "step": 421400 }, { "epoch": 4.854019840510275, "grad_norm": 0.703125, "learning_rate": 1.6250527188377133e-05, "loss": 0.9905502319335937, "step": 421600 }, { "epoch": 4.85632252558499, "grad_norm": 0.78515625, "learning_rate": 1.624325562455462e-05, "loss": 0.9697259521484375, "step": 421800 }, { "epoch": 4.858625210659705, "grad_norm": 0.84765625, "learning_rate": 1.62359840607321e-05, "loss": 0.9974535369873047, "step": 422000 }, { "epoch": 4.86092789573442, "grad_norm": 0.62890625, "learning_rate": 1.6228712496909587e-05, "loss": 0.9746042633056641, "step": 422200 }, { "epoch": 4.863230580809135, "grad_norm": 0.765625, "learning_rate": 1.6221440933087073e-05, "loss": 0.9784107971191406, "step": 422400 }, { "epoch": 4.865533265883849, "grad_norm": 0.73046875, "learning_rate": 1.6214169369264552e-05, "loss": 0.9914553833007812, "step": 422600 }, { "epoch": 4.867835950958565, "grad_norm": 0.546875, "learning_rate": 1.6206897805442038e-05, "loss": 0.9690621948242187, "step": 422800 }, { "epoch": 4.870138636033279, "grad_norm": 0.53515625, "learning_rate": 1.6199626241619524e-05, "loss": 0.9820099639892578, "step": 423000 }, { "epoch": 4.872441321107995, "grad_norm": 0.67578125, "learning_rate": 1.6192354677797006e-05, "loss": 0.9805403137207032, "step": 423200 }, { "epoch": 4.874744006182709, "grad_norm": 0.94921875, "learning_rate": 1.6185083113974492e-05, "loss": 0.9757598876953125, "step": 423400 }, { "epoch": 4.877046691257425, "grad_norm": 0.5625, "learning_rate": 1.6177811550151978e-05, "loss": 0.9821089172363281, "step": 423600 }, { "epoch": 4.879349376332139, "grad_norm": 0.58203125, "learning_rate": 1.6170539986329457e-05, "loss": 0.9766545867919922, "step": 423800 }, { "epoch": 4.881652061406855, "grad_norm": 0.609375, "learning_rate": 1.6163268422506943e-05, "loss": 0.9831093597412109, "step": 424000 }, { "epoch": 4.883954746481569, "grad_norm": 0.953125, "learning_rate": 1.615599685868443e-05, "loss": 0.9682130432128906, "step": 424200 }, { "epoch": 4.886257431556285, "grad_norm": 0.765625, "learning_rate": 1.6148725294861915e-05, "loss": 0.9696171569824219, "step": 424400 }, { "epoch": 4.888560116630999, "grad_norm": 0.8046875, "learning_rate": 1.6141453731039398e-05, "loss": 0.9785321807861328, "step": 424600 }, { "epoch": 4.890862801705714, "grad_norm": 0.8125, "learning_rate": 1.6134182167216883e-05, "loss": 0.9684022521972656, "step": 424800 }, { "epoch": 4.893165486780429, "grad_norm": 0.609375, "learning_rate": 1.6126910603394366e-05, "loss": 0.9904294586181641, "step": 425000 }, { "epoch": 4.895468171855144, "grad_norm": 0.6796875, "learning_rate": 1.611963903957185e-05, "loss": 0.9782858276367188, "step": 425200 }, { "epoch": 4.897770856929859, "grad_norm": 0.5, "learning_rate": 1.6112367475749334e-05, "loss": 0.995420913696289, "step": 425400 }, { "epoch": 4.900073542004574, "grad_norm": 0.96484375, "learning_rate": 1.610509591192682e-05, "loss": 0.9884532928466797, "step": 425600 }, { "epoch": 4.902376227079289, "grad_norm": 0.51171875, "learning_rate": 1.6097824348104303e-05, "loss": 0.9923461151123046, "step": 425800 }, { "epoch": 4.9046789121540035, "grad_norm": 0.6328125, "learning_rate": 1.609055278428179e-05, "loss": 0.9905690002441406, "step": 426000 }, { "epoch": 4.906981597228718, "grad_norm": 0.640625, "learning_rate": 1.6083281220459275e-05, "loss": 1.0047775268554688, "step": 426200 }, { "epoch": 4.9092842823034335, "grad_norm": 0.734375, "learning_rate": 1.6076009656636754e-05, "loss": 0.9881675720214844, "step": 426400 }, { "epoch": 4.911586967378148, "grad_norm": 0.64453125, "learning_rate": 1.606873809281424e-05, "loss": 0.9722449493408203, "step": 426600 }, { "epoch": 4.9138896524528635, "grad_norm": 0.5859375, "learning_rate": 1.6061466528991726e-05, "loss": 0.9992510223388672, "step": 426800 }, { "epoch": 4.916192337527578, "grad_norm": 0.98828125, "learning_rate": 1.605419496516921e-05, "loss": 0.9681453704833984, "step": 427000 }, { "epoch": 4.918495022602293, "grad_norm": 0.63671875, "learning_rate": 1.6046923401346694e-05, "loss": 0.9711811828613282, "step": 427200 }, { "epoch": 4.920797707677008, "grad_norm": 0.53125, "learning_rate": 1.603965183752418e-05, "loss": 0.9840038299560547, "step": 427400 }, { "epoch": 4.923100392751723, "grad_norm": 1.2421875, "learning_rate": 1.6032380273701663e-05, "loss": 0.9930586242675781, "step": 427600 }, { "epoch": 4.925403077826438, "grad_norm": 0.86328125, "learning_rate": 1.6025108709879145e-05, "loss": 0.9876455688476562, "step": 427800 }, { "epoch": 4.927705762901153, "grad_norm": 0.5, "learning_rate": 1.601783714605663e-05, "loss": 0.9847328186035156, "step": 428000 }, { "epoch": 4.930008447975868, "grad_norm": 0.70703125, "learning_rate": 1.6010565582234117e-05, "loss": 0.980836181640625, "step": 428200 }, { "epoch": 4.932311133050582, "grad_norm": 0.5390625, "learning_rate": 1.60032940184116e-05, "loss": 0.9755804443359375, "step": 428400 }, { "epoch": 4.934613818125298, "grad_norm": 0.71875, "learning_rate": 1.5996022454589085e-05, "loss": 0.9845207214355469, "step": 428600 }, { "epoch": 4.936916503200012, "grad_norm": 0.3984375, "learning_rate": 1.598875089076657e-05, "loss": 0.9741409301757813, "step": 428800 }, { "epoch": 4.939219188274728, "grad_norm": 0.6875, "learning_rate": 1.598147932694405e-05, "loss": 0.9703875732421875, "step": 429000 }, { "epoch": 4.941521873349442, "grad_norm": 0.57421875, "learning_rate": 1.5974207763121536e-05, "loss": 0.9845467376708984, "step": 429200 }, { "epoch": 4.943824558424158, "grad_norm": 0.8203125, "learning_rate": 1.5966936199299022e-05, "loss": 0.9741230010986328, "step": 429400 }, { "epoch": 4.946127243498872, "grad_norm": 0.5, "learning_rate": 1.5959664635476505e-05, "loss": 0.9744194793701172, "step": 429600 }, { "epoch": 4.948429928573587, "grad_norm": 0.984375, "learning_rate": 1.595239307165399e-05, "loss": 0.9622555541992187, "step": 429800 }, { "epoch": 4.950732613648302, "grad_norm": 0.65234375, "learning_rate": 1.5945121507831477e-05, "loss": 0.9699842071533203, "step": 430000 }, { "epoch": 4.953035298723017, "grad_norm": 0.48046875, "learning_rate": 1.593784994400896e-05, "loss": 0.9580533599853516, "step": 430200 }, { "epoch": 4.955337983797732, "grad_norm": 0.37890625, "learning_rate": 1.593057838018644e-05, "loss": 0.9905766296386719, "step": 430400 }, { "epoch": 4.957640668872447, "grad_norm": 0.76953125, "learning_rate": 1.5923306816363928e-05, "loss": 0.977527847290039, "step": 430600 }, { "epoch": 4.959943353947162, "grad_norm": 0.48046875, "learning_rate": 1.5916035252541413e-05, "loss": 0.9803998565673828, "step": 430800 }, { "epoch": 4.962246039021877, "grad_norm": 0.77734375, "learning_rate": 1.5908763688718896e-05, "loss": 1.0080958557128907, "step": 431000 }, { "epoch": 4.964548724096592, "grad_norm": 0.88671875, "learning_rate": 1.5901492124896382e-05, "loss": 0.9899720001220703, "step": 431200 }, { "epoch": 4.966851409171307, "grad_norm": 0.7421875, "learning_rate": 1.5894220561073864e-05, "loss": 0.96768798828125, "step": 431400 }, { "epoch": 4.969154094246022, "grad_norm": 0.984375, "learning_rate": 1.5886948997251347e-05, "loss": 0.9832350158691406, "step": 431600 }, { "epoch": 4.971456779320737, "grad_norm": 4.90625, "learning_rate": 1.5879677433428833e-05, "loss": 0.973259506225586, "step": 431800 }, { "epoch": 4.973759464395451, "grad_norm": 0.6328125, "learning_rate": 1.587240586960632e-05, "loss": 0.9868125915527344, "step": 432000 }, { "epoch": 4.976062149470167, "grad_norm": 0.73046875, "learning_rate": 1.58651343057838e-05, "loss": 1.0016079711914063, "step": 432200 }, { "epoch": 4.978364834544881, "grad_norm": 0.4921875, "learning_rate": 1.5857862741961287e-05, "loss": 0.997337875366211, "step": 432400 }, { "epoch": 4.980667519619597, "grad_norm": 1.15625, "learning_rate": 1.5850591178138773e-05, "loss": 0.9590795135498047, "step": 432600 }, { "epoch": 4.982970204694311, "grad_norm": 0.578125, "learning_rate": 1.5843319614316256e-05, "loss": 0.9921549224853515, "step": 432800 }, { "epoch": 4.985272889769027, "grad_norm": 1.140625, "learning_rate": 1.5836048050493738e-05, "loss": 0.9745076751708984, "step": 433000 }, { "epoch": 4.987575574843741, "grad_norm": 0.412109375, "learning_rate": 1.5828776486671224e-05, "loss": 0.972037582397461, "step": 433200 }, { "epoch": 4.989878259918456, "grad_norm": 0.8359375, "learning_rate": 1.582150492284871e-05, "loss": 0.973899154663086, "step": 433400 }, { "epoch": 4.992180944993171, "grad_norm": 0.796875, "learning_rate": 1.5814233359026193e-05, "loss": 0.9822638702392578, "step": 433600 }, { "epoch": 4.994483630067886, "grad_norm": 0.69140625, "learning_rate": 1.580696179520368e-05, "loss": 0.9719387054443359, "step": 433800 }, { "epoch": 4.996786315142601, "grad_norm": 0.546875, "learning_rate": 1.579969023138116e-05, "loss": 0.9759081268310547, "step": 434000 }, { "epoch": 4.999089000217316, "grad_norm": 0.54296875, "learning_rate": 1.5792418667558643e-05, "loss": 0.9978753662109375, "step": 434200 }, { "epoch": 5.0, "eval_loss": NaN, "eval_runtime": 432.1192, "eval_samples_per_second": 65.632, "eval_steps_per_second": 32.817, "step": 434280 }, { "epoch": 5.001381611044829, "grad_norm": 0.625, "learning_rate": 1.578514710373613e-05, "loss": 0.9861835479736328, "step": 434400 }, { "epoch": 5.003684296119544, "grad_norm": 0.51171875, "learning_rate": 1.5777875539913615e-05, "loss": 0.9894441986083984, "step": 434600 }, { "epoch": 5.005986981194259, "grad_norm": 0.83984375, "learning_rate": 1.5770603976091098e-05, "loss": 0.9802412414550781, "step": 434800 }, { "epoch": 5.008289666268974, "grad_norm": 0.48046875, "learning_rate": 1.5763332412268584e-05, "loss": 0.9692536163330078, "step": 435000 }, { "epoch": 5.010592351343688, "grad_norm": 0.83203125, "learning_rate": 1.575606084844607e-05, "loss": 0.9791400909423829, "step": 435200 }, { "epoch": 5.012895036418404, "grad_norm": 0.52734375, "learning_rate": 1.574878928462355e-05, "loss": 0.98474609375, "step": 435400 }, { "epoch": 5.015197721493118, "grad_norm": 0.423828125, "learning_rate": 1.5741517720801035e-05, "loss": 0.9832347869873047, "step": 435600 }, { "epoch": 5.017500406567834, "grad_norm": 0.7734375, "learning_rate": 1.573424615697852e-05, "loss": 0.983828353881836, "step": 435800 }, { "epoch": 5.019803091642548, "grad_norm": 0.58984375, "learning_rate": 1.5726974593156007e-05, "loss": 0.9714756011962891, "step": 436000 }, { "epoch": 5.022105776717264, "grad_norm": 0.57421875, "learning_rate": 1.571970302933349e-05, "loss": 0.9881432342529297, "step": 436200 }, { "epoch": 5.024408461791978, "grad_norm": 0.50390625, "learning_rate": 1.5712431465510975e-05, "loss": 0.9834969329833985, "step": 436400 }, { "epoch": 5.026711146866694, "grad_norm": 0.65234375, "learning_rate": 1.5705159901688457e-05, "loss": 0.9566364288330078, "step": 436600 }, { "epoch": 5.029013831941408, "grad_norm": 0.6171875, "learning_rate": 1.569788833786594e-05, "loss": 0.9873866271972657, "step": 436800 }, { "epoch": 5.031316517016123, "grad_norm": 0.41796875, "learning_rate": 1.5690616774043426e-05, "loss": 0.9714003753662109, "step": 437000 }, { "epoch": 5.033619202090838, "grad_norm": 0.80859375, "learning_rate": 1.5683345210220912e-05, "loss": 0.9779801940917969, "step": 437200 }, { "epoch": 5.035921887165553, "grad_norm": 0.515625, "learning_rate": 1.5676073646398394e-05, "loss": 0.9925363159179688, "step": 437400 }, { "epoch": 5.038224572240268, "grad_norm": 1.2421875, "learning_rate": 1.566880208257588e-05, "loss": 0.962649917602539, "step": 437600 }, { "epoch": 5.040527257314983, "grad_norm": 0.88671875, "learning_rate": 1.5661530518753363e-05, "loss": 0.9825556182861328, "step": 437800 }, { "epoch": 5.042829942389698, "grad_norm": 0.8046875, "learning_rate": 1.5654258954930845e-05, "loss": 0.9778278350830079, "step": 438000 }, { "epoch": 5.045132627464413, "grad_norm": 0.498046875, "learning_rate": 1.564698739110833e-05, "loss": 0.9800408935546875, "step": 438200 }, { "epoch": 5.047435312539128, "grad_norm": 1.0546875, "learning_rate": 1.5639715827285817e-05, "loss": 0.9869258117675781, "step": 438400 }, { "epoch": 5.049737997613843, "grad_norm": 0.94921875, "learning_rate": 1.56324442634633e-05, "loss": 1.0070904541015624, "step": 438600 }, { "epoch": 5.052040682688557, "grad_norm": 0.58984375, "learning_rate": 1.5625172699640786e-05, "loss": 0.9841986846923828, "step": 438800 }, { "epoch": 5.0543433677632725, "grad_norm": 1.09375, "learning_rate": 1.561790113581827e-05, "loss": 0.9610589599609375, "step": 439000 }, { "epoch": 5.056646052837987, "grad_norm": 0.4921875, "learning_rate": 1.5610629571995754e-05, "loss": 0.9943707275390625, "step": 439200 }, { "epoch": 5.0589487379127025, "grad_norm": 0.703125, "learning_rate": 1.5603358008173237e-05, "loss": 0.9718830108642578, "step": 439400 }, { "epoch": 5.061251422987417, "grad_norm": 0.6171875, "learning_rate": 1.5596086444350722e-05, "loss": 0.9629135131835938, "step": 439600 }, { "epoch": 5.0635541080621325, "grad_norm": 0.76953125, "learning_rate": 1.558881488052821e-05, "loss": 0.988746337890625, "step": 439800 }, { "epoch": 5.065856793136847, "grad_norm": 0.6015625, "learning_rate": 1.558154331670569e-05, "loss": 0.9679503631591797, "step": 440000 }, { "epoch": 5.068159478211562, "grad_norm": 1.8359375, "learning_rate": 1.5574271752883177e-05, "loss": 0.9796177673339844, "step": 440200 }, { "epoch": 5.070462163286277, "grad_norm": 0.5859375, "learning_rate": 1.556700018906066e-05, "loss": 0.9999834442138672, "step": 440400 }, { "epoch": 5.0727648483609915, "grad_norm": 0.6640625, "learning_rate": 1.5559728625238142e-05, "loss": 0.9751573181152344, "step": 440600 }, { "epoch": 5.075067533435707, "grad_norm": 0.43359375, "learning_rate": 1.5552457061415628e-05, "loss": 0.9943019866943359, "step": 440800 }, { "epoch": 5.0773702185104215, "grad_norm": 0.48046875, "learning_rate": 1.5545185497593114e-05, "loss": 0.9995348358154297, "step": 441000 }, { "epoch": 5.079672903585137, "grad_norm": 0.59375, "learning_rate": 1.5537913933770596e-05, "loss": 1.0012002563476563, "step": 441200 }, { "epoch": 5.081975588659851, "grad_norm": 0.63671875, "learning_rate": 1.5530642369948082e-05, "loss": 0.9686441802978516, "step": 441400 }, { "epoch": 5.084278273734567, "grad_norm": 0.79296875, "learning_rate": 1.5523370806125565e-05, "loss": 0.9707472991943359, "step": 441600 }, { "epoch": 5.086580958809281, "grad_norm": 0.5546875, "learning_rate": 1.551609924230305e-05, "loss": 0.991561279296875, "step": 441800 }, { "epoch": 5.088883643883997, "grad_norm": 0.578125, "learning_rate": 1.5508827678480533e-05, "loss": 0.9646013641357422, "step": 442000 }, { "epoch": 5.091186328958711, "grad_norm": 0.64453125, "learning_rate": 1.550155611465802e-05, "loss": 0.9842584991455078, "step": 442200 }, { "epoch": 5.093489014033427, "grad_norm": 0.640625, "learning_rate": 1.5494284550835505e-05, "loss": 0.9831058502197265, "step": 442400 }, { "epoch": 5.095791699108141, "grad_norm": 0.59765625, "learning_rate": 1.5487012987012987e-05, "loss": 0.9710477447509765, "step": 442600 }, { "epoch": 5.098094384182856, "grad_norm": 0.80859375, "learning_rate": 1.5479741423190473e-05, "loss": 0.986195068359375, "step": 442800 }, { "epoch": 5.100397069257571, "grad_norm": 0.5546875, "learning_rate": 1.5472469859367956e-05, "loss": 0.9769602966308594, "step": 443000 }, { "epoch": 5.102699754332286, "grad_norm": 0.7265625, "learning_rate": 1.546519829554544e-05, "loss": 0.982730484008789, "step": 443200 }, { "epoch": 5.105002439407001, "grad_norm": 0.94921875, "learning_rate": 1.5457926731722924e-05, "loss": 0.9746049499511719, "step": 443400 }, { "epoch": 5.107305124481716, "grad_norm": 0.5078125, "learning_rate": 1.545065516790041e-05, "loss": 1.0082730102539061, "step": 443600 }, { "epoch": 5.109607809556431, "grad_norm": 0.75390625, "learning_rate": 1.5443383604077893e-05, "loss": 0.9730638885498046, "step": 443800 }, { "epoch": 5.111910494631146, "grad_norm": 0.625, "learning_rate": 1.543611204025538e-05, "loss": 0.9843389129638672, "step": 444000 }, { "epoch": 5.114213179705861, "grad_norm": 0.63671875, "learning_rate": 1.542884047643286e-05, "loss": 0.9781219482421875, "step": 444200 }, { "epoch": 5.116515864780576, "grad_norm": 1.1171875, "learning_rate": 1.5421568912610344e-05, "loss": 0.9844216156005859, "step": 444400 }, { "epoch": 5.11881854985529, "grad_norm": 1.1796875, "learning_rate": 1.541429734878783e-05, "loss": 0.9864201354980469, "step": 444600 }, { "epoch": 5.121121234930006, "grad_norm": 1.0390625, "learning_rate": 1.5407025784965316e-05, "loss": 0.9955843353271484, "step": 444800 }, { "epoch": 5.12342392000472, "grad_norm": 0.85546875, "learning_rate": 1.53997542211428e-05, "loss": 0.9566255950927735, "step": 445000 }, { "epoch": 5.125726605079436, "grad_norm": 0.447265625, "learning_rate": 1.5392482657320284e-05, "loss": 0.9770396423339843, "step": 445200 }, { "epoch": 5.12802929015415, "grad_norm": 0.8203125, "learning_rate": 1.538521109349777e-05, "loss": 0.9763878631591797, "step": 445400 }, { "epoch": 5.130331975228866, "grad_norm": 0.62109375, "learning_rate": 1.5377939529675252e-05, "loss": 0.97738037109375, "step": 445600 }, { "epoch": 5.13263466030358, "grad_norm": 0.87890625, "learning_rate": 1.5370667965852735e-05, "loss": 0.9798085021972657, "step": 445800 }, { "epoch": 5.134937345378296, "grad_norm": 0.953125, "learning_rate": 1.536339640203022e-05, "loss": 0.9778961944580078, "step": 446000 }, { "epoch": 5.13724003045301, "grad_norm": 0.54296875, "learning_rate": 1.5356124838207707e-05, "loss": 0.9781346130371094, "step": 446200 }, { "epoch": 5.139542715527725, "grad_norm": 0.734375, "learning_rate": 1.534885327438519e-05, "loss": 1.0051431274414062, "step": 446400 }, { "epoch": 5.14184540060244, "grad_norm": 0.51171875, "learning_rate": 1.5341581710562675e-05, "loss": 0.9866223907470704, "step": 446600 }, { "epoch": 5.144148085677155, "grad_norm": 1.15625, "learning_rate": 1.5334310146740158e-05, "loss": 0.979072265625, "step": 446800 }, { "epoch": 5.14645077075187, "grad_norm": 0.47265625, "learning_rate": 1.532703858291764e-05, "loss": 1.0071894073486327, "step": 447000 }, { "epoch": 5.148753455826585, "grad_norm": 0.8203125, "learning_rate": 1.5319767019095126e-05, "loss": 0.9757035064697266, "step": 447200 }, { "epoch": 5.1510561409013, "grad_norm": 0.578125, "learning_rate": 1.5312495455272612e-05, "loss": 0.9830738067626953, "step": 447400 }, { "epoch": 5.153358825976015, "grad_norm": 0.7109375, "learning_rate": 1.5305223891450098e-05, "loss": 0.9869244384765625, "step": 447600 }, { "epoch": 5.15566151105073, "grad_norm": 0.65625, "learning_rate": 1.529795232762758e-05, "loss": 0.9828427124023438, "step": 447800 }, { "epoch": 5.1579641961254445, "grad_norm": 0.55859375, "learning_rate": 1.5290680763805063e-05, "loss": 0.9620997619628906, "step": 448000 }, { "epoch": 5.160266881200159, "grad_norm": 1.015625, "learning_rate": 1.528340919998255e-05, "loss": 0.9812986755371094, "step": 448200 }, { "epoch": 5.1625695662748745, "grad_norm": 0.61328125, "learning_rate": 1.527613763616003e-05, "loss": 0.9796999359130859, "step": 448400 }, { "epoch": 5.164872251349589, "grad_norm": 0.8125, "learning_rate": 1.5268866072337517e-05, "loss": 0.9977180480957031, "step": 448600 }, { "epoch": 5.1671749364243045, "grad_norm": 0.5546875, "learning_rate": 1.5261594508515003e-05, "loss": 0.9861807250976562, "step": 448800 }, { "epoch": 5.169477621499019, "grad_norm": 0.890625, "learning_rate": 1.5254322944692488e-05, "loss": 0.9859234619140625, "step": 449000 }, { "epoch": 5.171780306573734, "grad_norm": 0.6875, "learning_rate": 1.5247051380869972e-05, "loss": 0.9808116912841797, "step": 449200 }, { "epoch": 5.174082991648449, "grad_norm": 0.75, "learning_rate": 1.5239779817047453e-05, "loss": 0.9652620697021485, "step": 449400 }, { "epoch": 5.176385676723164, "grad_norm": 2.25, "learning_rate": 1.5232508253224939e-05, "loss": 0.9635680389404296, "step": 449600 }, { "epoch": 5.178688361797879, "grad_norm": 0.59375, "learning_rate": 1.5225236689402423e-05, "loss": 1.0047270202636718, "step": 449800 }, { "epoch": 5.1809910468725935, "grad_norm": 1.0078125, "learning_rate": 1.5217965125579909e-05, "loss": 0.9865448760986328, "step": 450000 }, { "epoch": 5.183293731947309, "grad_norm": 0.53125, "learning_rate": 1.5210693561757393e-05, "loss": 0.9875264739990235, "step": 450200 }, { "epoch": 5.1855964170220235, "grad_norm": 0.73828125, "learning_rate": 1.5203421997934877e-05, "loss": 0.9982109069824219, "step": 450400 }, { "epoch": 5.187899102096739, "grad_norm": 0.7421875, "learning_rate": 1.519615043411236e-05, "loss": 0.983709945678711, "step": 450600 }, { "epoch": 5.190201787171453, "grad_norm": 0.9375, "learning_rate": 1.5188878870289844e-05, "loss": 0.9661166381835937, "step": 450800 }, { "epoch": 5.192504472246169, "grad_norm": 1.03125, "learning_rate": 1.5181607306467328e-05, "loss": 0.9745197296142578, "step": 451000 }, { "epoch": 5.194807157320883, "grad_norm": 0.79296875, "learning_rate": 1.5174335742644814e-05, "loss": 0.9809587097167969, "step": 451200 }, { "epoch": 5.197109842395599, "grad_norm": 0.404296875, "learning_rate": 1.5167064178822298e-05, "loss": 0.9783151245117188, "step": 451400 }, { "epoch": 5.199412527470313, "grad_norm": 0.58984375, "learning_rate": 1.5159792614999784e-05, "loss": 0.9720295715332031, "step": 451600 }, { "epoch": 5.201715212545028, "grad_norm": 0.70703125, "learning_rate": 1.5152521051177265e-05, "loss": 0.9959677124023437, "step": 451800 }, { "epoch": 5.204017897619743, "grad_norm": 0.494140625, "learning_rate": 1.514524948735475e-05, "loss": 0.9739774322509765, "step": 452000 }, { "epoch": 5.206320582694458, "grad_norm": 0.69140625, "learning_rate": 1.5137977923532235e-05, "loss": 0.9681526947021485, "step": 452200 }, { "epoch": 5.208623267769173, "grad_norm": 0.74609375, "learning_rate": 1.513070635970972e-05, "loss": 0.9602870941162109, "step": 452400 }, { "epoch": 5.210925952843888, "grad_norm": 0.7734375, "learning_rate": 1.5123434795887204e-05, "loss": 1.0015093994140625, "step": 452600 }, { "epoch": 5.213228637918603, "grad_norm": 0.828125, "learning_rate": 1.511616323206469e-05, "loss": 0.96810302734375, "step": 452800 }, { "epoch": 5.215531322993318, "grad_norm": 0.474609375, "learning_rate": 1.5108891668242174e-05, "loss": 0.9807380676269531, "step": 453000 }, { "epoch": 5.217834008068033, "grad_norm": 0.404296875, "learning_rate": 1.5101620104419656e-05, "loss": 0.9774137115478516, "step": 453200 }, { "epoch": 5.220136693142748, "grad_norm": 0.5234375, "learning_rate": 1.509434854059714e-05, "loss": 0.9768766021728515, "step": 453400 }, { "epoch": 5.222439378217462, "grad_norm": 0.53125, "learning_rate": 1.5087076976774625e-05, "loss": 1.003528823852539, "step": 453600 }, { "epoch": 5.224742063292178, "grad_norm": 0.6484375, "learning_rate": 1.507980541295211e-05, "loss": 0.9844652557373047, "step": 453800 }, { "epoch": 5.227044748366892, "grad_norm": 0.828125, "learning_rate": 1.5072533849129595e-05, "loss": 0.9844374084472656, "step": 454000 }, { "epoch": 5.229347433441608, "grad_norm": 0.4140625, "learning_rate": 1.506526228530708e-05, "loss": 0.9929544830322266, "step": 454200 }, { "epoch": 5.231650118516322, "grad_norm": 1.2265625, "learning_rate": 1.5057990721484561e-05, "loss": 0.9618767547607422, "step": 454400 }, { "epoch": 5.233952803591038, "grad_norm": 0.6015625, "learning_rate": 1.5050719157662046e-05, "loss": 0.9770437622070313, "step": 454600 }, { "epoch": 5.236255488665752, "grad_norm": 0.55078125, "learning_rate": 1.5043447593839532e-05, "loss": 1.0074984741210937, "step": 454800 }, { "epoch": 5.238558173740468, "grad_norm": 1.0703125, "learning_rate": 1.5036176030017016e-05, "loss": 0.9927102661132813, "step": 455000 }, { "epoch": 5.240860858815182, "grad_norm": 0.96875, "learning_rate": 1.50289044661945e-05, "loss": 0.9880549621582031, "step": 455200 }, { "epoch": 5.243163543889897, "grad_norm": 0.859375, "learning_rate": 1.5021632902371986e-05, "loss": 0.9959085845947265, "step": 455400 }, { "epoch": 5.245466228964612, "grad_norm": 0.546875, "learning_rate": 1.501436133854947e-05, "loss": 0.993404541015625, "step": 455600 }, { "epoch": 5.247768914039327, "grad_norm": 0.90234375, "learning_rate": 1.5007089774726953e-05, "loss": 0.9818459320068359, "step": 455800 }, { "epoch": 5.250071599114042, "grad_norm": 0.640625, "learning_rate": 1.4999818210904437e-05, "loss": 0.9703733062744141, "step": 456000 }, { "epoch": 5.252374284188757, "grad_norm": 0.8984375, "learning_rate": 1.4992546647081921e-05, "loss": 0.9827092742919922, "step": 456200 }, { "epoch": 5.254676969263472, "grad_norm": 0.640625, "learning_rate": 1.4985275083259407e-05, "loss": 0.9929819488525391, "step": 456400 }, { "epoch": 5.256979654338187, "grad_norm": 0.6015625, "learning_rate": 1.497800351943689e-05, "loss": 0.9914261627197266, "step": 456600 }, { "epoch": 5.259282339412902, "grad_norm": 0.640625, "learning_rate": 1.4970731955614374e-05, "loss": 0.9822914123535156, "step": 456800 }, { "epoch": 5.261585024487617, "grad_norm": 0.66015625, "learning_rate": 1.496346039179186e-05, "loss": 0.9853893280029297, "step": 457000 }, { "epoch": 5.263887709562331, "grad_norm": 0.74609375, "learning_rate": 1.4956188827969344e-05, "loss": 0.9783312225341797, "step": 457200 }, { "epoch": 5.2661903946370465, "grad_norm": 0.447265625, "learning_rate": 1.4948917264146828e-05, "loss": 0.9891160583496094, "step": 457400 }, { "epoch": 5.268493079711761, "grad_norm": 0.5703125, "learning_rate": 1.4941645700324312e-05, "loss": 0.9707080841064453, "step": 457600 }, { "epoch": 5.2707957647864765, "grad_norm": 0.9375, "learning_rate": 1.4934374136501797e-05, "loss": 0.9764946746826172, "step": 457800 }, { "epoch": 5.273098449861191, "grad_norm": 0.6328125, "learning_rate": 1.492710257267928e-05, "loss": 0.9986644744873047, "step": 458000 }, { "epoch": 5.2754011349359065, "grad_norm": 0.75390625, "learning_rate": 1.4919831008856765e-05, "loss": 0.984770278930664, "step": 458200 }, { "epoch": 5.277703820010621, "grad_norm": 0.7109375, "learning_rate": 1.491255944503425e-05, "loss": 0.9775885772705079, "step": 458400 }, { "epoch": 5.280006505085336, "grad_norm": 0.8125, "learning_rate": 1.4905287881211733e-05, "loss": 0.9861846923828125, "step": 458600 }, { "epoch": 5.282309190160051, "grad_norm": 1.203125, "learning_rate": 1.4898016317389218e-05, "loss": 0.9947913360595703, "step": 458800 }, { "epoch": 5.284611875234766, "grad_norm": 0.625, "learning_rate": 1.4890744753566704e-05, "loss": 0.9821308898925781, "step": 459000 }, { "epoch": 5.286914560309481, "grad_norm": 0.546875, "learning_rate": 1.4883473189744186e-05, "loss": 0.991390609741211, "step": 459200 }, { "epoch": 5.2892172453841955, "grad_norm": 0.8203125, "learning_rate": 1.487620162592167e-05, "loss": 0.9703672027587891, "step": 459400 }, { "epoch": 5.291519930458911, "grad_norm": 0.82421875, "learning_rate": 1.4868930062099156e-05, "loss": 0.9787174224853515, "step": 459600 }, { "epoch": 5.293822615533625, "grad_norm": 0.47265625, "learning_rate": 1.4861658498276639e-05, "loss": 0.9987583923339843, "step": 459800 }, { "epoch": 5.296125300608341, "grad_norm": 0.796875, "learning_rate": 1.4854386934454125e-05, "loss": 0.9813053131103515, "step": 460000 }, { "epoch": 5.298427985683055, "grad_norm": 0.5703125, "learning_rate": 1.4847115370631609e-05, "loss": 1.0133036041259766, "step": 460200 }, { "epoch": 5.300730670757771, "grad_norm": 0.443359375, "learning_rate": 1.4839843806809091e-05, "loss": 1.000592269897461, "step": 460400 }, { "epoch": 5.303033355832485, "grad_norm": 0.71484375, "learning_rate": 1.4832572242986577e-05, "loss": 0.9804405212402344, "step": 460600 }, { "epoch": 5.3053360409072, "grad_norm": 0.7421875, "learning_rate": 1.4825300679164062e-05, "loss": 0.9746564483642578, "step": 460800 }, { "epoch": 5.307638725981915, "grad_norm": 0.70703125, "learning_rate": 1.4818029115341546e-05, "loss": 0.9901017761230468, "step": 461000 }, { "epoch": 5.30994141105663, "grad_norm": 0.55078125, "learning_rate": 1.481075755151903e-05, "loss": 0.9895965576171875, "step": 461200 }, { "epoch": 5.312244096131345, "grad_norm": 0.69140625, "learning_rate": 1.4803485987696514e-05, "loss": 0.9866258239746094, "step": 461400 }, { "epoch": 5.31454678120606, "grad_norm": 0.625, "learning_rate": 1.4796214423874e-05, "loss": 0.9936985778808594, "step": 461600 }, { "epoch": 5.316849466280775, "grad_norm": 0.5078125, "learning_rate": 1.4788942860051483e-05, "loss": 0.988270034790039, "step": 461800 }, { "epoch": 5.31915215135549, "grad_norm": 0.734375, "learning_rate": 1.4781671296228967e-05, "loss": 0.9763542938232422, "step": 462000 }, { "epoch": 5.321454836430205, "grad_norm": 0.55078125, "learning_rate": 1.4774399732406453e-05, "loss": 0.980770263671875, "step": 462200 }, { "epoch": 5.32375752150492, "grad_norm": 0.609375, "learning_rate": 1.4767128168583935e-05, "loss": 0.9823168182373047, "step": 462400 }, { "epoch": 5.326060206579635, "grad_norm": 0.734375, "learning_rate": 1.475985660476142e-05, "loss": 0.9989656829833984, "step": 462600 }, { "epoch": 5.32836289165435, "grad_norm": 1.53125, "learning_rate": 1.4752585040938905e-05, "loss": 1.0028610992431641, "step": 462800 }, { "epoch": 5.330665576729064, "grad_norm": 0.5625, "learning_rate": 1.4745313477116388e-05, "loss": 1.0008536529541017, "step": 463000 }, { "epoch": 5.33296826180378, "grad_norm": 0.88671875, "learning_rate": 1.4738041913293874e-05, "loss": 0.958477783203125, "step": 463200 }, { "epoch": 5.335270946878494, "grad_norm": 0.59375, "learning_rate": 1.4730770349471358e-05, "loss": 1.0013047027587891, "step": 463400 }, { "epoch": 5.33757363195321, "grad_norm": 1.9609375, "learning_rate": 1.472349878564884e-05, "loss": 0.9811349487304688, "step": 463600 }, { "epoch": 5.339876317027924, "grad_norm": 1.0078125, "learning_rate": 1.4716227221826327e-05, "loss": 0.9876372528076172, "step": 463800 }, { "epoch": 5.34217900210264, "grad_norm": 1.421875, "learning_rate": 1.470895565800381e-05, "loss": 0.987093505859375, "step": 464000 }, { "epoch": 5.344481687177354, "grad_norm": 0.94921875, "learning_rate": 1.4701684094181295e-05, "loss": 0.9624461364746094, "step": 464200 }, { "epoch": 5.346784372252069, "grad_norm": 0.66015625, "learning_rate": 1.469441253035878e-05, "loss": 0.972740249633789, "step": 464400 }, { "epoch": 5.349087057326784, "grad_norm": 0.50390625, "learning_rate": 1.4687140966536263e-05, "loss": 1.0043175506591797, "step": 464600 }, { "epoch": 5.351389742401499, "grad_norm": 0.8671875, "learning_rate": 1.467986940271375e-05, "loss": 0.9737282562255859, "step": 464800 }, { "epoch": 5.353692427476214, "grad_norm": 0.65234375, "learning_rate": 1.4672597838891232e-05, "loss": 0.9622456359863282, "step": 465000 }, { "epoch": 5.355995112550929, "grad_norm": 0.91796875, "learning_rate": 1.4665326275068716e-05, "loss": 0.9822862243652344, "step": 465200 }, { "epoch": 5.358297797625644, "grad_norm": 0.62109375, "learning_rate": 1.4658054711246202e-05, "loss": 0.9863087463378907, "step": 465400 }, { "epoch": 5.360600482700359, "grad_norm": 1.1953125, "learning_rate": 1.4650783147423685e-05, "loss": 1.0010931396484375, "step": 465600 }, { "epoch": 5.362903167775074, "grad_norm": 0.546875, "learning_rate": 1.4643511583601169e-05, "loss": 0.9757025146484375, "step": 465800 }, { "epoch": 5.365205852849789, "grad_norm": 0.97265625, "learning_rate": 1.4636240019778655e-05, "loss": 0.9824378204345703, "step": 466000 }, { "epoch": 5.367508537924504, "grad_norm": 0.70703125, "learning_rate": 1.4628968455956137e-05, "loss": 0.9661509704589843, "step": 466200 }, { "epoch": 5.3698112229992185, "grad_norm": 0.458984375, "learning_rate": 1.4621696892133623e-05, "loss": 0.967217025756836, "step": 466400 }, { "epoch": 5.372113908073933, "grad_norm": 0.466796875, "learning_rate": 1.4614425328311107e-05, "loss": 0.9927802276611328, "step": 466600 }, { "epoch": 5.3744165931486485, "grad_norm": 0.47265625, "learning_rate": 1.460715376448859e-05, "loss": 0.9893026733398438, "step": 466800 }, { "epoch": 5.376719278223363, "grad_norm": 0.65625, "learning_rate": 1.4599882200666076e-05, "loss": 0.9661732482910156, "step": 467000 }, { "epoch": 5.3790219632980785, "grad_norm": 0.50390625, "learning_rate": 1.459261063684356e-05, "loss": 0.9615573120117188, "step": 467200 }, { "epoch": 5.381324648372793, "grad_norm": 0.69140625, "learning_rate": 1.4585339073021046e-05, "loss": 0.9748114776611329, "step": 467400 }, { "epoch": 5.383627333447508, "grad_norm": 0.40234375, "learning_rate": 1.4578067509198528e-05, "loss": 0.9690747833251954, "step": 467600 }, { "epoch": 5.385930018522223, "grad_norm": 0.70703125, "learning_rate": 1.4570795945376013e-05, "loss": 0.9754686737060547, "step": 467800 }, { "epoch": 5.388232703596938, "grad_norm": 0.65625, "learning_rate": 1.4563524381553499e-05, "loss": 0.9902306365966796, "step": 468000 }, { "epoch": 5.390535388671653, "grad_norm": 0.6484375, "learning_rate": 1.4556252817730981e-05, "loss": 0.9710675811767578, "step": 468200 }, { "epoch": 5.3928380737463675, "grad_norm": 0.52734375, "learning_rate": 1.4548981253908465e-05, "loss": 0.9841913604736328, "step": 468400 }, { "epoch": 5.395140758821083, "grad_norm": 0.68359375, "learning_rate": 1.4541709690085951e-05, "loss": 0.9748066711425781, "step": 468600 }, { "epoch": 5.397443443895797, "grad_norm": 0.5234375, "learning_rate": 1.4534438126263434e-05, "loss": 0.9825104522705078, "step": 468800 }, { "epoch": 5.399746128970513, "grad_norm": 0.75390625, "learning_rate": 1.452716656244092e-05, "loss": 0.9869859313964844, "step": 469000 }, { "epoch": 5.402048814045227, "grad_norm": 1.3359375, "learning_rate": 1.4519894998618404e-05, "loss": 0.9971955108642578, "step": 469200 }, { "epoch": 5.404351499119943, "grad_norm": 0.71484375, "learning_rate": 1.4512623434795886e-05, "loss": 0.9768145751953125, "step": 469400 }, { "epoch": 5.406654184194657, "grad_norm": 1.0390625, "learning_rate": 1.4505351870973372e-05, "loss": 0.9668540954589844, "step": 469600 }, { "epoch": 5.408956869269373, "grad_norm": 0.91796875, "learning_rate": 1.4498080307150857e-05, "loss": 0.968299560546875, "step": 469800 }, { "epoch": 5.411259554344087, "grad_norm": 0.80078125, "learning_rate": 1.4490808743328339e-05, "loss": 1.008473892211914, "step": 470000 }, { "epoch": 5.413562239418802, "grad_norm": 0.5625, "learning_rate": 1.4483537179505825e-05, "loss": 0.9806656646728515, "step": 470200 }, { "epoch": 5.415864924493517, "grad_norm": 0.5546875, "learning_rate": 1.447626561568331e-05, "loss": 0.9698346710205078, "step": 470400 }, { "epoch": 5.418167609568232, "grad_norm": 0.671875, "learning_rate": 1.4468994051860795e-05, "loss": 0.9919847869873046, "step": 470600 }, { "epoch": 5.420470294642947, "grad_norm": 0.57421875, "learning_rate": 1.4461722488038278e-05, "loss": 0.9748435211181641, "step": 470800 }, { "epoch": 5.422772979717662, "grad_norm": 0.8984375, "learning_rate": 1.4454450924215762e-05, "loss": 0.9667948150634765, "step": 471000 }, { "epoch": 5.425075664792377, "grad_norm": 0.71875, "learning_rate": 1.4447179360393248e-05, "loss": 1.006150360107422, "step": 471200 }, { "epoch": 5.427378349867092, "grad_norm": 0.74609375, "learning_rate": 1.443990779657073e-05, "loss": 0.9815165710449218, "step": 471400 }, { "epoch": 5.429681034941807, "grad_norm": 0.93359375, "learning_rate": 1.4432636232748215e-05, "loss": 0.9920414733886719, "step": 471600 }, { "epoch": 5.431983720016522, "grad_norm": 0.6171875, "learning_rate": 1.44253646689257e-05, "loss": 0.9791954040527344, "step": 471800 }, { "epoch": 5.434286405091237, "grad_norm": 0.765625, "learning_rate": 1.4418093105103183e-05, "loss": 0.9826209259033203, "step": 472000 }, { "epoch": 5.436589090165952, "grad_norm": 0.9765625, "learning_rate": 1.4410821541280669e-05, "loss": 0.9753388214111328, "step": 472200 }, { "epoch": 5.438891775240666, "grad_norm": 0.78125, "learning_rate": 1.4403549977458153e-05, "loss": 0.9879838562011719, "step": 472400 }, { "epoch": 5.441194460315382, "grad_norm": 0.9140625, "learning_rate": 1.4396278413635636e-05, "loss": 0.9852864837646484, "step": 472600 }, { "epoch": 5.443497145390096, "grad_norm": 0.447265625, "learning_rate": 1.4389006849813122e-05, "loss": 0.9750405883789063, "step": 472800 }, { "epoch": 5.445799830464812, "grad_norm": 0.74609375, "learning_rate": 1.4381735285990606e-05, "loss": 0.9863434600830078, "step": 473000 }, { "epoch": 5.448102515539526, "grad_norm": 0.59375, "learning_rate": 1.437446372216809e-05, "loss": 0.9665998077392578, "step": 473200 }, { "epoch": 5.450405200614242, "grad_norm": 0.54296875, "learning_rate": 1.4367192158345574e-05, "loss": 0.9747258758544922, "step": 473400 }, { "epoch": 5.452707885688956, "grad_norm": 0.5, "learning_rate": 1.4359920594523058e-05, "loss": 0.9988768005371094, "step": 473600 }, { "epoch": 5.455010570763671, "grad_norm": 0.74609375, "learning_rate": 1.4352649030700543e-05, "loss": 0.9905022430419922, "step": 473800 }, { "epoch": 5.457313255838386, "grad_norm": 0.56640625, "learning_rate": 1.4345377466878027e-05, "loss": 0.9991416168212891, "step": 474000 }, { "epoch": 5.459615940913101, "grad_norm": 0.640625, "learning_rate": 1.4338105903055511e-05, "loss": 0.9977909851074219, "step": 474200 }, { "epoch": 5.461918625987816, "grad_norm": 0.5546875, "learning_rate": 1.4330834339232997e-05, "loss": 0.9725360107421875, "step": 474400 }, { "epoch": 5.464221311062531, "grad_norm": 0.8125, "learning_rate": 1.432356277541048e-05, "loss": 0.9939174652099609, "step": 474600 }, { "epoch": 5.466523996137246, "grad_norm": 1.0, "learning_rate": 1.4316291211587965e-05, "loss": 0.9697264862060547, "step": 474800 }, { "epoch": 5.468826681211961, "grad_norm": 1.0625, "learning_rate": 1.430901964776545e-05, "loss": 0.9911696624755859, "step": 475000 }, { "epoch": 5.471129366286676, "grad_norm": 0.62890625, "learning_rate": 1.4301748083942932e-05, "loss": 0.9740504455566407, "step": 475200 }, { "epoch": 5.4734320513613905, "grad_norm": 0.88671875, "learning_rate": 1.4294476520120418e-05, "loss": 0.948077163696289, "step": 475400 }, { "epoch": 5.475734736436106, "grad_norm": 0.91015625, "learning_rate": 1.4287204956297902e-05, "loss": 0.9827384185791016, "step": 475600 }, { "epoch": 5.4780374215108205, "grad_norm": 0.796875, "learning_rate": 1.4279933392475385e-05, "loss": 0.9965239715576172, "step": 475800 }, { "epoch": 5.480340106585535, "grad_norm": 0.7578125, "learning_rate": 1.427266182865287e-05, "loss": 0.980682373046875, "step": 476000 }, { "epoch": 5.4826427916602505, "grad_norm": 1.109375, "learning_rate": 1.4265390264830355e-05, "loss": 0.9934986877441406, "step": 476200 }, { "epoch": 5.484945476734965, "grad_norm": 0.71484375, "learning_rate": 1.425811870100784e-05, "loss": 0.979002456665039, "step": 476400 }, { "epoch": 5.4872481618096804, "grad_norm": 0.48828125, "learning_rate": 1.4250847137185323e-05, "loss": 0.9670918273925782, "step": 476600 }, { "epoch": 5.489550846884395, "grad_norm": 1.1640625, "learning_rate": 1.4243575573362808e-05, "loss": 0.9969381713867187, "step": 476800 }, { "epoch": 5.49185353195911, "grad_norm": 0.80078125, "learning_rate": 1.4236304009540292e-05, "loss": 0.9819905090332032, "step": 477000 }, { "epoch": 5.494156217033825, "grad_norm": 0.6953125, "learning_rate": 1.4229032445717776e-05, "loss": 0.9679257202148438, "step": 477200 }, { "epoch": 5.4964589021085395, "grad_norm": 0.859375, "learning_rate": 1.422176088189526e-05, "loss": 0.9745060729980469, "step": 477400 }, { "epoch": 5.498761587183255, "grad_norm": 0.72265625, "learning_rate": 1.4214489318072746e-05, "loss": 0.9809858703613281, "step": 477600 }, { "epoch": 5.5010642722579695, "grad_norm": 0.63671875, "learning_rate": 1.4207217754250229e-05, "loss": 0.9731687927246093, "step": 477800 }, { "epoch": 5.503366957332685, "grad_norm": 0.71484375, "learning_rate": 1.4199946190427715e-05, "loss": 0.9807541656494141, "step": 478000 }, { "epoch": 5.505669642407399, "grad_norm": 0.5859375, "learning_rate": 1.4192674626605199e-05, "loss": 1.0058878326416016, "step": 478200 }, { "epoch": 5.507972327482115, "grad_norm": 0.76953125, "learning_rate": 1.4185403062782681e-05, "loss": 1.0039275360107422, "step": 478400 }, { "epoch": 5.510275012556829, "grad_norm": 0.671875, "learning_rate": 1.4178131498960167e-05, "loss": 0.9918733978271485, "step": 478600 }, { "epoch": 5.512577697631545, "grad_norm": 0.6640625, "learning_rate": 1.4170859935137651e-05, "loss": 0.9834480285644531, "step": 478800 }, { "epoch": 5.514880382706259, "grad_norm": 0.52734375, "learning_rate": 1.4163588371315134e-05, "loss": 1.0038261413574219, "step": 479000 }, { "epoch": 5.517183067780975, "grad_norm": 0.89453125, "learning_rate": 1.415631680749262e-05, "loss": 0.9893887329101563, "step": 479200 }, { "epoch": 5.519485752855689, "grad_norm": 0.89453125, "learning_rate": 1.4149045243670104e-05, "loss": 0.9794209289550782, "step": 479400 }, { "epoch": 5.521788437930404, "grad_norm": 0.388671875, "learning_rate": 1.4141773679847588e-05, "loss": 0.96505126953125, "step": 479600 }, { "epoch": 5.524091123005119, "grad_norm": 1.140625, "learning_rate": 1.4134502116025073e-05, "loss": 0.9843000030517578, "step": 479800 }, { "epoch": 5.526393808079834, "grad_norm": 1.125, "learning_rate": 1.4127230552202557e-05, "loss": 0.9835649871826172, "step": 480000 }, { "epoch": 5.528696493154549, "grad_norm": 0.54296875, "learning_rate": 1.4119958988380041e-05, "loss": 1.0410501098632812, "step": 480200 }, { "epoch": 5.530999178229264, "grad_norm": 0.66796875, "learning_rate": 1.4112687424557525e-05, "loss": 0.9889697265625, "step": 480400 }, { "epoch": 5.533301863303979, "grad_norm": 0.73046875, "learning_rate": 1.4105415860735011e-05, "loss": 0.9981174468994141, "step": 480600 }, { "epoch": 5.535604548378694, "grad_norm": 0.54296875, "learning_rate": 1.4098144296912495e-05, "loss": 0.9815375518798828, "step": 480800 }, { "epoch": 5.537907233453408, "grad_norm": 0.66015625, "learning_rate": 1.4090872733089978e-05, "loss": 0.977080078125, "step": 481000 }, { "epoch": 5.540209918528124, "grad_norm": 0.6640625, "learning_rate": 1.4083601169267464e-05, "loss": 0.9870880126953125, "step": 481200 }, { "epoch": 5.542512603602838, "grad_norm": 0.75390625, "learning_rate": 1.4076329605444948e-05, "loss": 0.9716754150390625, "step": 481400 }, { "epoch": 5.544815288677554, "grad_norm": 0.75, "learning_rate": 1.406905804162243e-05, "loss": 0.986975326538086, "step": 481600 }, { "epoch": 5.547117973752268, "grad_norm": 0.4609375, "learning_rate": 1.4061786477799916e-05, "loss": 0.9707216644287109, "step": 481800 }, { "epoch": 5.549420658826984, "grad_norm": 1.2890625, "learning_rate": 1.40545149139774e-05, "loss": 0.9838639068603515, "step": 482000 }, { "epoch": 5.551723343901698, "grad_norm": 0.330078125, "learning_rate": 1.4047243350154885e-05, "loss": 0.978685302734375, "step": 482200 }, { "epoch": 5.554026028976414, "grad_norm": 0.69140625, "learning_rate": 1.4039971786332369e-05, "loss": 1.0009799957275392, "step": 482400 }, { "epoch": 5.556328714051128, "grad_norm": 0.625, "learning_rate": 1.4032700222509853e-05, "loss": 0.9997296905517579, "step": 482600 }, { "epoch": 5.558631399125844, "grad_norm": 0.8515625, "learning_rate": 1.4025428658687338e-05, "loss": 0.9815716552734375, "step": 482800 }, { "epoch": 5.560934084200558, "grad_norm": 0.5234375, "learning_rate": 1.4018157094864822e-05, "loss": 0.9789281463623047, "step": 483000 }, { "epoch": 5.563236769275273, "grad_norm": 0.5625, "learning_rate": 1.4010885531042306e-05, "loss": 0.9825881958007813, "step": 483200 }, { "epoch": 5.565539454349988, "grad_norm": 0.45703125, "learning_rate": 1.400361396721979e-05, "loss": 0.9777683258056641, "step": 483400 }, { "epoch": 5.567842139424703, "grad_norm": 0.76953125, "learning_rate": 1.3996342403397274e-05, "loss": 0.9617288208007813, "step": 483600 }, { "epoch": 5.570144824499418, "grad_norm": 0.80078125, "learning_rate": 1.398907083957476e-05, "loss": 0.9682086944580078, "step": 483800 }, { "epoch": 5.572447509574133, "grad_norm": 0.78125, "learning_rate": 1.3981799275752243e-05, "loss": 0.9663679504394531, "step": 484000 }, { "epoch": 5.574750194648848, "grad_norm": 0.87890625, "learning_rate": 1.3974527711929727e-05, "loss": 0.9882929992675781, "step": 484200 }, { "epoch": 5.577052879723563, "grad_norm": 0.4453125, "learning_rate": 1.3967256148107213e-05, "loss": 0.9890274810791015, "step": 484400 }, { "epoch": 5.579355564798277, "grad_norm": 0.671875, "learning_rate": 1.3959984584284697e-05, "loss": 0.995350341796875, "step": 484600 }, { "epoch": 5.5816582498729925, "grad_norm": 0.5546875, "learning_rate": 1.395271302046218e-05, "loss": 0.9710835266113281, "step": 484800 }, { "epoch": 5.583960934947708, "grad_norm": 0.6015625, "learning_rate": 1.3945441456639666e-05, "loss": 0.9732130432128906, "step": 485000 }, { "epoch": 5.5862636200224225, "grad_norm": 0.48046875, "learning_rate": 1.393816989281715e-05, "loss": 0.9844066619873046, "step": 485200 }, { "epoch": 5.588566305097137, "grad_norm": 0.65234375, "learning_rate": 1.3930898328994634e-05, "loss": 0.9600486755371094, "step": 485400 }, { "epoch": 5.5908689901718525, "grad_norm": 0.58203125, "learning_rate": 1.3923626765172118e-05, "loss": 0.9797865295410156, "step": 485600 }, { "epoch": 5.593171675246567, "grad_norm": 0.81640625, "learning_rate": 1.3916355201349603e-05, "loss": 0.9919526672363281, "step": 485800 }, { "epoch": 5.595474360321282, "grad_norm": 0.5703125, "learning_rate": 1.3909083637527087e-05, "loss": 0.9721823120117188, "step": 486000 }, { "epoch": 5.597777045395997, "grad_norm": 1.046875, "learning_rate": 1.3901812073704571e-05, "loss": 0.9831861114501953, "step": 486200 }, { "epoch": 5.600079730470712, "grad_norm": 0.78125, "learning_rate": 1.3894540509882055e-05, "loss": 0.9493144226074218, "step": 486400 }, { "epoch": 5.602382415545427, "grad_norm": 0.68359375, "learning_rate": 1.388726894605954e-05, "loss": 0.9714206695556641, "step": 486600 }, { "epoch": 5.6046851006201415, "grad_norm": 0.431640625, "learning_rate": 1.3879997382237024e-05, "loss": 0.9733635711669922, "step": 486800 }, { "epoch": 5.606987785694857, "grad_norm": 0.671875, "learning_rate": 1.387272581841451e-05, "loss": 0.9818306732177734, "step": 487000 }, { "epoch": 5.609290470769571, "grad_norm": 1.453125, "learning_rate": 1.3865454254591992e-05, "loss": 0.9948311614990234, "step": 487200 }, { "epoch": 5.611593155844287, "grad_norm": 0.62890625, "learning_rate": 1.3858182690769476e-05, "loss": 0.9782450866699218, "step": 487400 }, { "epoch": 5.613895840919001, "grad_norm": 0.79296875, "learning_rate": 1.3850911126946962e-05, "loss": 1.0036625671386719, "step": 487600 }, { "epoch": 5.616198525993717, "grad_norm": 0.77734375, "learning_rate": 1.3843639563124446e-05, "loss": 0.9743613433837891, "step": 487800 }, { "epoch": 5.618501211068431, "grad_norm": 0.75, "learning_rate": 1.383636799930193e-05, "loss": 0.9842996978759766, "step": 488000 }, { "epoch": 5.620803896143147, "grad_norm": 0.63671875, "learning_rate": 1.3829096435479415e-05, "loss": 0.9787957000732422, "step": 488200 }, { "epoch": 5.623106581217861, "grad_norm": 0.55078125, "learning_rate": 1.3821824871656899e-05, "loss": 0.9686898040771484, "step": 488400 }, { "epoch": 5.625409266292577, "grad_norm": 0.65625, "learning_rate": 1.3814553307834383e-05, "loss": 0.9968467712402344, "step": 488600 }, { "epoch": 5.627711951367291, "grad_norm": 0.90625, "learning_rate": 1.3807281744011868e-05, "loss": 0.9966775512695313, "step": 488800 }, { "epoch": 5.630014636442006, "grad_norm": 0.71875, "learning_rate": 1.3800010180189352e-05, "loss": 1.007319107055664, "step": 489000 }, { "epoch": 5.632317321516721, "grad_norm": 0.60546875, "learning_rate": 1.3792738616366836e-05, "loss": 1.000706024169922, "step": 489200 }, { "epoch": 5.634620006591436, "grad_norm": 0.84765625, "learning_rate": 1.378546705254432e-05, "loss": 0.9947959899902343, "step": 489400 }, { "epoch": 5.636922691666151, "grad_norm": 0.515625, "learning_rate": 1.3778195488721806e-05, "loss": 0.9884097290039062, "step": 489600 }, { "epoch": 5.639225376740866, "grad_norm": 0.80078125, "learning_rate": 1.3770923924899289e-05, "loss": 0.9712710571289063, "step": 489800 }, { "epoch": 5.641528061815581, "grad_norm": 0.83984375, "learning_rate": 1.3763652361076773e-05, "loss": 0.9973468017578125, "step": 490000 }, { "epoch": 5.643830746890296, "grad_norm": 0.79296875, "learning_rate": 1.3756380797254259e-05, "loss": 0.9909369659423828, "step": 490200 }, { "epoch": 5.64613343196501, "grad_norm": 0.498046875, "learning_rate": 1.3749109233431741e-05, "loss": 0.9876738739013672, "step": 490400 }, { "epoch": 5.648436117039726, "grad_norm": 0.5234375, "learning_rate": 1.3741837669609226e-05, "loss": 0.999638671875, "step": 490600 }, { "epoch": 5.65073880211444, "grad_norm": 1.015625, "learning_rate": 1.3734566105786711e-05, "loss": 0.9692737579345703, "step": 490800 }, { "epoch": 5.653041487189156, "grad_norm": 0.59375, "learning_rate": 1.3727294541964196e-05, "loss": 0.9833884429931641, "step": 491000 }, { "epoch": 5.65534417226387, "grad_norm": 0.8125, "learning_rate": 1.372002297814168e-05, "loss": 1.0041567230224608, "step": 491200 }, { "epoch": 5.657646857338586, "grad_norm": 0.49609375, "learning_rate": 1.3712751414319164e-05, "loss": 0.9968643951416015, "step": 491400 }, { "epoch": 5.6599495424133, "grad_norm": 0.6015625, "learning_rate": 1.3705479850496648e-05, "loss": 0.9939844512939453, "step": 491600 }, { "epoch": 5.662252227488016, "grad_norm": 0.50390625, "learning_rate": 1.3698208286674133e-05, "loss": 0.9795943450927734, "step": 491800 }, { "epoch": 5.66455491256273, "grad_norm": 1.09375, "learning_rate": 1.3690936722851617e-05, "loss": 0.9953731536865235, "step": 492000 }, { "epoch": 5.666857597637446, "grad_norm": 1.0546875, "learning_rate": 1.3683665159029101e-05, "loss": 0.9865888214111328, "step": 492200 }, { "epoch": 5.66916028271216, "grad_norm": 0.66015625, "learning_rate": 1.3676393595206585e-05, "loss": 0.9924819946289063, "step": 492400 }, { "epoch": 5.671462967786875, "grad_norm": 0.66796875, "learning_rate": 1.366912203138407e-05, "loss": 0.99431396484375, "step": 492600 }, { "epoch": 5.67376565286159, "grad_norm": 0.77734375, "learning_rate": 1.3661850467561555e-05, "loss": 0.9882295989990234, "step": 492800 }, { "epoch": 5.676068337936305, "grad_norm": 1.0859375, "learning_rate": 1.3654578903739038e-05, "loss": 0.9925931549072265, "step": 493000 }, { "epoch": 5.67837102301102, "grad_norm": 1.0625, "learning_rate": 1.3647307339916522e-05, "loss": 0.98350830078125, "step": 493200 }, { "epoch": 5.680673708085735, "grad_norm": 0.419921875, "learning_rate": 1.3640035776094008e-05, "loss": 0.9921775054931641, "step": 493400 }, { "epoch": 5.68297639316045, "grad_norm": 0.5703125, "learning_rate": 1.363276421227149e-05, "loss": 0.9786495971679687, "step": 493600 }, { "epoch": 5.6852790782351645, "grad_norm": 0.8828125, "learning_rate": 1.3625492648448976e-05, "loss": 0.9776170349121094, "step": 493800 }, { "epoch": 5.687581763309879, "grad_norm": 1.0, "learning_rate": 1.361822108462646e-05, "loss": 0.9838382720947265, "step": 494000 }, { "epoch": 5.6898844483845945, "grad_norm": 0.98046875, "learning_rate": 1.3610949520803943e-05, "loss": 0.9766007995605469, "step": 494200 }, { "epoch": 5.692187133459309, "grad_norm": 0.6484375, "learning_rate": 1.3603677956981429e-05, "loss": 0.9869244384765625, "step": 494400 }, { "epoch": 5.6944898185340245, "grad_norm": 0.57421875, "learning_rate": 1.3596406393158913e-05, "loss": 0.9463243865966797, "step": 494600 }, { "epoch": 5.696792503608739, "grad_norm": 0.7265625, "learning_rate": 1.3589134829336398e-05, "loss": 0.9932901000976563, "step": 494800 }, { "epoch": 5.699095188683454, "grad_norm": 0.86328125, "learning_rate": 1.3581863265513882e-05, "loss": 0.9636652374267578, "step": 495000 }, { "epoch": 5.701397873758169, "grad_norm": 0.8671875, "learning_rate": 1.3574591701691366e-05, "loss": 0.9758798217773438, "step": 495200 }, { "epoch": 5.703700558832884, "grad_norm": 0.419921875, "learning_rate": 1.3567320137868852e-05, "loss": 0.968555679321289, "step": 495400 }, { "epoch": 5.706003243907599, "grad_norm": 0.984375, "learning_rate": 1.3560048574046334e-05, "loss": 0.9713514709472656, "step": 495600 }, { "epoch": 5.708305928982314, "grad_norm": 0.60546875, "learning_rate": 1.3552777010223819e-05, "loss": 0.9624390411376953, "step": 495800 }, { "epoch": 5.710608614057029, "grad_norm": 0.828125, "learning_rate": 1.3545505446401305e-05, "loss": 0.9755973052978516, "step": 496000 }, { "epoch": 5.7129112991317434, "grad_norm": 0.6953125, "learning_rate": 1.3538233882578787e-05, "loss": 1.0029659271240234, "step": 496200 }, { "epoch": 5.715213984206459, "grad_norm": 0.8515625, "learning_rate": 1.3530962318756271e-05, "loss": 0.958271484375, "step": 496400 }, { "epoch": 5.717516669281173, "grad_norm": 0.423828125, "learning_rate": 1.3523690754933757e-05, "loss": 1.0108000183105468, "step": 496600 }, { "epoch": 5.719819354355889, "grad_norm": 0.73046875, "learning_rate": 1.351641919111124e-05, "loss": 0.9738809204101563, "step": 496800 }, { "epoch": 5.722122039430603, "grad_norm": 0.6875, "learning_rate": 1.3509147627288726e-05, "loss": 0.99912109375, "step": 497000 }, { "epoch": 5.724424724505319, "grad_norm": 0.494140625, "learning_rate": 1.350187606346621e-05, "loss": 0.99430419921875, "step": 497200 }, { "epoch": 5.726727409580033, "grad_norm": 0.486328125, "learning_rate": 1.3494604499643692e-05, "loss": 0.973975601196289, "step": 497400 }, { "epoch": 5.729030094654748, "grad_norm": 1.140625, "learning_rate": 1.3487332935821178e-05, "loss": 0.9921266937255859, "step": 497600 }, { "epoch": 5.731332779729463, "grad_norm": 0.8046875, "learning_rate": 1.3480061371998663e-05, "loss": 0.9895915222167969, "step": 497800 }, { "epoch": 5.733635464804178, "grad_norm": 0.69140625, "learning_rate": 1.3472789808176147e-05, "loss": 0.9898014831542968, "step": 498000 }, { "epoch": 5.735938149878893, "grad_norm": 0.90625, "learning_rate": 1.3465518244353631e-05, "loss": 0.9841976928710937, "step": 498200 }, { "epoch": 5.738240834953608, "grad_norm": 0.458984375, "learning_rate": 1.3458246680531115e-05, "loss": 0.9864323425292969, "step": 498400 }, { "epoch": 5.740543520028323, "grad_norm": 0.54296875, "learning_rate": 1.3450975116708601e-05, "loss": 0.9855081939697266, "step": 498600 }, { "epoch": 5.742846205103038, "grad_norm": 1.0625, "learning_rate": 1.3443703552886084e-05, "loss": 0.977813720703125, "step": 498800 }, { "epoch": 5.745148890177753, "grad_norm": 0.58984375, "learning_rate": 1.3436431989063568e-05, "loss": 1.0014332580566405, "step": 499000 }, { "epoch": 5.747451575252468, "grad_norm": 0.51171875, "learning_rate": 1.3429160425241054e-05, "loss": 0.9798948669433594, "step": 499200 }, { "epoch": 5.749754260327183, "grad_norm": 0.75390625, "learning_rate": 1.3421888861418536e-05, "loss": 0.9854695129394532, "step": 499400 }, { "epoch": 5.752056945401898, "grad_norm": 0.5703125, "learning_rate": 1.341461729759602e-05, "loss": 0.9640402221679687, "step": 499600 }, { "epoch": 5.754359630476612, "grad_norm": 0.62109375, "learning_rate": 1.3407345733773506e-05, "loss": 0.9828694915771484, "step": 499800 }, { "epoch": 5.756662315551328, "grad_norm": 0.60546875, "learning_rate": 1.3400074169950989e-05, "loss": 0.9606679534912109, "step": 500000 }, { "epoch": 5.758965000626042, "grad_norm": 0.8984375, "learning_rate": 1.3392802606128475e-05, "loss": 0.9945602416992188, "step": 500200 }, { "epoch": 5.761267685700758, "grad_norm": 0.7109375, "learning_rate": 1.3385531042305959e-05, "loss": 1.0002516937255859, "step": 500400 }, { "epoch": 5.763570370775472, "grad_norm": 0.99609375, "learning_rate": 1.3378259478483442e-05, "loss": 1.0048902893066407, "step": 500600 }, { "epoch": 5.765873055850188, "grad_norm": 0.6953125, "learning_rate": 1.3370987914660927e-05, "loss": 0.978136215209961, "step": 500800 }, { "epoch": 5.768175740924902, "grad_norm": 0.64453125, "learning_rate": 1.3363716350838412e-05, "loss": 0.9923693084716797, "step": 501000 }, { "epoch": 5.770478425999617, "grad_norm": 0.578125, "learning_rate": 1.3356444787015898e-05, "loss": 0.970635757446289, "step": 501200 }, { "epoch": 5.772781111074332, "grad_norm": 0.5078125, "learning_rate": 1.334917322319338e-05, "loss": 0.9800533294677735, "step": 501400 }, { "epoch": 5.7750837961490475, "grad_norm": 1.9296875, "learning_rate": 1.3341901659370864e-05, "loss": 1.0008333587646485, "step": 501600 }, { "epoch": 5.777386481223762, "grad_norm": 0.68359375, "learning_rate": 1.333463009554835e-05, "loss": 0.9850815582275391, "step": 501800 }, { "epoch": 5.779689166298477, "grad_norm": 0.77734375, "learning_rate": 1.3327358531725833e-05, "loss": 0.96795166015625, "step": 502000 }, { "epoch": 5.781991851373192, "grad_norm": 1.5703125, "learning_rate": 1.3320086967903317e-05, "loss": 0.9840054321289062, "step": 502200 }, { "epoch": 5.784294536447907, "grad_norm": 0.8671875, "learning_rate": 1.3312815404080803e-05, "loss": 0.9985717010498046, "step": 502400 }, { "epoch": 5.786597221522622, "grad_norm": 0.7109375, "learning_rate": 1.3305543840258285e-05, "loss": 0.9868987274169921, "step": 502600 }, { "epoch": 5.7888999065973366, "grad_norm": 0.64453125, "learning_rate": 1.3298272276435771e-05, "loss": 0.9638268280029297, "step": 502800 }, { "epoch": 5.791202591672052, "grad_norm": 0.7109375, "learning_rate": 1.3291000712613256e-05, "loss": 0.9871996307373047, "step": 503000 }, { "epoch": 5.7935052767467665, "grad_norm": 0.671875, "learning_rate": 1.3283729148790738e-05, "loss": 0.982093276977539, "step": 503200 }, { "epoch": 5.795807961821481, "grad_norm": 1.0078125, "learning_rate": 1.3276457584968224e-05, "loss": 0.9666788482666016, "step": 503400 }, { "epoch": 5.7981106468961965, "grad_norm": 0.80078125, "learning_rate": 1.3269186021145708e-05, "loss": 0.9756722259521484, "step": 503600 }, { "epoch": 5.800413331970911, "grad_norm": 0.6953125, "learning_rate": 1.326191445732319e-05, "loss": 0.9657235717773438, "step": 503800 }, { "epoch": 5.8027160170456265, "grad_norm": 0.69140625, "learning_rate": 1.3254642893500677e-05, "loss": 0.9707088470458984, "step": 504000 }, { "epoch": 5.805018702120341, "grad_norm": 0.6953125, "learning_rate": 1.3247371329678161e-05, "loss": 0.9648799133300782, "step": 504200 }, { "epoch": 5.807321387195056, "grad_norm": 0.458984375, "learning_rate": 1.3240099765855647e-05, "loss": 0.9958235168457031, "step": 504400 }, { "epoch": 5.809624072269771, "grad_norm": 1.1640625, "learning_rate": 1.323282820203313e-05, "loss": 0.9823985290527344, "step": 504600 }, { "epoch": 5.811926757344486, "grad_norm": 1.4140625, "learning_rate": 1.3225556638210614e-05, "loss": 0.9838928985595703, "step": 504800 }, { "epoch": 5.814229442419201, "grad_norm": 0.8203125, "learning_rate": 1.32182850743881e-05, "loss": 0.9789728546142578, "step": 505000 }, { "epoch": 5.816532127493916, "grad_norm": 0.546875, "learning_rate": 1.3211013510565582e-05, "loss": 0.9647856140136719, "step": 505200 }, { "epoch": 5.818834812568631, "grad_norm": 0.5859375, "learning_rate": 1.3203741946743066e-05, "loss": 0.9774513244628906, "step": 505400 }, { "epoch": 5.821137497643345, "grad_norm": 0.77734375, "learning_rate": 1.3196470382920552e-05, "loss": 0.9803495788574219, "step": 505600 }, { "epoch": 5.823440182718061, "grad_norm": 0.51171875, "learning_rate": 1.3189198819098035e-05, "loss": 0.9838663482666016, "step": 505800 }, { "epoch": 5.825742867792775, "grad_norm": 0.62109375, "learning_rate": 1.318192725527552e-05, "loss": 0.9702992248535156, "step": 506000 }, { "epoch": 5.828045552867491, "grad_norm": 1.0703125, "learning_rate": 1.3174655691453005e-05, "loss": 0.9721846771240235, "step": 506200 }, { "epoch": 5.830348237942205, "grad_norm": 0.77734375, "learning_rate": 1.3167384127630487e-05, "loss": 0.9824070739746094, "step": 506400 }, { "epoch": 5.832650923016921, "grad_norm": 1.0, "learning_rate": 1.3160112563807973e-05, "loss": 0.9909092712402344, "step": 506600 }, { "epoch": 5.834953608091635, "grad_norm": 0.6953125, "learning_rate": 1.3152840999985457e-05, "loss": 0.981254653930664, "step": 506800 }, { "epoch": 5.83725629316635, "grad_norm": 1.0546875, "learning_rate": 1.314556943616294e-05, "loss": 0.9601033782958984, "step": 507000 }, { "epoch": 5.839558978241065, "grad_norm": 0.69140625, "learning_rate": 1.3138297872340426e-05, "loss": 0.9732923126220703, "step": 507200 }, { "epoch": 5.84186166331578, "grad_norm": 0.98046875, "learning_rate": 1.313102630851791e-05, "loss": 0.9881997680664063, "step": 507400 }, { "epoch": 5.844164348390495, "grad_norm": 0.59765625, "learning_rate": 1.3123754744695394e-05, "loss": 0.9774773406982422, "step": 507600 }, { "epoch": 5.84646703346521, "grad_norm": 0.5546875, "learning_rate": 1.3116483180872879e-05, "loss": 0.9892032623291016, "step": 507800 }, { "epoch": 5.848769718539925, "grad_norm": 0.76171875, "learning_rate": 1.3109211617050363e-05, "loss": 0.9897892761230469, "step": 508000 }, { "epoch": 5.85107240361464, "grad_norm": 0.625, "learning_rate": 1.3101940053227849e-05, "loss": 0.9681523132324219, "step": 508200 }, { "epoch": 5.853375088689355, "grad_norm": 0.5234375, "learning_rate": 1.3094668489405331e-05, "loss": 0.966031494140625, "step": 508400 }, { "epoch": 5.85567777376407, "grad_norm": 0.625, "learning_rate": 1.3087396925582817e-05, "loss": 0.9670277404785156, "step": 508600 }, { "epoch": 5.857980458838785, "grad_norm": 0.59375, "learning_rate": 1.3080125361760301e-05, "loss": 0.9803645324707031, "step": 508800 }, { "epoch": 5.8602831439135, "grad_norm": 0.71484375, "learning_rate": 1.3072853797937784e-05, "loss": 0.9849859619140625, "step": 509000 }, { "epoch": 5.862585828988214, "grad_norm": 0.59765625, "learning_rate": 1.306558223411527e-05, "loss": 0.9650568389892578, "step": 509200 }, { "epoch": 5.86488851406293, "grad_norm": 0.90234375, "learning_rate": 1.3058310670292754e-05, "loss": 0.9649927520751953, "step": 509400 }, { "epoch": 5.867191199137644, "grad_norm": 0.83203125, "learning_rate": 1.3051039106470237e-05, "loss": 1.0007953643798828, "step": 509600 }, { "epoch": 5.86949388421236, "grad_norm": 0.80859375, "learning_rate": 1.3043767542647722e-05, "loss": 0.9851982879638672, "step": 509800 }, { "epoch": 5.871796569287074, "grad_norm": 0.6484375, "learning_rate": 1.3036495978825207e-05, "loss": 0.982063980102539, "step": 510000 }, { "epoch": 5.87409925436179, "grad_norm": 0.73046875, "learning_rate": 1.3029224415002691e-05, "loss": 0.9685086822509765, "step": 510200 }, { "epoch": 5.876401939436504, "grad_norm": 0.80859375, "learning_rate": 1.3021952851180175e-05, "loss": 0.9721865844726563, "step": 510400 }, { "epoch": 5.878704624511219, "grad_norm": 1.109375, "learning_rate": 1.301468128735766e-05, "loss": 0.985322265625, "step": 510600 }, { "epoch": 5.881007309585934, "grad_norm": 0.58984375, "learning_rate": 1.3007409723535144e-05, "loss": 0.9845337677001953, "step": 510800 }, { "epoch": 5.883309994660649, "grad_norm": 0.47265625, "learning_rate": 1.3000138159712628e-05, "loss": 0.9656434631347657, "step": 511000 }, { "epoch": 5.885612679735364, "grad_norm": 1.2109375, "learning_rate": 1.2992866595890112e-05, "loss": 0.9908671569824219, "step": 511200 }, { "epoch": 5.887915364810079, "grad_norm": 0.67578125, "learning_rate": 1.2985595032067598e-05, "loss": 0.9956317901611328, "step": 511400 }, { "epoch": 5.890218049884794, "grad_norm": 0.64453125, "learning_rate": 1.297832346824508e-05, "loss": 0.9613990783691406, "step": 511600 }, { "epoch": 5.892520734959509, "grad_norm": 1.078125, "learning_rate": 1.2971051904422566e-05, "loss": 0.988326416015625, "step": 511800 }, { "epoch": 5.894823420034224, "grad_norm": 0.71484375, "learning_rate": 1.296378034060005e-05, "loss": 0.9974417877197266, "step": 512000 }, { "epoch": 5.8971261051089385, "grad_norm": 0.458984375, "learning_rate": 1.2956508776777533e-05, "loss": 0.9984935760498047, "step": 512200 }, { "epoch": 5.899428790183654, "grad_norm": 0.462890625, "learning_rate": 1.2949237212955019e-05, "loss": 0.9851997375488282, "step": 512400 }, { "epoch": 5.9017314752583685, "grad_norm": 0.53125, "learning_rate": 1.2941965649132503e-05, "loss": 0.9762357330322265, "step": 512600 }, { "epoch": 5.904034160333083, "grad_norm": 1.03125, "learning_rate": 1.2934694085309986e-05, "loss": 0.9988518524169921, "step": 512800 }, { "epoch": 5.9063368454077985, "grad_norm": 0.65625, "learning_rate": 1.2927422521487472e-05, "loss": 0.9867639923095703, "step": 513000 }, { "epoch": 5.908639530482513, "grad_norm": 0.78125, "learning_rate": 1.2920150957664956e-05, "loss": 0.9704194641113282, "step": 513200 }, { "epoch": 5.910942215557228, "grad_norm": 0.671875, "learning_rate": 1.291287939384244e-05, "loss": 0.967171630859375, "step": 513400 }, { "epoch": 5.913244900631943, "grad_norm": 1.015625, "learning_rate": 1.2905607830019924e-05, "loss": 0.9707279968261718, "step": 513600 }, { "epoch": 5.915547585706658, "grad_norm": 0.60546875, "learning_rate": 1.2898336266197409e-05, "loss": 0.9839116668701172, "step": 513800 }, { "epoch": 5.917850270781373, "grad_norm": 0.6953125, "learning_rate": 1.2891064702374893e-05, "loss": 0.9717050933837891, "step": 514000 }, { "epoch": 5.9201529558560875, "grad_norm": 1.0234375, "learning_rate": 1.2883793138552377e-05, "loss": 1.015107421875, "step": 514200 }, { "epoch": 5.922455640930803, "grad_norm": 0.84375, "learning_rate": 1.2876521574729861e-05, "loss": 0.9687767028808594, "step": 514400 }, { "epoch": 5.924758326005517, "grad_norm": 0.47265625, "learning_rate": 1.2869250010907347e-05, "loss": 1.0059048461914062, "step": 514600 }, { "epoch": 5.927061011080233, "grad_norm": 0.73046875, "learning_rate": 1.286197844708483e-05, "loss": 0.9638690948486328, "step": 514800 }, { "epoch": 5.929363696154947, "grad_norm": 1.5390625, "learning_rate": 1.2854706883262316e-05, "loss": 0.9991024780273438, "step": 515000 }, { "epoch": 5.931666381229663, "grad_norm": 0.3828125, "learning_rate": 1.28474353194398e-05, "loss": 0.9884070587158204, "step": 515200 }, { "epoch": 5.933969066304377, "grad_norm": 0.73828125, "learning_rate": 1.2840163755617282e-05, "loss": 0.9854502868652344, "step": 515400 }, { "epoch": 5.936271751379093, "grad_norm": 0.65234375, "learning_rate": 1.2832892191794768e-05, "loss": 1.0004030609130858, "step": 515600 }, { "epoch": 5.938574436453807, "grad_norm": 0.478515625, "learning_rate": 1.2825620627972252e-05, "loss": 0.9818889617919921, "step": 515800 }, { "epoch": 5.940877121528523, "grad_norm": 1.1640625, "learning_rate": 1.2818349064149737e-05, "loss": 0.9734959411621094, "step": 516000 }, { "epoch": 5.943179806603237, "grad_norm": 0.48046875, "learning_rate": 1.2811077500327221e-05, "loss": 0.9703239440917969, "step": 516200 }, { "epoch": 5.945482491677952, "grad_norm": 1.0234375, "learning_rate": 1.2803805936504705e-05, "loss": 0.9912371063232421, "step": 516400 }, { "epoch": 5.947785176752667, "grad_norm": 0.67578125, "learning_rate": 1.279653437268219e-05, "loss": 0.9781558227539062, "step": 516600 }, { "epoch": 5.950087861827382, "grad_norm": 0.625, "learning_rate": 1.2789262808859674e-05, "loss": 0.9869168090820313, "step": 516800 }, { "epoch": 5.952390546902097, "grad_norm": 0.7109375, "learning_rate": 1.2781991245037158e-05, "loss": 0.9716383361816406, "step": 517000 }, { "epoch": 5.954693231976812, "grad_norm": 0.76171875, "learning_rate": 1.2774719681214642e-05, "loss": 0.9640602111816406, "step": 517200 }, { "epoch": 5.956995917051527, "grad_norm": 0.625, "learning_rate": 1.2767448117392126e-05, "loss": 0.9790910339355469, "step": 517400 }, { "epoch": 5.959298602126242, "grad_norm": 0.703125, "learning_rate": 1.2760176553569612e-05, "loss": 0.9806784057617187, "step": 517600 }, { "epoch": 5.961601287200956, "grad_norm": 0.703125, "learning_rate": 1.2752904989747095e-05, "loss": 0.984098892211914, "step": 517800 }, { "epoch": 5.963903972275672, "grad_norm": 0.7734375, "learning_rate": 1.2745633425924579e-05, "loss": 0.9858362579345703, "step": 518000 }, { "epoch": 5.966206657350387, "grad_norm": 0.490234375, "learning_rate": 1.2738361862102065e-05, "loss": 0.9572196960449219, "step": 518200 }, { "epoch": 5.968509342425102, "grad_norm": 0.68359375, "learning_rate": 1.2731090298279549e-05, "loss": 0.9759970092773438, "step": 518400 }, { "epoch": 5.970812027499816, "grad_norm": 0.57421875, "learning_rate": 1.2723818734457031e-05, "loss": 0.9888639831542969, "step": 518600 }, { "epoch": 5.973114712574532, "grad_norm": 0.72265625, "learning_rate": 1.2716547170634517e-05, "loss": 0.9922422790527343, "step": 518800 }, { "epoch": 5.975417397649246, "grad_norm": 0.51953125, "learning_rate": 1.2709275606812002e-05, "loss": 0.9752543640136718, "step": 519000 }, { "epoch": 5.977720082723962, "grad_norm": 0.99609375, "learning_rate": 1.2702004042989486e-05, "loss": 0.9682593536376953, "step": 519200 }, { "epoch": 5.980022767798676, "grad_norm": 0.515625, "learning_rate": 1.269473247916697e-05, "loss": 1.0047833251953124, "step": 519400 }, { "epoch": 5.982325452873392, "grad_norm": 0.578125, "learning_rate": 1.2687460915344454e-05, "loss": 0.9858283996582031, "step": 519600 }, { "epoch": 5.984628137948106, "grad_norm": 0.64453125, "learning_rate": 1.2680189351521938e-05, "loss": 0.9966690826416016, "step": 519800 }, { "epoch": 5.986930823022821, "grad_norm": 0.5234375, "learning_rate": 1.2672917787699423e-05, "loss": 0.9701039123535157, "step": 520000 }, { "epoch": 5.989233508097536, "grad_norm": 1.0234375, "learning_rate": 1.2665646223876907e-05, "loss": 0.9833212280273438, "step": 520200 }, { "epoch": 5.991536193172251, "grad_norm": 0.89453125, "learning_rate": 1.2658374660054391e-05, "loss": 0.9889899444580078, "step": 520400 }, { "epoch": 5.993838878246966, "grad_norm": 0.5703125, "learning_rate": 1.2651103096231875e-05, "loss": 0.9911026000976563, "step": 520600 }, { "epoch": 5.996141563321681, "grad_norm": 0.453125, "learning_rate": 1.2643831532409361e-05, "loss": 0.9813486480712891, "step": 520800 }, { "epoch": 5.998444248396396, "grad_norm": 0.8203125, "learning_rate": 1.2636559968586844e-05, "loss": 0.9834247589111328, "step": 521000 }, { "epoch": 6.0, "eval_loss": NaN, "eval_runtime": 429.1974, "eval_samples_per_second": 66.079, "eval_steps_per_second": 33.041, "step": 521136 }, { "epoch": 6.000736859223909, "grad_norm": 0.8359375, "learning_rate": 1.2629288404764328e-05, "loss": 0.9674974060058594, "step": 521200 }, { "epoch": 6.003039544298623, "grad_norm": 0.64453125, "learning_rate": 1.2622016840941814e-05, "loss": 0.9826670837402344, "step": 521400 }, { "epoch": 6.005342229373339, "grad_norm": 0.546875, "learning_rate": 1.2614745277119298e-05, "loss": 0.9674659729003906, "step": 521600 }, { "epoch": 6.007644914448053, "grad_norm": 0.671875, "learning_rate": 1.2607473713296782e-05, "loss": 0.9796168518066406, "step": 521800 }, { "epoch": 6.009947599522769, "grad_norm": 0.5234375, "learning_rate": 1.2600202149474267e-05, "loss": 0.9959929656982421, "step": 522000 }, { "epoch": 6.012250284597483, "grad_norm": 0.5859375, "learning_rate": 1.259293058565175e-05, "loss": 0.9869330596923828, "step": 522200 }, { "epoch": 6.014552969672199, "grad_norm": 1.3984375, "learning_rate": 1.2585659021829235e-05, "loss": 0.9866191101074219, "step": 522400 }, { "epoch": 6.016855654746913, "grad_norm": 0.5234375, "learning_rate": 1.257838745800672e-05, "loss": 0.9863572692871094, "step": 522600 }, { "epoch": 6.019158339821629, "grad_norm": 0.5546875, "learning_rate": 1.2571115894184203e-05, "loss": 0.9905815887451171, "step": 522800 }, { "epoch": 6.021461024896343, "grad_norm": 1.2578125, "learning_rate": 1.2563844330361688e-05, "loss": 0.9822950744628907, "step": 523000 }, { "epoch": 6.023763709971058, "grad_norm": 0.52734375, "learning_rate": 1.2556572766539172e-05, "loss": 0.9872956085205078, "step": 523200 }, { "epoch": 6.026066395045773, "grad_norm": 0.88671875, "learning_rate": 1.2549301202716658e-05, "loss": 0.9910843658447266, "step": 523400 }, { "epoch": 6.028369080120488, "grad_norm": 0.62109375, "learning_rate": 1.254202963889414e-05, "loss": 1.0010240173339844, "step": 523600 }, { "epoch": 6.030671765195203, "grad_norm": 0.45703125, "learning_rate": 1.2534758075071625e-05, "loss": 0.9774690246582032, "step": 523800 }, { "epoch": 6.032974450269918, "grad_norm": 0.95703125, "learning_rate": 1.252748651124911e-05, "loss": 0.9842904663085937, "step": 524000 }, { "epoch": 6.035277135344633, "grad_norm": 0.71484375, "learning_rate": 1.2520214947426593e-05, "loss": 0.98850830078125, "step": 524200 }, { "epoch": 6.037579820419348, "grad_norm": 0.404296875, "learning_rate": 1.2512943383604077e-05, "loss": 0.9948532867431641, "step": 524400 }, { "epoch": 6.039882505494063, "grad_norm": 0.6171875, "learning_rate": 1.2505671819781563e-05, "loss": 0.9795927429199218, "step": 524600 }, { "epoch": 6.042185190568778, "grad_norm": 0.51953125, "learning_rate": 1.2498400255959047e-05, "loss": 0.9803174591064453, "step": 524800 }, { "epoch": 6.044487875643492, "grad_norm": 0.68359375, "learning_rate": 1.2491128692136532e-05, "loss": 0.9761277770996094, "step": 525000 }, { "epoch": 6.0467905607182075, "grad_norm": 1.703125, "learning_rate": 1.2483857128314016e-05, "loss": 0.9698514556884765, "step": 525200 }, { "epoch": 6.049093245792922, "grad_norm": 1.0390625, "learning_rate": 1.24765855644915e-05, "loss": 0.9775434875488281, "step": 525400 }, { "epoch": 6.0513959308676375, "grad_norm": 1.0234375, "learning_rate": 1.2469314000668984e-05, "loss": 0.9901437377929687, "step": 525600 }, { "epoch": 6.053698615942352, "grad_norm": 0.8359375, "learning_rate": 1.2462042436846468e-05, "loss": 0.993725814819336, "step": 525800 }, { "epoch": 6.0560013010170675, "grad_norm": 0.7265625, "learning_rate": 1.2454770873023953e-05, "loss": 0.9937523651123047, "step": 526000 }, { "epoch": 6.058303986091782, "grad_norm": 0.5703125, "learning_rate": 1.2447499309201437e-05, "loss": 0.9665583038330078, "step": 526200 }, { "epoch": 6.060606671166497, "grad_norm": 1.140625, "learning_rate": 1.2440227745378921e-05, "loss": 0.9925328063964843, "step": 526400 }, { "epoch": 6.062909356241212, "grad_norm": 0.59375, "learning_rate": 1.2432956181556407e-05, "loss": 0.9762063598632813, "step": 526600 }, { "epoch": 6.065212041315927, "grad_norm": 0.69140625, "learning_rate": 1.242568461773389e-05, "loss": 0.9671697998046875, "step": 526800 }, { "epoch": 6.067514726390642, "grad_norm": 0.51953125, "learning_rate": 1.2418413053911374e-05, "loss": 0.9953849792480469, "step": 527000 }, { "epoch": 6.0698174114653565, "grad_norm": 0.59375, "learning_rate": 1.241114149008886e-05, "loss": 0.9750828552246094, "step": 527200 }, { "epoch": 6.072120096540072, "grad_norm": 0.625, "learning_rate": 1.2403869926266342e-05, "loss": 0.9784751129150391, "step": 527400 }, { "epoch": 6.074422781614786, "grad_norm": 0.8671875, "learning_rate": 1.2396598362443826e-05, "loss": 0.99782958984375, "step": 527600 }, { "epoch": 6.076725466689502, "grad_norm": 0.8359375, "learning_rate": 1.2389326798621312e-05, "loss": 0.9635990142822266, "step": 527800 }, { "epoch": 6.079028151764216, "grad_norm": 0.451171875, "learning_rate": 1.2382055234798797e-05, "loss": 0.9723565673828125, "step": 528000 }, { "epoch": 6.081330836838932, "grad_norm": 0.62890625, "learning_rate": 1.237478367097628e-05, "loss": 0.9830453491210938, "step": 528200 }, { "epoch": 6.083633521913646, "grad_norm": 0.9375, "learning_rate": 1.2367512107153765e-05, "loss": 0.9581756591796875, "step": 528400 }, { "epoch": 6.085936206988362, "grad_norm": 0.96484375, "learning_rate": 1.236024054333125e-05, "loss": 0.9884815216064453, "step": 528600 }, { "epoch": 6.088238892063076, "grad_norm": 0.70703125, "learning_rate": 1.2352968979508733e-05, "loss": 0.9800252532958984, "step": 528800 }, { "epoch": 6.090541577137791, "grad_norm": 1.1640625, "learning_rate": 1.2345697415686218e-05, "loss": 0.9709556579589844, "step": 529000 }, { "epoch": 6.092844262212506, "grad_norm": 0.5390625, "learning_rate": 1.2338425851863704e-05, "loss": 1.0069298553466797, "step": 529200 }, { "epoch": 6.095146947287221, "grad_norm": 0.75, "learning_rate": 1.2331154288041186e-05, "loss": 0.9980406951904297, "step": 529400 }, { "epoch": 6.097449632361936, "grad_norm": 0.62109375, "learning_rate": 1.232388272421867e-05, "loss": 0.9931936645507813, "step": 529600 }, { "epoch": 6.099752317436651, "grad_norm": 0.68359375, "learning_rate": 1.2316611160396156e-05, "loss": 0.9748165130615234, "step": 529800 }, { "epoch": 6.102055002511366, "grad_norm": 0.91015625, "learning_rate": 1.2309339596573639e-05, "loss": 0.98735107421875, "step": 530000 }, { "epoch": 6.104357687586081, "grad_norm": 0.734375, "learning_rate": 1.2302068032751123e-05, "loss": 0.976137924194336, "step": 530200 }, { "epoch": 6.106660372660796, "grad_norm": 0.76171875, "learning_rate": 1.2294796468928609e-05, "loss": 0.9755792236328125, "step": 530400 }, { "epoch": 6.108963057735511, "grad_norm": 0.5546875, "learning_rate": 1.2287524905106091e-05, "loss": 0.9658280181884765, "step": 530600 }, { "epoch": 6.111265742810225, "grad_norm": 0.6328125, "learning_rate": 1.2280253341283577e-05, "loss": 0.954208984375, "step": 530800 }, { "epoch": 6.113568427884941, "grad_norm": 0.7265625, "learning_rate": 1.2272981777461062e-05, "loss": 0.9845800018310547, "step": 531000 }, { "epoch": 6.115871112959655, "grad_norm": 1.0546875, "learning_rate": 1.2265710213638544e-05, "loss": 0.9828291320800782, "step": 531200 }, { "epoch": 6.118173798034371, "grad_norm": 0.38671875, "learning_rate": 1.225843864981603e-05, "loss": 0.9656654357910156, "step": 531400 }, { "epoch": 6.120476483109085, "grad_norm": 0.84375, "learning_rate": 1.2251167085993514e-05, "loss": 0.9733367156982422, "step": 531600 }, { "epoch": 6.122779168183801, "grad_norm": 0.7109375, "learning_rate": 1.2243895522170998e-05, "loss": 0.9854462432861328, "step": 531800 }, { "epoch": 6.125081853258515, "grad_norm": 0.671875, "learning_rate": 1.2236623958348483e-05, "loss": 0.9575458526611328, "step": 532000 }, { "epoch": 6.127384538333231, "grad_norm": 0.578125, "learning_rate": 1.2229352394525967e-05, "loss": 0.9649818420410157, "step": 532200 }, { "epoch": 6.129687223407945, "grad_norm": 0.62890625, "learning_rate": 1.2222080830703453e-05, "loss": 0.9760279083251953, "step": 532400 }, { "epoch": 6.13198990848266, "grad_norm": 0.53125, "learning_rate": 1.2214809266880935e-05, "loss": 1.0074124145507812, "step": 532600 }, { "epoch": 6.134292593557375, "grad_norm": 0.47265625, "learning_rate": 1.220753770305842e-05, "loss": 0.9710540008544922, "step": 532800 }, { "epoch": 6.13659527863209, "grad_norm": 0.7265625, "learning_rate": 1.2200266139235905e-05, "loss": 0.9692363739013672, "step": 533000 }, { "epoch": 6.138897963706805, "grad_norm": 0.87890625, "learning_rate": 1.2192994575413388e-05, "loss": 0.9787443542480468, "step": 533200 }, { "epoch": 6.14120064878152, "grad_norm": 0.65625, "learning_rate": 1.2185723011590872e-05, "loss": 0.9511615753173828, "step": 533400 }, { "epoch": 6.143503333856235, "grad_norm": 0.76171875, "learning_rate": 1.2178451447768358e-05, "loss": 0.9663115692138672, "step": 533600 }, { "epoch": 6.14580601893095, "grad_norm": 0.72265625, "learning_rate": 1.217117988394584e-05, "loss": 0.9776692962646485, "step": 533800 }, { "epoch": 6.148108704005665, "grad_norm": 0.609375, "learning_rate": 1.2163908320123327e-05, "loss": 0.983729248046875, "step": 534000 }, { "epoch": 6.1504113890803795, "grad_norm": 0.4609375, "learning_rate": 1.215663675630081e-05, "loss": 0.9854757690429687, "step": 534200 }, { "epoch": 6.152714074155094, "grad_norm": 0.515625, "learning_rate": 1.2149365192478293e-05, "loss": 0.9797981262207032, "step": 534400 }, { "epoch": 6.1550167592298095, "grad_norm": 0.6484375, "learning_rate": 1.214209362865578e-05, "loss": 0.9856068420410157, "step": 534600 }, { "epoch": 6.157319444304524, "grad_norm": 0.80078125, "learning_rate": 1.2134822064833263e-05, "loss": 0.9999673461914063, "step": 534800 }, { "epoch": 6.1596221293792395, "grad_norm": 0.55859375, "learning_rate": 1.2127550501010748e-05, "loss": 0.9946244049072266, "step": 535000 }, { "epoch": 6.161924814453954, "grad_norm": 0.51953125, "learning_rate": 1.2120278937188232e-05, "loss": 0.9824993133544921, "step": 535200 }, { "epoch": 6.164227499528669, "grad_norm": 1.0546875, "learning_rate": 1.2113007373365716e-05, "loss": 0.9499840545654297, "step": 535400 }, { "epoch": 6.166530184603384, "grad_norm": 0.447265625, "learning_rate": 1.2105735809543202e-05, "loss": 0.9955195617675782, "step": 535600 }, { "epoch": 6.168832869678099, "grad_norm": 0.9140625, "learning_rate": 1.2098464245720685e-05, "loss": 0.9737226104736328, "step": 535800 }, { "epoch": 6.171135554752814, "grad_norm": 0.94140625, "learning_rate": 1.2091192681898169e-05, "loss": 0.9871718597412109, "step": 536000 }, { "epoch": 6.1734382398275285, "grad_norm": 1.234375, "learning_rate": 1.2083921118075655e-05, "loss": 0.9826788330078124, "step": 536200 }, { "epoch": 6.175740924902244, "grad_norm": 0.71484375, "learning_rate": 1.2076649554253137e-05, "loss": 1.0013955688476563, "step": 536400 }, { "epoch": 6.1780436099769585, "grad_norm": 0.484375, "learning_rate": 1.2069377990430623e-05, "loss": 0.9916542053222657, "step": 536600 }, { "epoch": 6.180346295051674, "grad_norm": 0.42578125, "learning_rate": 1.2062106426608107e-05, "loss": 0.9936505889892578, "step": 536800 }, { "epoch": 6.182648980126388, "grad_norm": 0.69921875, "learning_rate": 1.205483486278559e-05, "loss": 0.9823659515380859, "step": 537000 }, { "epoch": 6.184951665201104, "grad_norm": 0.7109375, "learning_rate": 1.2047563298963076e-05, "loss": 0.974571762084961, "step": 537200 }, { "epoch": 6.187254350275818, "grad_norm": 0.61328125, "learning_rate": 1.204029173514056e-05, "loss": 0.9920982360839844, "step": 537400 }, { "epoch": 6.189557035350534, "grad_norm": 0.68359375, "learning_rate": 1.2033020171318042e-05, "loss": 0.9927661895751954, "step": 537600 }, { "epoch": 6.191859720425248, "grad_norm": 1.3359375, "learning_rate": 1.2025748607495528e-05, "loss": 0.9779354858398438, "step": 537800 }, { "epoch": 6.194162405499963, "grad_norm": 0.46875, "learning_rate": 1.2018477043673013e-05, "loss": 0.9786163330078125, "step": 538000 }, { "epoch": 6.196465090574678, "grad_norm": 0.67578125, "learning_rate": 1.2011205479850499e-05, "loss": 0.9637989807128906, "step": 538200 }, { "epoch": 6.198767775649393, "grad_norm": 0.57421875, "learning_rate": 1.2003933916027981e-05, "loss": 0.9681629943847656, "step": 538400 }, { "epoch": 6.201070460724108, "grad_norm": 0.62109375, "learning_rate": 1.1996662352205465e-05, "loss": 0.9763223266601563, "step": 538600 }, { "epoch": 6.203373145798823, "grad_norm": 0.6484375, "learning_rate": 1.1989390788382951e-05, "loss": 0.9757502746582031, "step": 538800 }, { "epoch": 6.205675830873538, "grad_norm": 0.79296875, "learning_rate": 1.1982119224560434e-05, "loss": 1.003903350830078, "step": 539000 }, { "epoch": 6.207978515948253, "grad_norm": 0.74609375, "learning_rate": 1.1974847660737918e-05, "loss": 0.9690301513671875, "step": 539200 }, { "epoch": 6.210281201022968, "grad_norm": 0.6796875, "learning_rate": 1.1967576096915404e-05, "loss": 0.9842018127441406, "step": 539400 }, { "epoch": 6.212583886097683, "grad_norm": 0.6328125, "learning_rate": 1.1960304533092886e-05, "loss": 0.9938206481933594, "step": 539600 }, { "epoch": 6.214886571172397, "grad_norm": 0.59375, "learning_rate": 1.1953032969270372e-05, "loss": 0.9942153930664063, "step": 539800 }, { "epoch": 6.217189256247113, "grad_norm": 0.55078125, "learning_rate": 1.1945761405447857e-05, "loss": 0.9966661834716797, "step": 540000 }, { "epoch": 6.219491941321827, "grad_norm": 0.8515625, "learning_rate": 1.1938489841625339e-05, "loss": 0.972867660522461, "step": 540200 }, { "epoch": 6.221794626396543, "grad_norm": 0.46484375, "learning_rate": 1.1931218277802825e-05, "loss": 0.9939933776855469, "step": 540400 }, { "epoch": 6.224097311471257, "grad_norm": 0.455078125, "learning_rate": 1.192394671398031e-05, "loss": 0.9651322174072265, "step": 540600 }, { "epoch": 6.226399996545973, "grad_norm": 0.62890625, "learning_rate": 1.1916675150157792e-05, "loss": 0.9611105346679687, "step": 540800 }, { "epoch": 6.228702681620687, "grad_norm": 0.60546875, "learning_rate": 1.1909403586335278e-05, "loss": 0.9767247009277343, "step": 541000 }, { "epoch": 6.231005366695403, "grad_norm": 0.734375, "learning_rate": 1.1902132022512762e-05, "loss": 0.9699462127685546, "step": 541200 }, { "epoch": 6.233308051770117, "grad_norm": 1.953125, "learning_rate": 1.1894860458690246e-05, "loss": 0.9935227966308594, "step": 541400 }, { "epoch": 6.235610736844832, "grad_norm": 0.640625, "learning_rate": 1.188758889486773e-05, "loss": 0.9764249420166016, "step": 541600 }, { "epoch": 6.237913421919547, "grad_norm": 0.84765625, "learning_rate": 1.1880317331045214e-05, "loss": 0.9721925354003906, "step": 541800 }, { "epoch": 6.240216106994262, "grad_norm": 0.416015625, "learning_rate": 1.18730457672227e-05, "loss": 0.9650587463378906, "step": 542000 }, { "epoch": 6.242518792068977, "grad_norm": 0.65625, "learning_rate": 1.1865774203400183e-05, "loss": 0.9611381530761719, "step": 542200 }, { "epoch": 6.244821477143692, "grad_norm": 0.77734375, "learning_rate": 1.1858502639577669e-05, "loss": 0.9796166229248047, "step": 542400 }, { "epoch": 6.247124162218407, "grad_norm": 0.53125, "learning_rate": 1.1851231075755153e-05, "loss": 0.9999110412597656, "step": 542600 }, { "epoch": 6.249426847293122, "grad_norm": 0.65234375, "learning_rate": 1.1843959511932636e-05, "loss": 0.9900628662109375, "step": 542800 }, { "epoch": 6.251729532367837, "grad_norm": 0.5625, "learning_rate": 1.1836687948110121e-05, "loss": 0.9753203582763672, "step": 543000 }, { "epoch": 6.2540322174425516, "grad_norm": 0.490234375, "learning_rate": 1.1829416384287606e-05, "loss": 0.96914306640625, "step": 543200 }, { "epoch": 6.256334902517267, "grad_norm": 0.625, "learning_rate": 1.1822144820465088e-05, "loss": 0.9859267425537109, "step": 543400 }, { "epoch": 6.2586375875919815, "grad_norm": 0.490234375, "learning_rate": 1.1814873256642574e-05, "loss": 0.9566590881347656, "step": 543600 }, { "epoch": 6.260940272666696, "grad_norm": 0.55859375, "learning_rate": 1.1807601692820058e-05, "loss": 0.9894088745117188, "step": 543800 }, { "epoch": 6.2632429577414115, "grad_norm": 0.58203125, "learning_rate": 1.1800330128997543e-05, "loss": 0.9496869659423828, "step": 544000 }, { "epoch": 6.265545642816126, "grad_norm": 0.7265625, "learning_rate": 1.1793058565175027e-05, "loss": 0.9789578247070313, "step": 544200 }, { "epoch": 6.2678483278908415, "grad_norm": 0.78515625, "learning_rate": 1.1785787001352511e-05, "loss": 0.9891857147216797, "step": 544400 }, { "epoch": 6.270151012965556, "grad_norm": 1.9453125, "learning_rate": 1.1778515437529995e-05, "loss": 0.9948699188232422, "step": 544600 }, { "epoch": 6.272453698040271, "grad_norm": 0.6171875, "learning_rate": 1.177124387370748e-05, "loss": 0.9798444366455078, "step": 544800 }, { "epoch": 6.274756383114986, "grad_norm": 0.5859375, "learning_rate": 1.1763972309884964e-05, "loss": 0.9842873382568359, "step": 545000 }, { "epoch": 6.2770590681897005, "grad_norm": 0.5234375, "learning_rate": 1.175670074606245e-05, "loss": 0.9862162017822266, "step": 545200 }, { "epoch": 6.279361753264416, "grad_norm": 0.5078125, "learning_rate": 1.1749429182239932e-05, "loss": 1.006587600708008, "step": 545400 }, { "epoch": 6.2816644383391305, "grad_norm": 0.69140625, "learning_rate": 1.1742157618417418e-05, "loss": 0.9883873748779297, "step": 545600 }, { "epoch": 6.283967123413846, "grad_norm": 0.43359375, "learning_rate": 1.1734886054594902e-05, "loss": 0.982315673828125, "step": 545800 }, { "epoch": 6.28626980848856, "grad_norm": 0.52734375, "learning_rate": 1.1727614490772385e-05, "loss": 0.9863622283935547, "step": 546000 }, { "epoch": 6.288572493563276, "grad_norm": 0.408203125, "learning_rate": 1.172034292694987e-05, "loss": 0.9699191284179688, "step": 546200 }, { "epoch": 6.29087517863799, "grad_norm": 0.57421875, "learning_rate": 1.1713071363127355e-05, "loss": 0.9829322052001953, "step": 546400 }, { "epoch": 6.293177863712706, "grad_norm": 0.5703125, "learning_rate": 1.1705799799304837e-05, "loss": 0.9939772796630859, "step": 546600 }, { "epoch": 6.29548054878742, "grad_norm": 0.77734375, "learning_rate": 1.1698528235482323e-05, "loss": 0.9853797149658203, "step": 546800 }, { "epoch": 6.297783233862136, "grad_norm": 0.76953125, "learning_rate": 1.1691256671659808e-05, "loss": 0.9782255554199218, "step": 547000 }, { "epoch": 6.30008591893685, "grad_norm": 0.55859375, "learning_rate": 1.1683985107837292e-05, "loss": 0.9772499847412109, "step": 547200 }, { "epoch": 6.302388604011565, "grad_norm": 0.89453125, "learning_rate": 1.1676713544014776e-05, "loss": 0.967388916015625, "step": 547400 }, { "epoch": 6.30469128908628, "grad_norm": 0.90625, "learning_rate": 1.166944198019226e-05, "loss": 0.9973257446289062, "step": 547600 }, { "epoch": 6.306993974160995, "grad_norm": 0.5546875, "learning_rate": 1.1662170416369744e-05, "loss": 1.0004740142822266, "step": 547800 }, { "epoch": 6.30929665923571, "grad_norm": 0.68359375, "learning_rate": 1.1654898852547229e-05, "loss": 0.9807405090332031, "step": 548000 }, { "epoch": 6.311599344310425, "grad_norm": 0.5859375, "learning_rate": 1.1647627288724713e-05, "loss": 0.9859786987304687, "step": 548200 }, { "epoch": 6.31390202938514, "grad_norm": 1.0625, "learning_rate": 1.1640355724902199e-05, "loss": 0.969800796508789, "step": 548400 }, { "epoch": 6.316204714459855, "grad_norm": 0.5859375, "learning_rate": 1.1633084161079681e-05, "loss": 0.9897576141357421, "step": 548600 }, { "epoch": 6.31850739953457, "grad_norm": 0.51171875, "learning_rate": 1.1625812597257167e-05, "loss": 0.9738155364990234, "step": 548800 }, { "epoch": 6.320810084609285, "grad_norm": 0.80859375, "learning_rate": 1.1618541033434651e-05, "loss": 1.0006730651855469, "step": 549000 }, { "epoch": 6.323112769683999, "grad_norm": 0.478515625, "learning_rate": 1.1611269469612134e-05, "loss": 1.010643768310547, "step": 549200 }, { "epoch": 6.325415454758715, "grad_norm": 0.6015625, "learning_rate": 1.160399790578962e-05, "loss": 0.9987123870849609, "step": 549400 }, { "epoch": 6.327718139833429, "grad_norm": 0.5390625, "learning_rate": 1.1596726341967104e-05, "loss": 0.9761300659179688, "step": 549600 }, { "epoch": 6.330020824908145, "grad_norm": 0.921875, "learning_rate": 1.1589454778144588e-05, "loss": 0.9792920684814453, "step": 549800 }, { "epoch": 6.332323509982859, "grad_norm": 0.58984375, "learning_rate": 1.1582183214322073e-05, "loss": 0.9785138702392578, "step": 550000 }, { "epoch": 6.334626195057575, "grad_norm": 1.4296875, "learning_rate": 1.1574911650499557e-05, "loss": 0.9807654571533203, "step": 550200 }, { "epoch": 6.336928880132289, "grad_norm": 0.76953125, "learning_rate": 1.1567640086677041e-05, "loss": 0.9899097442626953, "step": 550400 }, { "epoch": 6.339231565207005, "grad_norm": 0.49609375, "learning_rate": 1.1560368522854525e-05, "loss": 0.9844416046142578, "step": 550600 }, { "epoch": 6.341534250281719, "grad_norm": 0.52734375, "learning_rate": 1.155309695903201e-05, "loss": 0.986839370727539, "step": 550800 }, { "epoch": 6.343836935356434, "grad_norm": 0.9609375, "learning_rate": 1.1545825395209494e-05, "loss": 1.0087448120117188, "step": 551000 }, { "epoch": 6.346139620431149, "grad_norm": 0.421875, "learning_rate": 1.1538553831386978e-05, "loss": 0.9610017395019531, "step": 551200 }, { "epoch": 6.348442305505864, "grad_norm": 0.5, "learning_rate": 1.1531282267564464e-05, "loss": 1.00368896484375, "step": 551400 }, { "epoch": 6.350744990580579, "grad_norm": 0.48046875, "learning_rate": 1.1524010703741946e-05, "loss": 0.9645812225341797, "step": 551600 }, { "epoch": 6.353047675655294, "grad_norm": 0.482421875, "learning_rate": 1.151673913991943e-05, "loss": 0.9886111450195313, "step": 551800 }, { "epoch": 6.355350360730009, "grad_norm": 0.70703125, "learning_rate": 1.1509467576096916e-05, "loss": 1.0107182312011718, "step": 552000 }, { "epoch": 6.357653045804724, "grad_norm": 0.546875, "learning_rate": 1.15021960122744e-05, "loss": 0.9821375274658203, "step": 552200 }, { "epoch": 6.359955730879439, "grad_norm": 0.9375, "learning_rate": 1.1494924448451883e-05, "loss": 0.9769761657714844, "step": 552400 }, { "epoch": 6.3622584159541535, "grad_norm": 0.60546875, "learning_rate": 1.1487652884629369e-05, "loss": 0.9906520080566407, "step": 552600 }, { "epoch": 6.364561101028868, "grad_norm": 0.66015625, "learning_rate": 1.1480381320806853e-05, "loss": 0.9958131408691406, "step": 552800 }, { "epoch": 6.3668637861035835, "grad_norm": 0.486328125, "learning_rate": 1.1473109756984338e-05, "loss": 0.9820102691650391, "step": 553000 }, { "epoch": 6.369166471178298, "grad_norm": 0.640625, "learning_rate": 1.1465838193161822e-05, "loss": 1.0095059204101562, "step": 553200 }, { "epoch": 6.3714691562530135, "grad_norm": 0.546875, "learning_rate": 1.1458566629339306e-05, "loss": 0.9783484649658203, "step": 553400 }, { "epoch": 6.373771841327728, "grad_norm": 0.51171875, "learning_rate": 1.145129506551679e-05, "loss": 0.9865557098388672, "step": 553600 }, { "epoch": 6.376074526402443, "grad_norm": 0.6953125, "learning_rate": 1.1444023501694274e-05, "loss": 1.0026549530029296, "step": 553800 }, { "epoch": 6.378377211477158, "grad_norm": 0.95703125, "learning_rate": 1.1436751937871759e-05, "loss": 0.9793618774414062, "step": 554000 }, { "epoch": 6.380679896551873, "grad_norm": 0.5703125, "learning_rate": 1.1429480374049243e-05, "loss": 0.9879568481445312, "step": 554200 }, { "epoch": 6.382982581626588, "grad_norm": 0.94921875, "learning_rate": 1.1422208810226727e-05, "loss": 1.0095554351806642, "step": 554400 }, { "epoch": 6.3852852667013025, "grad_norm": 0.84765625, "learning_rate": 1.1414937246404213e-05, "loss": 0.9665096282958985, "step": 554600 }, { "epoch": 6.387587951776018, "grad_norm": 0.7734375, "learning_rate": 1.1407665682581696e-05, "loss": 0.99393798828125, "step": 554800 }, { "epoch": 6.389890636850732, "grad_norm": 0.640625, "learning_rate": 1.140039411875918e-05, "loss": 0.9509799194335937, "step": 555000 }, { "epoch": 6.392193321925448, "grad_norm": 0.51171875, "learning_rate": 1.1393122554936666e-05, "loss": 0.9921061706542968, "step": 555200 }, { "epoch": 6.394496007000162, "grad_norm": 0.47265625, "learning_rate": 1.138585099111415e-05, "loss": 0.9750463104248047, "step": 555400 }, { "epoch": 6.396798692074878, "grad_norm": 0.8203125, "learning_rate": 1.1378579427291634e-05, "loss": 0.9920413970947266, "step": 555600 }, { "epoch": 6.399101377149592, "grad_norm": 0.56640625, "learning_rate": 1.1371307863469118e-05, "loss": 1.0085044860839845, "step": 555800 }, { "epoch": 6.401404062224308, "grad_norm": 0.53515625, "learning_rate": 1.1364036299646603e-05, "loss": 0.9668448638916015, "step": 556000 }, { "epoch": 6.403706747299022, "grad_norm": 0.80078125, "learning_rate": 1.1356764735824087e-05, "loss": 0.9831298828125, "step": 556200 }, { "epoch": 6.406009432373738, "grad_norm": 1.03125, "learning_rate": 1.1349493172001571e-05, "loss": 0.9696995544433594, "step": 556400 }, { "epoch": 6.408312117448452, "grad_norm": 0.51953125, "learning_rate": 1.1342221608179055e-05, "loss": 0.9708090209960938, "step": 556600 }, { "epoch": 6.410614802523167, "grad_norm": 0.72265625, "learning_rate": 1.133495004435654e-05, "loss": 0.9818246459960938, "step": 556800 }, { "epoch": 6.412917487597882, "grad_norm": 0.55859375, "learning_rate": 1.1327678480534024e-05, "loss": 0.9953689575195312, "step": 557000 }, { "epoch": 6.415220172672597, "grad_norm": 0.78125, "learning_rate": 1.132040691671151e-05, "loss": 0.9716912841796875, "step": 557200 }, { "epoch": 6.417522857747312, "grad_norm": 0.765625, "learning_rate": 1.1313135352888992e-05, "loss": 0.9794044494628906, "step": 557400 }, { "epoch": 6.419825542822027, "grad_norm": 0.50390625, "learning_rate": 1.1305863789066476e-05, "loss": 0.9842906951904297, "step": 557600 }, { "epoch": 6.422128227896742, "grad_norm": 0.765625, "learning_rate": 1.1298592225243962e-05, "loss": 0.9960566711425781, "step": 557800 }, { "epoch": 6.424430912971457, "grad_norm": 0.86328125, "learning_rate": 1.1291320661421445e-05, "loss": 0.9707205200195312, "step": 558000 }, { "epoch": 6.426733598046171, "grad_norm": 1.078125, "learning_rate": 1.1284049097598929e-05, "loss": 0.9869296264648437, "step": 558200 }, { "epoch": 6.429036283120887, "grad_norm": 0.8046875, "learning_rate": 1.1276777533776415e-05, "loss": 0.9972148895263672, "step": 558400 }, { "epoch": 6.431338968195601, "grad_norm": 0.55078125, "learning_rate": 1.1269505969953899e-05, "loss": 0.9682855224609375, "step": 558600 }, { "epoch": 6.433641653270317, "grad_norm": 1.0390625, "learning_rate": 1.1262234406131383e-05, "loss": 1.0019464874267578, "step": 558800 }, { "epoch": 6.435944338345031, "grad_norm": 0.70703125, "learning_rate": 1.1254962842308868e-05, "loss": 0.9992044067382813, "step": 559000 }, { "epoch": 6.438247023419747, "grad_norm": 0.58203125, "learning_rate": 1.1247691278486352e-05, "loss": 0.9800476837158203, "step": 559200 }, { "epoch": 6.440549708494461, "grad_norm": 0.9921875, "learning_rate": 1.1240419714663836e-05, "loss": 0.9893782043457031, "step": 559400 }, { "epoch": 6.442852393569177, "grad_norm": 0.52734375, "learning_rate": 1.123314815084132e-05, "loss": 0.9816644287109375, "step": 559600 }, { "epoch": 6.445155078643891, "grad_norm": 0.625, "learning_rate": 1.1225876587018804e-05, "loss": 0.9631548309326172, "step": 559800 }, { "epoch": 6.447457763718607, "grad_norm": 0.7265625, "learning_rate": 1.1218605023196289e-05, "loss": 0.9729603576660156, "step": 560000 }, { "epoch": 6.449760448793321, "grad_norm": 1.0, "learning_rate": 1.1211333459373773e-05, "loss": 0.9714144134521484, "step": 560200 }, { "epoch": 6.452063133868036, "grad_norm": 1.7421875, "learning_rate": 1.1204061895551259e-05, "loss": 0.9656848907470703, "step": 560400 }, { "epoch": 6.454365818942751, "grad_norm": 0.8359375, "learning_rate": 1.1196790331728741e-05, "loss": 0.9788755798339843, "step": 560600 }, { "epoch": 6.456668504017466, "grad_norm": 0.65625, "learning_rate": 1.1189518767906225e-05, "loss": 0.9863886260986328, "step": 560800 }, { "epoch": 6.458971189092181, "grad_norm": 0.59765625, "learning_rate": 1.1182247204083711e-05, "loss": 0.9713378143310547, "step": 561000 }, { "epoch": 6.461273874166896, "grad_norm": 1.1484375, "learning_rate": 1.1174975640261194e-05, "loss": 0.9846022033691406, "step": 561200 }, { "epoch": 6.463576559241611, "grad_norm": 0.71875, "learning_rate": 1.1167704076438678e-05, "loss": 0.9709203338623047, "step": 561400 }, { "epoch": 6.4658792443163255, "grad_norm": 0.55859375, "learning_rate": 1.1160432512616164e-05, "loss": 0.9927424621582032, "step": 561600 }, { "epoch": 6.46818192939104, "grad_norm": 0.53515625, "learning_rate": 1.1153160948793648e-05, "loss": 0.982939224243164, "step": 561800 }, { "epoch": 6.4704846144657555, "grad_norm": 0.68359375, "learning_rate": 1.1145889384971132e-05, "loss": 0.9967118835449219, "step": 562000 }, { "epoch": 6.47278729954047, "grad_norm": 0.71484375, "learning_rate": 1.1138617821148617e-05, "loss": 0.9820690155029297, "step": 562200 }, { "epoch": 6.4750899846151855, "grad_norm": 1.0390625, "learning_rate": 1.1131346257326101e-05, "loss": 1.004434585571289, "step": 562400 }, { "epoch": 6.4773926696899, "grad_norm": 0.640625, "learning_rate": 1.1124074693503585e-05, "loss": 1.005102081298828, "step": 562600 }, { "epoch": 6.4796953547646154, "grad_norm": 0.8515625, "learning_rate": 1.111680312968107e-05, "loss": 0.9745596313476562, "step": 562800 }, { "epoch": 6.48199803983933, "grad_norm": 0.5390625, "learning_rate": 1.1109531565858555e-05, "loss": 0.9957767486572265, "step": 563000 }, { "epoch": 6.484300724914045, "grad_norm": 0.734375, "learning_rate": 1.1102260002036038e-05, "loss": 0.996214599609375, "step": 563200 }, { "epoch": 6.48660340998876, "grad_norm": 0.453125, "learning_rate": 1.1094988438213522e-05, "loss": 0.9917230224609375, "step": 563400 }, { "epoch": 6.488906095063475, "grad_norm": 0.58984375, "learning_rate": 1.1087716874391008e-05, "loss": 0.9812522888183594, "step": 563600 }, { "epoch": 6.49120878013819, "grad_norm": 0.6484375, "learning_rate": 1.108044531056849e-05, "loss": 0.9831491851806641, "step": 563800 }, { "epoch": 6.4935114652129045, "grad_norm": 0.83203125, "learning_rate": 1.1073173746745975e-05, "loss": 0.9870780181884765, "step": 564000 }, { "epoch": 6.49581415028762, "grad_norm": 0.6640625, "learning_rate": 1.106590218292346e-05, "loss": 0.960843505859375, "step": 564200 }, { "epoch": 6.498116835362334, "grad_norm": 0.6328125, "learning_rate": 1.1058630619100943e-05, "loss": 0.9944307708740234, "step": 564400 }, { "epoch": 6.50041952043705, "grad_norm": 0.76171875, "learning_rate": 1.1051359055278429e-05, "loss": 0.9977530670166016, "step": 564600 }, { "epoch": 6.502722205511764, "grad_norm": 0.6171875, "learning_rate": 1.1044087491455913e-05, "loss": 0.9751404571533203, "step": 564800 }, { "epoch": 6.50502489058648, "grad_norm": 0.61328125, "learning_rate": 1.1036815927633396e-05, "loss": 1.0031847381591796, "step": 565000 }, { "epoch": 6.507327575661194, "grad_norm": 0.68359375, "learning_rate": 1.1029544363810882e-05, "loss": 0.9857213592529297, "step": 565200 }, { "epoch": 6.509630260735909, "grad_norm": 0.83203125, "learning_rate": 1.1022272799988366e-05, "loss": 0.9579655456542969, "step": 565400 }, { "epoch": 6.511932945810624, "grad_norm": 2.703125, "learning_rate": 1.101500123616585e-05, "loss": 0.970751724243164, "step": 565600 }, { "epoch": 6.514235630885339, "grad_norm": 0.58203125, "learning_rate": 1.1007729672343334e-05, "loss": 0.9810092163085937, "step": 565800 }, { "epoch": 6.516538315960054, "grad_norm": 0.69921875, "learning_rate": 1.1000458108520819e-05, "loss": 0.9883064270019531, "step": 566000 }, { "epoch": 6.518841001034769, "grad_norm": 0.7890625, "learning_rate": 1.0993186544698304e-05, "loss": 0.9706736755371094, "step": 566200 }, { "epoch": 6.521143686109484, "grad_norm": 0.51953125, "learning_rate": 1.0985914980875787e-05, "loss": 0.9820281982421875, "step": 566400 }, { "epoch": 6.523446371184199, "grad_norm": 0.83203125, "learning_rate": 1.0978643417053271e-05, "loss": 0.9836884307861328, "step": 566600 }, { "epoch": 6.525749056258914, "grad_norm": 1.4609375, "learning_rate": 1.0971371853230757e-05, "loss": 1.001689682006836, "step": 566800 }, { "epoch": 6.528051741333629, "grad_norm": 0.765625, "learning_rate": 1.096410028940824e-05, "loss": 0.9856477355957032, "step": 567000 }, { "epoch": 6.530354426408344, "grad_norm": 1.734375, "learning_rate": 1.0956828725585724e-05, "loss": 0.9702422332763672, "step": 567200 }, { "epoch": 6.532657111483059, "grad_norm": 0.91015625, "learning_rate": 1.094955716176321e-05, "loss": 0.990765609741211, "step": 567400 }, { "epoch": 6.534959796557773, "grad_norm": 0.53515625, "learning_rate": 1.0942285597940692e-05, "loss": 1.006974563598633, "step": 567600 }, { "epoch": 6.537262481632489, "grad_norm": 0.70703125, "learning_rate": 1.0935014034118178e-05, "loss": 0.9736676788330079, "step": 567800 }, { "epoch": 6.539565166707203, "grad_norm": 0.80859375, "learning_rate": 1.0927742470295662e-05, "loss": 0.9964972686767578, "step": 568000 }, { "epoch": 6.541867851781919, "grad_norm": 0.83984375, "learning_rate": 1.0920470906473145e-05, "loss": 0.9812130737304687, "step": 568200 }, { "epoch": 6.544170536856633, "grad_norm": 0.494140625, "learning_rate": 1.0913199342650631e-05, "loss": 0.9940660858154297, "step": 568400 }, { "epoch": 6.546473221931349, "grad_norm": 1.140625, "learning_rate": 1.0905927778828115e-05, "loss": 0.9886941528320312, "step": 568600 }, { "epoch": 6.548775907006063, "grad_norm": 0.640625, "learning_rate": 1.08986562150056e-05, "loss": 0.9685357666015625, "step": 568800 }, { "epoch": 6.551078592080778, "grad_norm": 0.5859375, "learning_rate": 1.0891384651183084e-05, "loss": 0.9673428344726562, "step": 569000 }, { "epoch": 6.553381277155493, "grad_norm": 0.5390625, "learning_rate": 1.0884113087360568e-05, "loss": 0.9898664855957031, "step": 569200 }, { "epoch": 6.5556839622302086, "grad_norm": 0.65625, "learning_rate": 1.0876841523538054e-05, "loss": 0.9710381317138672, "step": 569400 }, { "epoch": 6.557986647304923, "grad_norm": 0.57421875, "learning_rate": 1.0869569959715536e-05, "loss": 0.957591552734375, "step": 569600 }, { "epoch": 6.560289332379638, "grad_norm": 0.53515625, "learning_rate": 1.086229839589302e-05, "loss": 0.9589216613769531, "step": 569800 }, { "epoch": 6.562592017454353, "grad_norm": 0.515625, "learning_rate": 1.0855026832070506e-05, "loss": 0.9881840515136718, "step": 570000 }, { "epoch": 6.564894702529068, "grad_norm": 0.8828125, "learning_rate": 1.0847755268247989e-05, "loss": 0.9679238891601563, "step": 570200 }, { "epoch": 6.567197387603783, "grad_norm": 0.76953125, "learning_rate": 1.0840483704425475e-05, "loss": 0.9674862670898438, "step": 570400 }, { "epoch": 6.569500072678498, "grad_norm": 0.7265625, "learning_rate": 1.0833212140602959e-05, "loss": 0.9502196502685547, "step": 570600 }, { "epoch": 6.571802757753213, "grad_norm": 0.86328125, "learning_rate": 1.0825940576780442e-05, "loss": 0.9787293243408203, "step": 570800 }, { "epoch": 6.5741054428279275, "grad_norm": 0.55078125, "learning_rate": 1.0818669012957927e-05, "loss": 1.0087420654296875, "step": 571000 }, { "epoch": 6.576408127902642, "grad_norm": 0.6796875, "learning_rate": 1.0811397449135412e-05, "loss": 0.9817219543457031, "step": 571200 }, { "epoch": 6.5787108129773575, "grad_norm": 0.74609375, "learning_rate": 1.0804125885312894e-05, "loss": 0.9803526306152344, "step": 571400 }, { "epoch": 6.581013498052072, "grad_norm": 0.8125, "learning_rate": 1.079685432149038e-05, "loss": 0.9712112426757813, "step": 571600 }, { "epoch": 6.5833161831267875, "grad_norm": 0.5546875, "learning_rate": 1.0789582757667864e-05, "loss": 0.9745654296875, "step": 571800 }, { "epoch": 6.585618868201502, "grad_norm": 1.0546875, "learning_rate": 1.078231119384535e-05, "loss": 0.9731366729736328, "step": 572000 }, { "epoch": 6.587921553276217, "grad_norm": 0.80859375, "learning_rate": 1.0775039630022833e-05, "loss": 0.9887467193603515, "step": 572200 }, { "epoch": 6.590224238350932, "grad_norm": 0.859375, "learning_rate": 1.0767768066200317e-05, "loss": 0.9958180999755859, "step": 572400 }, { "epoch": 6.592526923425647, "grad_norm": 0.67578125, "learning_rate": 1.0760496502377803e-05, "loss": 0.9899420166015624, "step": 572600 }, { "epoch": 6.594829608500362, "grad_norm": 0.76171875, "learning_rate": 1.0753224938555285e-05, "loss": 0.9905350494384766, "step": 572800 }, { "epoch": 6.597132293575077, "grad_norm": 0.640625, "learning_rate": 1.074595337473277e-05, "loss": 0.9972842407226562, "step": 573000 }, { "epoch": 6.599434978649792, "grad_norm": 0.74609375, "learning_rate": 1.0738681810910256e-05, "loss": 0.9325897216796875, "step": 573200 }, { "epoch": 6.601737663724506, "grad_norm": 1.0703125, "learning_rate": 1.0731410247087738e-05, "loss": 0.9847271728515625, "step": 573400 }, { "epoch": 6.604040348799222, "grad_norm": 0.80078125, "learning_rate": 1.0724138683265224e-05, "loss": 0.9817544555664063, "step": 573600 }, { "epoch": 6.606343033873936, "grad_norm": 0.85546875, "learning_rate": 1.0716867119442708e-05, "loss": 0.9679446411132813, "step": 573800 }, { "epoch": 6.608645718948652, "grad_norm": 0.72265625, "learning_rate": 1.070959555562019e-05, "loss": 0.9627344512939453, "step": 574000 }, { "epoch": 6.610948404023366, "grad_norm": 0.95703125, "learning_rate": 1.0702323991797677e-05, "loss": 1.007912139892578, "step": 574200 }, { "epoch": 6.613251089098082, "grad_norm": 0.5390625, "learning_rate": 1.0695052427975161e-05, "loss": 0.9748046112060547, "step": 574400 }, { "epoch": 6.615553774172796, "grad_norm": 0.56640625, "learning_rate": 1.0687780864152643e-05, "loss": 0.971591567993164, "step": 574600 }, { "epoch": 6.617856459247511, "grad_norm": 0.52734375, "learning_rate": 1.068050930033013e-05, "loss": 0.9806672668457032, "step": 574800 }, { "epoch": 6.620159144322226, "grad_norm": 0.47265625, "learning_rate": 1.0673237736507614e-05, "loss": 0.9956932830810546, "step": 575000 }, { "epoch": 6.622461829396941, "grad_norm": 1.546875, "learning_rate": 1.0665966172685098e-05, "loss": 0.9696024322509765, "step": 575200 }, { "epoch": 6.624764514471656, "grad_norm": 0.6328125, "learning_rate": 1.0658694608862582e-05, "loss": 0.96540283203125, "step": 575400 }, { "epoch": 6.627067199546371, "grad_norm": 0.515625, "learning_rate": 1.0651423045040066e-05, "loss": 0.9723766326904297, "step": 575600 }, { "epoch": 6.629369884621086, "grad_norm": 0.99609375, "learning_rate": 1.0644151481217552e-05, "loss": 1.006049346923828, "step": 575800 }, { "epoch": 6.631672569695801, "grad_norm": 0.75, "learning_rate": 1.0636879917395035e-05, "loss": 0.9848546600341797, "step": 576000 }, { "epoch": 6.633975254770516, "grad_norm": 0.66015625, "learning_rate": 1.062960835357252e-05, "loss": 1.018324203491211, "step": 576200 }, { "epoch": 6.636277939845231, "grad_norm": 0.61328125, "learning_rate": 1.0622336789750005e-05, "loss": 0.9924317169189453, "step": 576400 }, { "epoch": 6.638580624919946, "grad_norm": 0.6015625, "learning_rate": 1.0615065225927487e-05, "loss": 0.9519772338867187, "step": 576600 }, { "epoch": 6.640883309994661, "grad_norm": 0.7265625, "learning_rate": 1.0607793662104973e-05, "loss": 0.9751395416259766, "step": 576800 }, { "epoch": 6.643185995069375, "grad_norm": 1.0859375, "learning_rate": 1.0600522098282457e-05, "loss": 0.9836444854736328, "step": 577000 }, { "epoch": 6.645488680144091, "grad_norm": 0.58984375, "learning_rate": 1.059325053445994e-05, "loss": 0.9723554229736329, "step": 577200 }, { "epoch": 6.647791365218805, "grad_norm": 0.62109375, "learning_rate": 1.0585978970637426e-05, "loss": 1.0011803436279296, "step": 577400 }, { "epoch": 6.650094050293521, "grad_norm": 0.87109375, "learning_rate": 1.057870740681491e-05, "loss": 0.9975678253173829, "step": 577600 }, { "epoch": 6.652396735368235, "grad_norm": 0.447265625, "learning_rate": 1.0571435842992394e-05, "loss": 0.9962368774414062, "step": 577800 }, { "epoch": 6.654699420442951, "grad_norm": 0.474609375, "learning_rate": 1.0564164279169879e-05, "loss": 0.9701191711425782, "step": 578000 }, { "epoch": 6.657002105517665, "grad_norm": 0.59765625, "learning_rate": 1.0556892715347363e-05, "loss": 0.9803343200683594, "step": 578200 }, { "epoch": 6.65930479059238, "grad_norm": 1.1484375, "learning_rate": 1.0549621151524847e-05, "loss": 0.9848207855224609, "step": 578400 }, { "epoch": 6.661607475667095, "grad_norm": 0.73046875, "learning_rate": 1.0542349587702331e-05, "loss": 0.9811007690429687, "step": 578600 }, { "epoch": 6.66391016074181, "grad_norm": 0.9765625, "learning_rate": 1.0535078023879815e-05, "loss": 0.9867758941650391, "step": 578800 }, { "epoch": 6.666212845816525, "grad_norm": 0.546875, "learning_rate": 1.0527806460057301e-05, "loss": 0.9914443206787109, "step": 579000 }, { "epoch": 6.66851553089124, "grad_norm": 1.0078125, "learning_rate": 1.0520534896234784e-05, "loss": 0.9794180297851562, "step": 579200 }, { "epoch": 6.670818215965955, "grad_norm": 0.6875, "learning_rate": 1.051326333241227e-05, "loss": 0.9820137023925781, "step": 579400 }, { "epoch": 6.67312090104067, "grad_norm": 0.89453125, "learning_rate": 1.0505991768589754e-05, "loss": 0.990504150390625, "step": 579600 }, { "epoch": 6.675423586115385, "grad_norm": 0.7265625, "learning_rate": 1.0498720204767236e-05, "loss": 0.9704412078857422, "step": 579800 }, { "epoch": 6.6777262711900995, "grad_norm": 0.4765625, "learning_rate": 1.0491448640944722e-05, "loss": 0.9653994750976562, "step": 580000 }, { "epoch": 6.680028956264815, "grad_norm": 0.734375, "learning_rate": 1.0484177077122207e-05, "loss": 0.9979000091552734, "step": 580200 }, { "epoch": 6.6823316413395295, "grad_norm": 0.6796875, "learning_rate": 1.0476905513299689e-05, "loss": 0.9706903076171876, "step": 580400 }, { "epoch": 6.684634326414244, "grad_norm": 0.7890625, "learning_rate": 1.0469633949477175e-05, "loss": 0.9929607391357422, "step": 580600 }, { "epoch": 6.6869370114889595, "grad_norm": 0.8203125, "learning_rate": 1.046236238565466e-05, "loss": 0.9664354705810547, "step": 580800 }, { "epoch": 6.689239696563674, "grad_norm": 0.466796875, "learning_rate": 1.0455090821832144e-05, "loss": 0.9774636840820312, "step": 581000 }, { "epoch": 6.691542381638389, "grad_norm": 0.474609375, "learning_rate": 1.0447819258009628e-05, "loss": 0.9902906799316407, "step": 581200 }, { "epoch": 6.693845066713104, "grad_norm": 0.54296875, "learning_rate": 1.0440547694187112e-05, "loss": 1.0105450439453125, "step": 581400 }, { "epoch": 6.696147751787819, "grad_norm": 0.5703125, "learning_rate": 1.0433276130364596e-05, "loss": 0.9908228302001953, "step": 581600 }, { "epoch": 6.698450436862534, "grad_norm": 0.80859375, "learning_rate": 1.042600456654208e-05, "loss": 0.9905318450927735, "step": 581800 }, { "epoch": 6.7007531219372485, "grad_norm": 0.9140625, "learning_rate": 1.0418733002719565e-05, "loss": 0.9779328155517578, "step": 582000 }, { "epoch": 6.703055807011964, "grad_norm": 0.5703125, "learning_rate": 1.041146143889705e-05, "loss": 0.9844884490966797, "step": 582200 }, { "epoch": 6.7053584920866784, "grad_norm": 0.54296875, "learning_rate": 1.0404189875074533e-05, "loss": 0.9839838409423828, "step": 582400 }, { "epoch": 6.707661177161394, "grad_norm": 0.78125, "learning_rate": 1.0396918311252019e-05, "loss": 0.9807382202148438, "step": 582600 }, { "epoch": 6.709963862236108, "grad_norm": 0.71484375, "learning_rate": 1.0389646747429503e-05, "loss": 0.9836902618408203, "step": 582800 }, { "epoch": 6.712266547310824, "grad_norm": 0.828125, "learning_rate": 1.0382375183606986e-05, "loss": 0.9829158020019532, "step": 583000 }, { "epoch": 6.714569232385538, "grad_norm": 0.55859375, "learning_rate": 1.0375103619784472e-05, "loss": 0.9916680908203125, "step": 583200 }, { "epoch": 6.716871917460254, "grad_norm": 0.65625, "learning_rate": 1.0367832055961956e-05, "loss": 0.9769731903076172, "step": 583400 }, { "epoch": 6.719174602534968, "grad_norm": 0.84765625, "learning_rate": 1.036056049213944e-05, "loss": 0.9810326385498047, "step": 583600 }, { "epoch": 6.721477287609684, "grad_norm": 0.828125, "learning_rate": 1.0353288928316924e-05, "loss": 1.0014809417724608, "step": 583800 }, { "epoch": 6.723779972684398, "grad_norm": 0.5234375, "learning_rate": 1.0346017364494408e-05, "loss": 0.9822134399414062, "step": 584000 }, { "epoch": 6.726082657759113, "grad_norm": 0.77734375, "learning_rate": 1.0338745800671893e-05, "loss": 0.9904820251464844, "step": 584200 }, { "epoch": 6.728385342833828, "grad_norm": 0.73828125, "learning_rate": 1.0331474236849377e-05, "loss": 0.9892137145996094, "step": 584400 }, { "epoch": 6.730688027908543, "grad_norm": 1.4765625, "learning_rate": 1.0324202673026861e-05, "loss": 0.980720443725586, "step": 584600 }, { "epoch": 6.732990712983258, "grad_norm": 0.66015625, "learning_rate": 1.0316931109204345e-05, "loss": 0.9904631805419922, "step": 584800 }, { "epoch": 6.735293398057973, "grad_norm": 0.60546875, "learning_rate": 1.030965954538183e-05, "loss": 0.9949741363525391, "step": 585000 }, { "epoch": 6.737596083132688, "grad_norm": 0.478515625, "learning_rate": 1.0302387981559315e-05, "loss": 1.012327880859375, "step": 585200 }, { "epoch": 6.739898768207403, "grad_norm": 0.69921875, "learning_rate": 1.02951164177368e-05, "loss": 0.9787694549560547, "step": 585400 }, { "epoch": 6.742201453282117, "grad_norm": 0.80859375, "learning_rate": 1.0287844853914282e-05, "loss": 0.9854193878173828, "step": 585600 }, { "epoch": 6.744504138356833, "grad_norm": 0.6796875, "learning_rate": 1.0280573290091768e-05, "loss": 0.9754302215576172, "step": 585800 }, { "epoch": 6.746806823431548, "grad_norm": 1.0625, "learning_rate": 1.0273301726269252e-05, "loss": 0.9814857482910156, "step": 586000 }, { "epoch": 6.749109508506263, "grad_norm": 0.59375, "learning_rate": 1.0266030162446735e-05, "loss": 0.9915824890136719, "step": 586200 }, { "epoch": 6.751412193580977, "grad_norm": 0.61328125, "learning_rate": 1.025875859862422e-05, "loss": 0.9872344970703125, "step": 586400 }, { "epoch": 6.753714878655693, "grad_norm": 1.0, "learning_rate": 1.0251487034801705e-05, "loss": 0.9672900390625, "step": 586600 }, { "epoch": 6.756017563730407, "grad_norm": 0.5546875, "learning_rate": 1.024421547097919e-05, "loss": 0.9766867065429687, "step": 586800 }, { "epoch": 6.758320248805123, "grad_norm": 1.453125, "learning_rate": 1.0236943907156673e-05, "loss": 1.0006546783447265, "step": 587000 }, { "epoch": 6.760622933879837, "grad_norm": 0.7890625, "learning_rate": 1.0229672343334158e-05, "loss": 0.9878829193115234, "step": 587200 }, { "epoch": 6.762925618954553, "grad_norm": 0.73828125, "learning_rate": 1.0222400779511642e-05, "loss": 0.9849906921386719, "step": 587400 }, { "epoch": 6.765228304029267, "grad_norm": 0.84375, "learning_rate": 1.0215129215689126e-05, "loss": 0.9837782287597656, "step": 587600 }, { "epoch": 6.767530989103982, "grad_norm": 0.796875, "learning_rate": 1.020785765186661e-05, "loss": 0.978974609375, "step": 587800 }, { "epoch": 6.769833674178697, "grad_norm": 0.76953125, "learning_rate": 1.0200586088044095e-05, "loss": 0.9979602813720703, "step": 588000 }, { "epoch": 6.772136359253412, "grad_norm": 0.71875, "learning_rate": 1.0193314524221579e-05, "loss": 0.9683854675292969, "step": 588200 }, { "epoch": 6.774439044328127, "grad_norm": 0.56640625, "learning_rate": 1.0186042960399065e-05, "loss": 0.9971164703369141, "step": 588400 }, { "epoch": 6.776741729402842, "grad_norm": 0.6796875, "learning_rate": 1.0178771396576547e-05, "loss": 0.9966475677490234, "step": 588600 }, { "epoch": 6.779044414477557, "grad_norm": 1.4375, "learning_rate": 1.0171499832754031e-05, "loss": 0.9796976470947265, "step": 588800 }, { "epoch": 6.7813470995522716, "grad_norm": 0.77734375, "learning_rate": 1.0164228268931517e-05, "loss": 0.9383587646484375, "step": 589000 }, { "epoch": 6.783649784626987, "grad_norm": 0.68359375, "learning_rate": 1.0156956705109002e-05, "loss": 0.9837628936767578, "step": 589200 }, { "epoch": 6.7859524697017015, "grad_norm": 0.72265625, "learning_rate": 1.0149685141286484e-05, "loss": 0.9929660034179687, "step": 589400 }, { "epoch": 6.788255154776417, "grad_norm": 0.439453125, "learning_rate": 1.014241357746397e-05, "loss": 0.993055191040039, "step": 589600 }, { "epoch": 6.7905578398511315, "grad_norm": 1.203125, "learning_rate": 1.0135142013641454e-05, "loss": 1.001646957397461, "step": 589800 }, { "epoch": 6.792860524925846, "grad_norm": 0.53515625, "learning_rate": 1.0127870449818938e-05, "loss": 0.9851081085205078, "step": 590000 }, { "epoch": 6.7951632100005614, "grad_norm": 0.65625, "learning_rate": 1.0120598885996423e-05, "loss": 0.9693524932861328, "step": 590200 }, { "epoch": 6.797465895075276, "grad_norm": 1.078125, "learning_rate": 1.0113327322173907e-05, "loss": 0.9681202697753907, "step": 590400 }, { "epoch": 6.799768580149991, "grad_norm": 0.98828125, "learning_rate": 1.0106055758351391e-05, "loss": 0.9943393707275391, "step": 590600 }, { "epoch": 6.802071265224706, "grad_norm": 1.671875, "learning_rate": 1.0098784194528875e-05, "loss": 0.9649395751953125, "step": 590800 }, { "epoch": 6.804373950299421, "grad_norm": 0.81640625, "learning_rate": 1.0091512630706361e-05, "loss": 0.9603765869140625, "step": 591000 }, { "epoch": 6.806676635374136, "grad_norm": 0.6484375, "learning_rate": 1.0084241066883844e-05, "loss": 0.9838564300537109, "step": 591200 }, { "epoch": 6.8089793204488505, "grad_norm": 0.828125, "learning_rate": 1.0076969503061328e-05, "loss": 0.9951017761230468, "step": 591400 }, { "epoch": 6.811282005523566, "grad_norm": 0.6015625, "learning_rate": 1.0069697939238814e-05, "loss": 0.9828236389160157, "step": 591600 }, { "epoch": 6.81358469059828, "grad_norm": 0.7109375, "learning_rate": 1.0062426375416296e-05, "loss": 0.9695124053955078, "step": 591800 }, { "epoch": 6.815887375672996, "grad_norm": 0.58984375, "learning_rate": 1.005515481159378e-05, "loss": 0.979861831665039, "step": 592000 }, { "epoch": 6.81819006074771, "grad_norm": 1.21875, "learning_rate": 1.0047883247771267e-05, "loss": 0.9814624786376953, "step": 592200 }, { "epoch": 6.820492745822426, "grad_norm": 0.98046875, "learning_rate": 1.004061168394875e-05, "loss": 0.9897750091552734, "step": 592400 }, { "epoch": 6.82279543089714, "grad_norm": 0.81640625, "learning_rate": 1.0033340120126235e-05, "loss": 0.9900749206542969, "step": 592600 }, { "epoch": 6.825098115971856, "grad_norm": 0.77734375, "learning_rate": 1.002606855630372e-05, "loss": 1.0019539642333983, "step": 592800 }, { "epoch": 6.82740080104657, "grad_norm": 0.486328125, "learning_rate": 1.0018796992481203e-05, "loss": 0.9855136108398438, "step": 593000 }, { "epoch": 6.829703486121286, "grad_norm": 0.640625, "learning_rate": 1.0011525428658688e-05, "loss": 0.9888275909423828, "step": 593200 }, { "epoch": 6.832006171196, "grad_norm": 0.423828125, "learning_rate": 1.0004253864836172e-05, "loss": 0.9735780334472657, "step": 593400 }, { "epoch": 6.834308856270715, "grad_norm": 0.6328125, "learning_rate": 9.996982301013656e-06, "loss": 0.9800492858886719, "step": 593600 }, { "epoch": 6.83661154134543, "grad_norm": 0.40625, "learning_rate": 9.98971073719114e-06, "loss": 0.9859529113769532, "step": 593800 }, { "epoch": 6.838914226420145, "grad_norm": 0.4765625, "learning_rate": 9.982439173368625e-06, "loss": 0.9810272979736329, "step": 594000 }, { "epoch": 6.84121691149486, "grad_norm": 0.80859375, "learning_rate": 9.97516760954611e-06, "loss": 0.9831668090820312, "step": 594200 }, { "epoch": 6.843519596569575, "grad_norm": 0.640625, "learning_rate": 9.967896045723593e-06, "loss": 0.9732088470458984, "step": 594400 }, { "epoch": 6.84582228164429, "grad_norm": 0.91796875, "learning_rate": 9.960624481901077e-06, "loss": 0.9884004974365235, "step": 594600 }, { "epoch": 6.848124966719005, "grad_norm": 0.703125, "learning_rate": 9.953352918078563e-06, "loss": 0.9899817657470703, "step": 594800 }, { "epoch": 6.850427651793719, "grad_norm": 0.68359375, "learning_rate": 9.946081354256046e-06, "loss": 0.981840591430664, "step": 595000 }, { "epoch": 6.852730336868435, "grad_norm": 0.69140625, "learning_rate": 9.93880979043353e-06, "loss": 0.9764828491210937, "step": 595200 }, { "epoch": 6.855033021943149, "grad_norm": 0.55078125, "learning_rate": 9.931538226611016e-06, "loss": 0.9888670349121094, "step": 595400 }, { "epoch": 6.857335707017865, "grad_norm": 0.6953125, "learning_rate": 9.9242666627885e-06, "loss": 0.99365966796875, "step": 595600 }, { "epoch": 6.859638392092579, "grad_norm": 0.671875, "learning_rate": 9.916995098965984e-06, "loss": 0.9660527038574219, "step": 595800 }, { "epoch": 6.861941077167295, "grad_norm": 0.921875, "learning_rate": 9.909723535143468e-06, "loss": 0.9956941986083985, "step": 596000 }, { "epoch": 6.864243762242009, "grad_norm": 0.6796875, "learning_rate": 9.902451971320953e-06, "loss": 0.9861712646484375, "step": 596200 }, { "epoch": 6.866546447316725, "grad_norm": 1.234375, "learning_rate": 9.895180407498437e-06, "loss": 0.9897097778320313, "step": 596400 }, { "epoch": 6.868849132391439, "grad_norm": 0.578125, "learning_rate": 9.887908843675921e-06, "loss": 0.9684822845458985, "step": 596600 }, { "epoch": 6.8711518174661546, "grad_norm": 0.65625, "learning_rate": 9.880637279853405e-06, "loss": 0.9750865936279297, "step": 596800 }, { "epoch": 6.873454502540869, "grad_norm": 0.6015625, "learning_rate": 9.87336571603089e-06, "loss": 0.9999384307861328, "step": 597000 }, { "epoch": 6.875757187615584, "grad_norm": 0.56640625, "learning_rate": 9.866094152208374e-06, "loss": 0.9845417785644531, "step": 597200 }, { "epoch": 6.878059872690299, "grad_norm": 0.498046875, "learning_rate": 9.85882258838586e-06, "loss": 0.9779905700683593, "step": 597400 }, { "epoch": 6.880362557765014, "grad_norm": 0.6171875, "learning_rate": 9.851551024563342e-06, "loss": 0.9748655700683594, "step": 597600 }, { "epoch": 6.882665242839729, "grad_norm": 0.47265625, "learning_rate": 9.844279460740826e-06, "loss": 0.9606812286376953, "step": 597800 }, { "epoch": 6.884967927914444, "grad_norm": 0.45703125, "learning_rate": 9.837007896918312e-06, "loss": 0.9712443542480469, "step": 598000 }, { "epoch": 6.887270612989159, "grad_norm": 0.7421875, "learning_rate": 9.829736333095795e-06, "loss": 0.9712157440185547, "step": 598200 }, { "epoch": 6.8895732980638735, "grad_norm": 0.60546875, "learning_rate": 9.82246476927328e-06, "loss": 0.9641321563720703, "step": 598400 }, { "epoch": 6.891875983138588, "grad_norm": 0.66796875, "learning_rate": 9.815193205450765e-06, "loss": 0.9719064331054688, "step": 598600 }, { "epoch": 6.8941786682133035, "grad_norm": 0.53515625, "learning_rate": 9.807921641628247e-06, "loss": 0.9778326416015625, "step": 598800 }, { "epoch": 6.896481353288018, "grad_norm": 1.6328125, "learning_rate": 9.800650077805733e-06, "loss": 0.9895073699951172, "step": 599000 }, { "epoch": 6.8987840383627335, "grad_norm": 0.828125, "learning_rate": 9.793378513983218e-06, "loss": 0.9691558074951172, "step": 599200 }, { "epoch": 6.901086723437448, "grad_norm": 0.72265625, "learning_rate": 9.786106950160702e-06, "loss": 0.9776676940917969, "step": 599400 }, { "epoch": 6.903389408512163, "grad_norm": 0.79296875, "learning_rate": 9.778835386338186e-06, "loss": 0.9621530914306641, "step": 599600 }, { "epoch": 6.905692093586878, "grad_norm": 0.7890625, "learning_rate": 9.77156382251567e-06, "loss": 0.9924739074707031, "step": 599800 }, { "epoch": 6.907994778661593, "grad_norm": 0.609375, "learning_rate": 9.764292258693156e-06, "loss": 0.9811209869384766, "step": 600000 }, { "epoch": 6.910297463736308, "grad_norm": 0.63671875, "learning_rate": 9.757020694870639e-06, "loss": 0.9884233856201172, "step": 600200 }, { "epoch": 6.912600148811023, "grad_norm": 0.8671875, "learning_rate": 9.749749131048123e-06, "loss": 0.9793074798583984, "step": 600400 }, { "epoch": 6.914902833885738, "grad_norm": 0.43359375, "learning_rate": 9.742477567225609e-06, "loss": 0.9784436798095704, "step": 600600 }, { "epoch": 6.917205518960452, "grad_norm": 0.7421875, "learning_rate": 9.735206003403091e-06, "loss": 0.9627828979492188, "step": 600800 }, { "epoch": 6.919508204035168, "grad_norm": 0.76953125, "learning_rate": 9.727934439580576e-06, "loss": 0.9826019287109375, "step": 601000 }, { "epoch": 6.921810889109882, "grad_norm": 0.71484375, "learning_rate": 9.720662875758062e-06, "loss": 0.9585595703125, "step": 601200 }, { "epoch": 6.924113574184598, "grad_norm": 0.92578125, "learning_rate": 9.713391311935544e-06, "loss": 0.9860497283935546, "step": 601400 }, { "epoch": 6.926416259259312, "grad_norm": 0.83203125, "learning_rate": 9.70611974811303e-06, "loss": 0.9735778045654296, "step": 601600 }, { "epoch": 6.928718944334028, "grad_norm": 0.8359375, "learning_rate": 9.698848184290514e-06, "loss": 0.9859268951416016, "step": 601800 }, { "epoch": 6.931021629408742, "grad_norm": 0.8125, "learning_rate": 9.691576620467997e-06, "loss": 0.9492156219482422, "step": 602000 }, { "epoch": 6.933324314483457, "grad_norm": 0.498046875, "learning_rate": 9.684305056645483e-06, "loss": 0.988839111328125, "step": 602200 }, { "epoch": 6.935626999558172, "grad_norm": 0.890625, "learning_rate": 9.677033492822967e-06, "loss": 1.00001220703125, "step": 602400 }, { "epoch": 6.937929684632888, "grad_norm": 0.58203125, "learning_rate": 9.669761929000451e-06, "loss": 0.9814157104492187, "step": 602600 }, { "epoch": 6.940232369707602, "grad_norm": 0.66796875, "learning_rate": 9.662490365177935e-06, "loss": 0.9747137451171874, "step": 602800 }, { "epoch": 6.942535054782317, "grad_norm": 1.125, "learning_rate": 9.65521880135542e-06, "loss": 0.9681507873535157, "step": 603000 }, { "epoch": 6.944837739857032, "grad_norm": 0.490234375, "learning_rate": 9.647947237532905e-06, "loss": 0.9693973541259766, "step": 603200 }, { "epoch": 6.947140424931747, "grad_norm": 0.3984375, "learning_rate": 9.640675673710388e-06, "loss": 0.9954480743408203, "step": 603400 }, { "epoch": 6.949443110006462, "grad_norm": 0.84375, "learning_rate": 9.633404109887872e-06, "loss": 0.9874771881103516, "step": 603600 }, { "epoch": 6.951745795081177, "grad_norm": 0.58203125, "learning_rate": 9.626132546065358e-06, "loss": 0.9629541778564453, "step": 603800 }, { "epoch": 6.954048480155892, "grad_norm": 0.58984375, "learning_rate": 9.61886098224284e-06, "loss": 0.977274169921875, "step": 604000 }, { "epoch": 6.956351165230607, "grad_norm": 0.51953125, "learning_rate": 9.611589418420327e-06, "loss": 0.996618881225586, "step": 604200 }, { "epoch": 6.958653850305321, "grad_norm": 0.53515625, "learning_rate": 9.60431785459781e-06, "loss": 0.9640678405761719, "step": 604400 }, { "epoch": 6.960956535380037, "grad_norm": 0.8671875, "learning_rate": 9.597046290775293e-06, "loss": 0.9609552001953126, "step": 604600 }, { "epoch": 6.963259220454751, "grad_norm": 1.21875, "learning_rate": 9.58977472695278e-06, "loss": 0.9898723602294922, "step": 604800 }, { "epoch": 6.965561905529467, "grad_norm": 0.80859375, "learning_rate": 9.582503163130263e-06, "loss": 0.9942790985107421, "step": 605000 }, { "epoch": 6.967864590604181, "grad_norm": 0.55859375, "learning_rate": 9.575231599307746e-06, "loss": 0.9800389099121094, "step": 605200 }, { "epoch": 6.970167275678897, "grad_norm": 0.671875, "learning_rate": 9.567960035485232e-06, "loss": 0.9767919158935547, "step": 605400 }, { "epoch": 6.972469960753611, "grad_norm": 1.390625, "learning_rate": 9.560688471662716e-06, "loss": 0.9678658294677734, "step": 605600 }, { "epoch": 6.974772645828327, "grad_norm": 0.87890625, "learning_rate": 9.553416907840202e-06, "loss": 0.9765434265136719, "step": 605800 }, { "epoch": 6.977075330903041, "grad_norm": 0.67578125, "learning_rate": 9.546145344017684e-06, "loss": 0.9870706939697266, "step": 606000 }, { "epoch": 6.9793780159777565, "grad_norm": 0.67578125, "learning_rate": 9.538873780195169e-06, "loss": 0.9717103576660157, "step": 606200 }, { "epoch": 6.981680701052471, "grad_norm": 0.55859375, "learning_rate": 9.531602216372655e-06, "loss": 0.9808879089355469, "step": 606400 }, { "epoch": 6.983983386127186, "grad_norm": 0.435546875, "learning_rate": 9.524330652550137e-06, "loss": 1.0108739471435546, "step": 606600 }, { "epoch": 6.986286071201901, "grad_norm": 0.79296875, "learning_rate": 9.517059088727621e-06, "loss": 0.9731607818603516, "step": 606800 }, { "epoch": 6.988588756276616, "grad_norm": 0.494140625, "learning_rate": 9.509787524905107e-06, "loss": 0.9771558380126953, "step": 607000 }, { "epoch": 6.990891441351331, "grad_norm": 0.73046875, "learning_rate": 9.50251596108259e-06, "loss": 0.9768960571289063, "step": 607200 }, { "epoch": 6.9931941264260455, "grad_norm": 0.578125, "learning_rate": 9.495244397260076e-06, "loss": 0.986895523071289, "step": 607400 }, { "epoch": 6.995496811500761, "grad_norm": 0.75390625, "learning_rate": 9.48797283343756e-06, "loss": 0.9975414276123047, "step": 607600 }, { "epoch": 6.9977994965754755, "grad_norm": 0.6015625, "learning_rate": 9.480701269615042e-06, "loss": 1.000497055053711, "step": 607800 }, { "epoch": 7.0, "eval_loss": NaN, "eval_runtime": 430.5016, "eval_samples_per_second": 65.879, "eval_steps_per_second": 32.941, "step": 607992 }, { "epoch": 7.000092107402988, "grad_norm": 0.9296875, "learning_rate": 9.473429705792528e-06, "loss": 0.9825310516357422, "step": 608000 }, { "epoch": 7.002394792477704, "grad_norm": 0.90234375, "learning_rate": 9.466158141970013e-06, "loss": 0.9799756622314453, "step": 608200 }, { "epoch": 7.004697477552418, "grad_norm": 0.62890625, "learning_rate": 9.458886578147495e-06, "loss": 0.9800210571289063, "step": 608400 }, { "epoch": 7.007000162627134, "grad_norm": 0.63671875, "learning_rate": 9.451615014324981e-06, "loss": 0.9912975311279297, "step": 608600 }, { "epoch": 7.009302847701848, "grad_norm": 0.953125, "learning_rate": 9.444343450502465e-06, "loss": 0.9743272399902344, "step": 608800 }, { "epoch": 7.011605532776564, "grad_norm": 0.8984375, "learning_rate": 9.43707188667995e-06, "loss": 0.9799197387695312, "step": 609000 }, { "epoch": 7.013908217851278, "grad_norm": 0.5, "learning_rate": 9.429800322857434e-06, "loss": 0.9837110137939453, "step": 609200 }, { "epoch": 7.016210902925993, "grad_norm": 0.8984375, "learning_rate": 9.422528759034918e-06, "loss": 1.004596939086914, "step": 609400 }, { "epoch": 7.018513588000708, "grad_norm": 0.345703125, "learning_rate": 9.415257195212404e-06, "loss": 0.9808485412597656, "step": 609600 }, { "epoch": 7.020816273075423, "grad_norm": 0.73046875, "learning_rate": 9.407985631389886e-06, "loss": 0.9921746826171876, "step": 609800 }, { "epoch": 7.023118958150138, "grad_norm": 0.86328125, "learning_rate": 9.40071406756737e-06, "loss": 0.9875336456298828, "step": 610000 }, { "epoch": 7.025421643224853, "grad_norm": 0.59375, "learning_rate": 9.393442503744856e-06, "loss": 0.9784149932861328, "step": 610200 }, { "epoch": 7.027724328299568, "grad_norm": 0.71875, "learning_rate": 9.386170939922339e-06, "loss": 0.9732196044921875, "step": 610400 }, { "epoch": 7.030027013374283, "grad_norm": 1.34375, "learning_rate": 9.378899376099825e-06, "loss": 1.0045655822753907, "step": 610600 }, { "epoch": 7.032329698448998, "grad_norm": 0.84765625, "learning_rate": 9.371627812277309e-06, "loss": 0.9965348052978515, "step": 610800 }, { "epoch": 7.034632383523713, "grad_norm": 0.7734375, "learning_rate": 9.364356248454792e-06, "loss": 0.9734232330322266, "step": 611000 }, { "epoch": 7.036935068598428, "grad_norm": 0.7890625, "learning_rate": 9.357084684632278e-06, "loss": 0.9870662689208984, "step": 611200 }, { "epoch": 7.0392377536731425, "grad_norm": 0.61328125, "learning_rate": 9.349813120809762e-06, "loss": 0.9682694244384765, "step": 611400 }, { "epoch": 7.041540438747857, "grad_norm": 0.40234375, "learning_rate": 9.342541556987246e-06, "loss": 0.9698184967041016, "step": 611600 }, { "epoch": 7.0438431238225725, "grad_norm": 0.8515625, "learning_rate": 9.33526999316473e-06, "loss": 0.9657843780517578, "step": 611800 }, { "epoch": 7.046145808897287, "grad_norm": 0.6953125, "learning_rate": 9.327998429342214e-06, "loss": 0.9849095153808594, "step": 612000 }, { "epoch": 7.0484484939720025, "grad_norm": 0.73046875, "learning_rate": 9.320726865519699e-06, "loss": 0.9951589965820312, "step": 612200 }, { "epoch": 7.050751179046717, "grad_norm": 1.9375, "learning_rate": 9.313455301697183e-06, "loss": 0.9628787231445313, "step": 612400 }, { "epoch": 7.053053864121432, "grad_norm": 1.1328125, "learning_rate": 9.306183737874667e-06, "loss": 0.9930134582519531, "step": 612600 }, { "epoch": 7.055356549196147, "grad_norm": 0.796875, "learning_rate": 9.298912174052153e-06, "loss": 0.9693550872802734, "step": 612800 }, { "epoch": 7.057659234270862, "grad_norm": 0.416015625, "learning_rate": 9.291640610229636e-06, "loss": 0.9798488616943359, "step": 613000 }, { "epoch": 7.059961919345577, "grad_norm": 0.5390625, "learning_rate": 9.284369046407121e-06, "loss": 0.9596015167236328, "step": 613200 }, { "epoch": 7.0622646044202915, "grad_norm": 0.77734375, "learning_rate": 9.277097482584606e-06, "loss": 0.9790519714355469, "step": 613400 }, { "epoch": 7.064567289495007, "grad_norm": 0.95703125, "learning_rate": 9.269825918762088e-06, "loss": 0.9601467895507813, "step": 613600 }, { "epoch": 7.066869974569721, "grad_norm": 0.4609375, "learning_rate": 9.262554354939574e-06, "loss": 0.9998540496826172, "step": 613800 }, { "epoch": 7.069172659644437, "grad_norm": 0.5234375, "learning_rate": 9.255282791117058e-06, "loss": 0.9718901824951172, "step": 614000 }, { "epoch": 7.071475344719151, "grad_norm": 0.443359375, "learning_rate": 9.248011227294541e-06, "loss": 0.9607735443115234, "step": 614200 }, { "epoch": 7.073778029793867, "grad_norm": 0.97265625, "learning_rate": 9.240739663472027e-06, "loss": 0.9820717620849609, "step": 614400 }, { "epoch": 7.076080714868581, "grad_norm": 1.046875, "learning_rate": 9.233468099649511e-06, "loss": 0.9817266845703125, "step": 614600 }, { "epoch": 7.078383399943297, "grad_norm": 0.86328125, "learning_rate": 9.226196535826995e-06, "loss": 0.9754546356201171, "step": 614800 }, { "epoch": 7.080686085018011, "grad_norm": 0.83984375, "learning_rate": 9.21892497200448e-06, "loss": 0.9722274780273438, "step": 615000 }, { "epoch": 7.082988770092726, "grad_norm": 0.5078125, "learning_rate": 9.211653408181964e-06, "loss": 0.9742633056640625, "step": 615200 }, { "epoch": 7.085291455167441, "grad_norm": 0.81640625, "learning_rate": 9.204381844359448e-06, "loss": 0.961524658203125, "step": 615400 }, { "epoch": 7.087594140242156, "grad_norm": 0.75, "learning_rate": 9.197110280536932e-06, "loss": 0.9746446990966797, "step": 615600 }, { "epoch": 7.089896825316871, "grad_norm": 0.69140625, "learning_rate": 9.189838716714416e-06, "loss": 1.0018827056884765, "step": 615800 }, { "epoch": 7.092199510391586, "grad_norm": 1.0859375, "learning_rate": 9.182567152891902e-06, "loss": 0.9909403991699218, "step": 616000 }, { "epoch": 7.094502195466301, "grad_norm": 0.515625, "learning_rate": 9.175295589069385e-06, "loss": 0.9678092193603516, "step": 616200 }, { "epoch": 7.096804880541016, "grad_norm": 1.1015625, "learning_rate": 9.16802402524687e-06, "loss": 0.9697416687011718, "step": 616400 }, { "epoch": 7.099107565615731, "grad_norm": 1.5859375, "learning_rate": 9.160752461424355e-06, "loss": 0.9911090850830078, "step": 616600 }, { "epoch": 7.101410250690446, "grad_norm": 0.75, "learning_rate": 9.153480897601837e-06, "loss": 0.9620626068115234, "step": 616800 }, { "epoch": 7.10371293576516, "grad_norm": 0.59765625, "learning_rate": 9.146209333779323e-06, "loss": 0.9994487762451172, "step": 617000 }, { "epoch": 7.106015620839876, "grad_norm": 0.56640625, "learning_rate": 9.138937769956808e-06, "loss": 0.9509933471679688, "step": 617200 }, { "epoch": 7.10831830591459, "grad_norm": 0.703125, "learning_rate": 9.131666206134292e-06, "loss": 0.9687966918945312, "step": 617400 }, { "epoch": 7.110620990989306, "grad_norm": 3.984375, "learning_rate": 9.124394642311776e-06, "loss": 0.9788529968261719, "step": 617600 }, { "epoch": 7.11292367606402, "grad_norm": 1.1171875, "learning_rate": 9.11712307848926e-06, "loss": 0.9835548400878906, "step": 617800 }, { "epoch": 7.115226361138736, "grad_norm": 0.734375, "learning_rate": 9.109851514666744e-06, "loss": 1.001695556640625, "step": 618000 }, { "epoch": 7.11752904621345, "grad_norm": 1.125, "learning_rate": 9.102579950844229e-06, "loss": 0.989010238647461, "step": 618200 }, { "epoch": 7.119831731288166, "grad_norm": 0.765625, "learning_rate": 9.095308387021713e-06, "loss": 0.9796863555908203, "step": 618400 }, { "epoch": 7.12213441636288, "grad_norm": 0.53515625, "learning_rate": 9.088036823199197e-06, "loss": 1.0017696380615235, "step": 618600 }, { "epoch": 7.124437101437595, "grad_norm": 0.63671875, "learning_rate": 9.080765259376681e-06, "loss": 0.9877196502685547, "step": 618800 }, { "epoch": 7.12673978651231, "grad_norm": 0.890625, "learning_rate": 9.073493695554167e-06, "loss": 0.9870804595947266, "step": 619000 }, { "epoch": 7.129042471587025, "grad_norm": 0.77734375, "learning_rate": 9.066222131731651e-06, "loss": 0.9838044738769531, "step": 619200 }, { "epoch": 7.13134515666174, "grad_norm": 0.81640625, "learning_rate": 9.058950567909134e-06, "loss": 0.9858052825927734, "step": 619400 }, { "epoch": 7.133647841736455, "grad_norm": 0.63671875, "learning_rate": 9.05167900408662e-06, "loss": 0.9669033050537109, "step": 619600 }, { "epoch": 7.13595052681117, "grad_norm": 0.9765625, "learning_rate": 9.044407440264104e-06, "loss": 1.0087360382080077, "step": 619800 }, { "epoch": 7.138253211885885, "grad_norm": 1.0859375, "learning_rate": 9.037135876441587e-06, "loss": 0.995894775390625, "step": 620000 }, { "epoch": 7.1405558969606, "grad_norm": 0.83984375, "learning_rate": 9.029864312619073e-06, "loss": 0.9510137176513672, "step": 620200 }, { "epoch": 7.1428585820353145, "grad_norm": 0.58203125, "learning_rate": 9.022592748796557e-06, "loss": 0.9642363739013672, "step": 620400 }, { "epoch": 7.145161267110029, "grad_norm": 0.69140625, "learning_rate": 9.015321184974041e-06, "loss": 0.9794168090820312, "step": 620600 }, { "epoch": 7.1474639521847445, "grad_norm": 0.92578125, "learning_rate": 9.008049621151525e-06, "loss": 0.9878856658935546, "step": 620800 }, { "epoch": 7.149766637259459, "grad_norm": 0.6171875, "learning_rate": 9.00077805732901e-06, "loss": 0.982391357421875, "step": 621000 }, { "epoch": 7.1520693223341745, "grad_norm": 0.78125, "learning_rate": 8.993506493506494e-06, "loss": 0.9797698211669922, "step": 621200 }, { "epoch": 7.154372007408889, "grad_norm": 0.69140625, "learning_rate": 8.986234929683978e-06, "loss": 0.9885771942138671, "step": 621400 }, { "epoch": 7.156674692483604, "grad_norm": 0.69140625, "learning_rate": 8.978963365861462e-06, "loss": 0.9900411224365234, "step": 621600 }, { "epoch": 7.158977377558319, "grad_norm": 0.52734375, "learning_rate": 8.971691802038946e-06, "loss": 0.9649449157714843, "step": 621800 }, { "epoch": 7.161280062633034, "grad_norm": 1.28125, "learning_rate": 8.96442023821643e-06, "loss": 0.9854252624511719, "step": 622000 }, { "epoch": 7.163582747707749, "grad_norm": 1.1328125, "learning_rate": 8.957148674393916e-06, "loss": 0.9867980194091797, "step": 622200 }, { "epoch": 7.1658854327824635, "grad_norm": 0.6484375, "learning_rate": 8.949877110571399e-06, "loss": 0.9880463409423829, "step": 622400 }, { "epoch": 7.168188117857179, "grad_norm": 1.2734375, "learning_rate": 8.942605546748883e-06, "loss": 1.0098218536376953, "step": 622600 }, { "epoch": 7.1704908029318934, "grad_norm": 0.9453125, "learning_rate": 8.935333982926369e-06, "loss": 0.964631576538086, "step": 622800 }, { "epoch": 7.172793488006609, "grad_norm": 0.57421875, "learning_rate": 8.928062419103853e-06, "loss": 0.9773719787597657, "step": 623000 }, { "epoch": 7.175096173081323, "grad_norm": 0.70703125, "learning_rate": 8.920790855281336e-06, "loss": 0.9826641082763672, "step": 623200 }, { "epoch": 7.177398858156039, "grad_norm": 0.5625, "learning_rate": 8.913519291458822e-06, "loss": 0.9746383666992188, "step": 623400 }, { "epoch": 7.179701543230753, "grad_norm": 0.78515625, "learning_rate": 8.906247727636306e-06, "loss": 0.9711588287353515, "step": 623600 }, { "epoch": 7.182004228305469, "grad_norm": 1.0, "learning_rate": 8.89897616381379e-06, "loss": 0.9825574493408203, "step": 623800 }, { "epoch": 7.184306913380183, "grad_norm": 1.7890625, "learning_rate": 8.891704599991274e-06, "loss": 0.9776390075683594, "step": 624000 }, { "epoch": 7.186609598454898, "grad_norm": 0.90234375, "learning_rate": 8.884433036168759e-06, "loss": 0.9564485168457031, "step": 624200 }, { "epoch": 7.188912283529613, "grad_norm": 8.25, "learning_rate": 8.877161472346243e-06, "loss": 0.9756488037109375, "step": 624400 }, { "epoch": 7.191214968604328, "grad_norm": 0.7578125, "learning_rate": 8.869889908523727e-06, "loss": 0.9909695434570313, "step": 624600 }, { "epoch": 7.193517653679043, "grad_norm": 0.5234375, "learning_rate": 8.862618344701213e-06, "loss": 0.9954541015625, "step": 624800 }, { "epoch": 7.195820338753758, "grad_norm": 0.640625, "learning_rate": 8.855346780878695e-06, "loss": 0.9796237945556641, "step": 625000 }, { "epoch": 7.198123023828473, "grad_norm": 0.65625, "learning_rate": 8.84807521705618e-06, "loss": 0.9632915496826172, "step": 625200 }, { "epoch": 7.200425708903188, "grad_norm": 0.6484375, "learning_rate": 8.840803653233666e-06, "loss": 0.9457245635986328, "step": 625400 }, { "epoch": 7.202728393977903, "grad_norm": 1.7265625, "learning_rate": 8.833532089411148e-06, "loss": 0.9884097290039062, "step": 625600 }, { "epoch": 7.205031079052618, "grad_norm": 0.7734375, "learning_rate": 8.826260525588632e-06, "loss": 0.9882837677001953, "step": 625800 }, { "epoch": 7.207333764127332, "grad_norm": 0.734375, "learning_rate": 8.818988961766118e-06, "loss": 0.9795391845703125, "step": 626000 }, { "epoch": 7.209636449202048, "grad_norm": 0.50390625, "learning_rate": 8.811717397943602e-06, "loss": 0.9771727752685547, "step": 626200 }, { "epoch": 7.211939134276762, "grad_norm": 0.6484375, "learning_rate": 8.804445834121087e-06, "loss": 0.9845864868164063, "step": 626400 }, { "epoch": 7.214241819351478, "grad_norm": 0.8203125, "learning_rate": 8.797174270298571e-06, "loss": 0.9764852905273438, "step": 626600 }, { "epoch": 7.216544504426192, "grad_norm": 0.58984375, "learning_rate": 8.789902706476055e-06, "loss": 0.9779194641113281, "step": 626800 }, { "epoch": 7.218847189500908, "grad_norm": 0.71875, "learning_rate": 8.78263114265354e-06, "loss": 0.9794198608398438, "step": 627000 }, { "epoch": 7.221149874575622, "grad_norm": 0.7109375, "learning_rate": 8.775359578831024e-06, "loss": 0.9964470672607422, "step": 627200 }, { "epoch": 7.223452559650338, "grad_norm": 0.5390625, "learning_rate": 8.768088015008508e-06, "loss": 0.9815599822998047, "step": 627400 }, { "epoch": 7.225755244725052, "grad_norm": 0.55078125, "learning_rate": 8.760816451185992e-06, "loss": 0.9903423309326171, "step": 627600 }, { "epoch": 7.228057929799768, "grad_norm": 0.5625, "learning_rate": 8.753544887363476e-06, "loss": 0.9563906097412109, "step": 627800 }, { "epoch": 7.230360614874482, "grad_norm": 0.6953125, "learning_rate": 8.746273323540962e-06, "loss": 0.9850975036621094, "step": 628000 }, { "epoch": 7.232663299949197, "grad_norm": 0.4375, "learning_rate": 8.739001759718445e-06, "loss": 0.9879227447509765, "step": 628200 }, { "epoch": 7.234965985023912, "grad_norm": 0.72265625, "learning_rate": 8.731730195895929e-06, "loss": 0.9770551300048829, "step": 628400 }, { "epoch": 7.237268670098627, "grad_norm": 0.58203125, "learning_rate": 8.724458632073415e-06, "loss": 0.991946029663086, "step": 628600 }, { "epoch": 7.239571355173342, "grad_norm": 1.0390625, "learning_rate": 8.717187068250897e-06, "loss": 0.9801811218261719, "step": 628800 }, { "epoch": 7.241874040248057, "grad_norm": 0.515625, "learning_rate": 8.709915504428382e-06, "loss": 0.9778077697753906, "step": 629000 }, { "epoch": 7.244176725322772, "grad_norm": 0.470703125, "learning_rate": 8.702643940605867e-06, "loss": 0.9597901153564453, "step": 629200 }, { "epoch": 7.2464794103974866, "grad_norm": 0.734375, "learning_rate": 8.695372376783352e-06, "loss": 0.9801737976074218, "step": 629400 }, { "epoch": 7.248782095472202, "grad_norm": 1.203125, "learning_rate": 8.688100812960836e-06, "loss": 0.9846310424804687, "step": 629600 }, { "epoch": 7.2510847805469165, "grad_norm": 0.77734375, "learning_rate": 8.68082924913832e-06, "loss": 0.9861672973632812, "step": 629800 }, { "epoch": 7.253387465621631, "grad_norm": 0.609375, "learning_rate": 8.673557685315804e-06, "loss": 1.0003617095947266, "step": 630000 }, { "epoch": 7.2556901506963465, "grad_norm": 1.15625, "learning_rate": 8.666286121493289e-06, "loss": 0.9874579620361328, "step": 630200 }, { "epoch": 7.257992835771061, "grad_norm": 0.765625, "learning_rate": 8.659014557670773e-06, "loss": 0.9611412811279297, "step": 630400 }, { "epoch": 7.2602955208457765, "grad_norm": 0.423828125, "learning_rate": 8.651742993848257e-06, "loss": 0.98235107421875, "step": 630600 }, { "epoch": 7.262598205920491, "grad_norm": 0.66015625, "learning_rate": 8.644471430025741e-06, "loss": 0.9877023315429687, "step": 630800 }, { "epoch": 7.264900890995206, "grad_norm": 0.89453125, "learning_rate": 8.637199866203225e-06, "loss": 0.9970263671875, "step": 631000 }, { "epoch": 7.267203576069921, "grad_norm": 0.578125, "learning_rate": 8.629928302380711e-06, "loss": 0.9533394622802734, "step": 631200 }, { "epoch": 7.269506261144636, "grad_norm": 0.458984375, "learning_rate": 8.622656738558194e-06, "loss": 0.9910484313964844, "step": 631400 }, { "epoch": 7.271808946219351, "grad_norm": 0.65234375, "learning_rate": 8.615385174735678e-06, "loss": 0.9794743347167969, "step": 631600 }, { "epoch": 7.2741116312940655, "grad_norm": 0.86328125, "learning_rate": 8.608113610913164e-06, "loss": 0.9812853240966797, "step": 631800 }, { "epoch": 7.276414316368781, "grad_norm": 2.609375, "learning_rate": 8.600842047090647e-06, "loss": 0.9823606109619141, "step": 632000 }, { "epoch": 7.278717001443495, "grad_norm": 0.87109375, "learning_rate": 8.593570483268132e-06, "loss": 0.979590835571289, "step": 632200 }, { "epoch": 7.281019686518211, "grad_norm": 0.68359375, "learning_rate": 8.586298919445617e-06, "loss": 0.988263168334961, "step": 632400 }, { "epoch": 7.283322371592925, "grad_norm": 0.76171875, "learning_rate": 8.5790273556231e-06, "loss": 0.979410400390625, "step": 632600 }, { "epoch": 7.285625056667641, "grad_norm": 0.7265625, "learning_rate": 8.571755791800585e-06, "loss": 0.9735614776611328, "step": 632800 }, { "epoch": 7.287927741742355, "grad_norm": 0.478515625, "learning_rate": 8.56448422797807e-06, "loss": 1.0004599761962891, "step": 633000 }, { "epoch": 7.290230426817071, "grad_norm": 0.92578125, "learning_rate": 8.557212664155554e-06, "loss": 0.9967330932617188, "step": 633200 }, { "epoch": 7.292533111891785, "grad_norm": 0.56640625, "learning_rate": 8.549941100333038e-06, "loss": 0.9675569915771485, "step": 633400 }, { "epoch": 7.2948357969665, "grad_norm": 0.41015625, "learning_rate": 8.542669536510522e-06, "loss": 0.9942715454101563, "step": 633600 }, { "epoch": 7.297138482041215, "grad_norm": 0.63671875, "learning_rate": 8.535397972688008e-06, "loss": 0.9726704406738281, "step": 633800 }, { "epoch": 7.29944116711593, "grad_norm": 0.5859375, "learning_rate": 8.52812640886549e-06, "loss": 0.9834327697753906, "step": 634000 }, { "epoch": 7.301743852190645, "grad_norm": 0.609375, "learning_rate": 8.520854845042975e-06, "loss": 0.9955378723144531, "step": 634200 }, { "epoch": 7.30404653726536, "grad_norm": 0.66796875, "learning_rate": 8.51358328122046e-06, "loss": 0.9764264678955078, "step": 634400 }, { "epoch": 7.306349222340075, "grad_norm": 0.52734375, "learning_rate": 8.506311717397943e-06, "loss": 0.9716084289550782, "step": 634600 }, { "epoch": 7.30865190741479, "grad_norm": 0.54296875, "learning_rate": 8.499040153575427e-06, "loss": 0.9564635467529297, "step": 634800 }, { "epoch": 7.310954592489505, "grad_norm": 1.7109375, "learning_rate": 8.491768589752913e-06, "loss": 0.9855192565917968, "step": 635000 }, { "epoch": 7.31325727756422, "grad_norm": 0.77734375, "learning_rate": 8.484497025930396e-06, "loss": 0.9694292449951172, "step": 635200 }, { "epoch": 7.315559962638934, "grad_norm": 0.58984375, "learning_rate": 8.477225462107882e-06, "loss": 0.9754814910888672, "step": 635400 }, { "epoch": 7.31786264771365, "grad_norm": 0.71875, "learning_rate": 8.469953898285366e-06, "loss": 0.995964126586914, "step": 635600 }, { "epoch": 7.320165332788364, "grad_norm": 0.62890625, "learning_rate": 8.462682334462848e-06, "loss": 0.9831593322753907, "step": 635800 }, { "epoch": 7.32246801786308, "grad_norm": 0.5703125, "learning_rate": 8.455410770640334e-06, "loss": 0.994800796508789, "step": 636000 }, { "epoch": 7.324770702937794, "grad_norm": 0.7265625, "learning_rate": 8.448139206817819e-06, "loss": 0.9779727172851562, "step": 636200 }, { "epoch": 7.32707338801251, "grad_norm": 1.46875, "learning_rate": 8.440867642995303e-06, "loss": 0.9931973266601563, "step": 636400 }, { "epoch": 7.329376073087224, "grad_norm": 0.51953125, "learning_rate": 8.433596079172787e-06, "loss": 0.9613636779785156, "step": 636600 }, { "epoch": 7.33167875816194, "grad_norm": 0.5859375, "learning_rate": 8.426324515350271e-06, "loss": 0.9925965118408203, "step": 636800 }, { "epoch": 7.333981443236654, "grad_norm": 0.75390625, "learning_rate": 8.419052951527757e-06, "loss": 0.978579330444336, "step": 637000 }, { "epoch": 7.336284128311369, "grad_norm": 1.0234375, "learning_rate": 8.41178138770524e-06, "loss": 0.972872314453125, "step": 637200 }, { "epoch": 7.338586813386084, "grad_norm": 0.94140625, "learning_rate": 8.404509823882724e-06, "loss": 0.9567903900146484, "step": 637400 }, { "epoch": 7.340889498460799, "grad_norm": 0.5546875, "learning_rate": 8.39723826006021e-06, "loss": 0.9756443786621094, "step": 637600 }, { "epoch": 7.343192183535514, "grad_norm": 0.671875, "learning_rate": 8.389966696237692e-06, "loss": 1.0001806640625, "step": 637800 }, { "epoch": 7.345494868610229, "grad_norm": 0.62890625, "learning_rate": 8.382695132415178e-06, "loss": 0.9706695556640625, "step": 638000 }, { "epoch": 7.347797553684944, "grad_norm": 0.7265625, "learning_rate": 8.375423568592662e-06, "loss": 0.9860546112060546, "step": 638200 }, { "epoch": 7.350100238759659, "grad_norm": 2.03125, "learning_rate": 8.368152004770145e-06, "loss": 0.9711141204833984, "step": 638400 }, { "epoch": 7.352402923834374, "grad_norm": 0.466796875, "learning_rate": 8.360880440947631e-06, "loss": 0.9637662506103516, "step": 638600 }, { "epoch": 7.3547056089090885, "grad_norm": 0.470703125, "learning_rate": 8.353608877125115e-06, "loss": 1.0081533813476562, "step": 638800 }, { "epoch": 7.357008293983803, "grad_norm": 0.6796875, "learning_rate": 8.346337313302598e-06, "loss": 0.9800515747070313, "step": 639000 }, { "epoch": 7.3593109790585185, "grad_norm": 1.046875, "learning_rate": 8.339065749480084e-06, "loss": 0.9915232849121094, "step": 639200 }, { "epoch": 7.361613664133233, "grad_norm": 0.53515625, "learning_rate": 8.331794185657568e-06, "loss": 0.9679240417480469, "step": 639400 }, { "epoch": 7.3639163492079485, "grad_norm": 0.46484375, "learning_rate": 8.324522621835054e-06, "loss": 0.9997870635986328, "step": 639600 }, { "epoch": 7.366219034282663, "grad_norm": 0.69140625, "learning_rate": 8.317251058012536e-06, "loss": 0.9761660766601562, "step": 639800 }, { "epoch": 7.368521719357378, "grad_norm": 0.9140625, "learning_rate": 8.30997949419002e-06, "loss": 0.9725517272949219, "step": 640000 }, { "epoch": 7.370824404432093, "grad_norm": 0.70703125, "learning_rate": 8.302707930367506e-06, "loss": 0.9768034362792969, "step": 640200 }, { "epoch": 7.373127089506808, "grad_norm": 0.5625, "learning_rate": 8.295436366544989e-06, "loss": 0.997316665649414, "step": 640400 }, { "epoch": 7.375429774581523, "grad_norm": 0.51953125, "learning_rate": 8.288164802722473e-06, "loss": 0.9917243957519531, "step": 640600 }, { "epoch": 7.377732459656238, "grad_norm": 0.5390625, "learning_rate": 8.280893238899959e-06, "loss": 0.9770442962646484, "step": 640800 }, { "epoch": 7.380035144730953, "grad_norm": 0.5234375, "learning_rate": 8.273621675077442e-06, "loss": 0.9819647979736328, "step": 641000 }, { "epoch": 7.382337829805667, "grad_norm": 0.90625, "learning_rate": 8.266350111254927e-06, "loss": 0.9610335540771484, "step": 641200 }, { "epoch": 7.384640514880383, "grad_norm": 0.71484375, "learning_rate": 8.259078547432412e-06, "loss": 0.9789620971679688, "step": 641400 }, { "epoch": 7.386943199955097, "grad_norm": 0.5546875, "learning_rate": 8.251806983609894e-06, "loss": 0.9713826751708985, "step": 641600 }, { "epoch": 7.389245885029813, "grad_norm": 0.4296875, "learning_rate": 8.24453541978738e-06, "loss": 0.9683750152587891, "step": 641800 }, { "epoch": 7.391548570104527, "grad_norm": 0.84375, "learning_rate": 8.237263855964864e-06, "loss": 0.9706134796142578, "step": 642000 }, { "epoch": 7.393851255179243, "grad_norm": 0.62109375, "learning_rate": 8.229992292142347e-06, "loss": 0.9962574768066407, "step": 642200 }, { "epoch": 7.396153940253957, "grad_norm": 0.9296875, "learning_rate": 8.222720728319833e-06, "loss": 1.0055622100830077, "step": 642400 }, { "epoch": 7.398456625328672, "grad_norm": 0.46875, "learning_rate": 8.215449164497317e-06, "loss": 0.973365478515625, "step": 642600 }, { "epoch": 7.400759310403387, "grad_norm": 0.609375, "learning_rate": 8.208177600674803e-06, "loss": 0.9849382019042969, "step": 642800 }, { "epoch": 7.403061995478102, "grad_norm": 0.515625, "learning_rate": 8.200906036852285e-06, "loss": 0.9878323364257813, "step": 643000 }, { "epoch": 7.405364680552817, "grad_norm": 0.83984375, "learning_rate": 8.19363447302977e-06, "loss": 1.0094932556152343, "step": 643200 }, { "epoch": 7.407667365627532, "grad_norm": 0.671875, "learning_rate": 8.186362909207256e-06, "loss": 0.9762681579589844, "step": 643400 }, { "epoch": 7.409970050702247, "grad_norm": 2.25, "learning_rate": 8.179091345384738e-06, "loss": 0.9903445434570313, "step": 643600 }, { "epoch": 7.412272735776962, "grad_norm": 0.65625, "learning_rate": 8.171819781562222e-06, "loss": 0.9842520904541016, "step": 643800 }, { "epoch": 7.414575420851677, "grad_norm": 0.6953125, "learning_rate": 8.164548217739708e-06, "loss": 1.0014985656738282, "step": 644000 }, { "epoch": 7.416878105926392, "grad_norm": 1.0625, "learning_rate": 8.15727665391719e-06, "loss": 0.98802490234375, "step": 644200 }, { "epoch": 7.419180791001107, "grad_norm": 0.482421875, "learning_rate": 8.150005090094677e-06, "loss": 0.9854653930664062, "step": 644400 }, { "epoch": 7.421483476075822, "grad_norm": 0.9765625, "learning_rate": 8.14273352627216e-06, "loss": 0.9909928131103516, "step": 644600 }, { "epoch": 7.423786161150536, "grad_norm": 0.8046875, "learning_rate": 8.135461962449643e-06, "loss": 0.9801638031005859, "step": 644800 }, { "epoch": 7.426088846225252, "grad_norm": 0.765625, "learning_rate": 8.12819039862713e-06, "loss": 0.994657974243164, "step": 645000 }, { "epoch": 7.428391531299966, "grad_norm": 0.8359375, "learning_rate": 8.120918834804613e-06, "loss": 0.9822552490234375, "step": 645200 }, { "epoch": 7.430694216374682, "grad_norm": 0.70703125, "learning_rate": 8.113647270982098e-06, "loss": 0.965282211303711, "step": 645400 }, { "epoch": 7.432996901449396, "grad_norm": 0.95703125, "learning_rate": 8.106375707159582e-06, "loss": 0.9767619323730469, "step": 645600 }, { "epoch": 7.435299586524112, "grad_norm": 0.5390625, "learning_rate": 8.099104143337066e-06, "loss": 0.9821694946289062, "step": 645800 }, { "epoch": 7.437602271598826, "grad_norm": 0.7421875, "learning_rate": 8.09183257951455e-06, "loss": 0.9880028533935546, "step": 646000 }, { "epoch": 7.439904956673541, "grad_norm": 0.61328125, "learning_rate": 8.084561015692035e-06, "loss": 1.0000632476806641, "step": 646200 }, { "epoch": 7.442207641748256, "grad_norm": 0.66015625, "learning_rate": 8.077289451869519e-06, "loss": 0.9520333862304687, "step": 646400 }, { "epoch": 7.444510326822971, "grad_norm": 0.68359375, "learning_rate": 8.070017888047005e-06, "loss": 0.962379150390625, "step": 646600 }, { "epoch": 7.446813011897686, "grad_norm": 1.015625, "learning_rate": 8.062746324224487e-06, "loss": 0.9810494995117187, "step": 646800 }, { "epoch": 7.449115696972401, "grad_norm": 0.62890625, "learning_rate": 8.055474760401973e-06, "loss": 0.9787494659423828, "step": 647000 }, { "epoch": 7.451418382047116, "grad_norm": 0.84375, "learning_rate": 8.048203196579457e-06, "loss": 0.9649417877197266, "step": 647200 }, { "epoch": 7.453721067121831, "grad_norm": 1.0, "learning_rate": 8.04093163275694e-06, "loss": 0.9953223419189453, "step": 647400 }, { "epoch": 7.456023752196546, "grad_norm": 0.90625, "learning_rate": 8.033660068934426e-06, "loss": 0.9852490997314454, "step": 647600 }, { "epoch": 7.4583264372712605, "grad_norm": 0.8828125, "learning_rate": 8.02638850511191e-06, "loss": 0.9794223022460937, "step": 647800 }, { "epoch": 7.460629122345976, "grad_norm": 0.94921875, "learning_rate": 8.019116941289393e-06, "loss": 0.9743696594238281, "step": 648000 }, { "epoch": 7.4629318074206905, "grad_norm": 1.0234375, "learning_rate": 8.011845377466878e-06, "loss": 0.9630597686767578, "step": 648200 }, { "epoch": 7.465234492495405, "grad_norm": 0.7265625, "learning_rate": 8.004573813644363e-06, "loss": 0.9866986846923829, "step": 648400 }, { "epoch": 7.4675371775701205, "grad_norm": 0.765625, "learning_rate": 7.997302249821847e-06, "loss": 0.996558837890625, "step": 648600 }, { "epoch": 7.469839862644835, "grad_norm": 0.625, "learning_rate": 7.990030685999331e-06, "loss": 0.9859928894042969, "step": 648800 }, { "epoch": 7.47214254771955, "grad_norm": 0.859375, "learning_rate": 7.982759122176815e-06, "loss": 0.9754070281982422, "step": 649000 }, { "epoch": 7.474445232794265, "grad_norm": 0.70703125, "learning_rate": 7.9754875583543e-06, "loss": 1.0027849578857422, "step": 649200 }, { "epoch": 7.47674791786898, "grad_norm": 0.6875, "learning_rate": 7.968215994531784e-06, "loss": 0.968758316040039, "step": 649400 }, { "epoch": 7.479050602943695, "grad_norm": 0.7890625, "learning_rate": 7.960944430709268e-06, "loss": 0.9768476867675782, "step": 649600 }, { "epoch": 7.48135328801841, "grad_norm": 1.3671875, "learning_rate": 7.953672866886754e-06, "loss": 0.965670166015625, "step": 649800 }, { "epoch": 7.483655973093125, "grad_norm": 0.76953125, "learning_rate": 7.946401303064236e-06, "loss": 0.9942027282714844, "step": 650000 }, { "epoch": 7.4859586581678395, "grad_norm": 0.5625, "learning_rate": 7.939129739241722e-06, "loss": 0.9836433410644532, "step": 650200 }, { "epoch": 7.488261343242555, "grad_norm": 0.71484375, "learning_rate": 7.931858175419207e-06, "loss": 0.9702881622314453, "step": 650400 }, { "epoch": 7.490564028317269, "grad_norm": 0.78125, "learning_rate": 7.924586611596689e-06, "loss": 0.9784402465820312, "step": 650600 }, { "epoch": 7.492866713391985, "grad_norm": 0.486328125, "learning_rate": 7.917315047774175e-06, "loss": 1.0029482269287109, "step": 650800 }, { "epoch": 7.495169398466699, "grad_norm": 0.5546875, "learning_rate": 7.91004348395166e-06, "loss": 0.9745333099365234, "step": 651000 }, { "epoch": 7.497472083541415, "grad_norm": 0.6796875, "learning_rate": 7.902771920129143e-06, "loss": 0.9536399841308594, "step": 651200 }, { "epoch": 7.499774768616129, "grad_norm": 0.56640625, "learning_rate": 7.895500356306628e-06, "loss": 0.9742577362060547, "step": 651400 }, { "epoch": 7.502077453690845, "grad_norm": 0.58984375, "learning_rate": 7.888228792484112e-06, "loss": 0.9795113372802734, "step": 651600 }, { "epoch": 7.504380138765559, "grad_norm": 0.66015625, "learning_rate": 7.880957228661596e-06, "loss": 1.003966293334961, "step": 651800 }, { "epoch": 7.506682823840274, "grad_norm": 0.85546875, "learning_rate": 7.87368566483908e-06, "loss": 0.97415283203125, "step": 652000 }, { "epoch": 7.508985508914989, "grad_norm": 0.85546875, "learning_rate": 7.866414101016565e-06, "loss": 0.9731611633300781, "step": 652200 }, { "epoch": 7.511288193989704, "grad_norm": 0.87890625, "learning_rate": 7.859142537194049e-06, "loss": 0.983914566040039, "step": 652400 }, { "epoch": 7.513590879064419, "grad_norm": 0.51953125, "learning_rate": 7.851870973371533e-06, "loss": 0.9763735961914063, "step": 652600 }, { "epoch": 7.515893564139134, "grad_norm": 2.84375, "learning_rate": 7.844599409549019e-06, "loss": 0.969703140258789, "step": 652800 }, { "epoch": 7.518196249213849, "grad_norm": 0.447265625, "learning_rate": 7.837327845726503e-06, "loss": 0.9964493560791016, "step": 653000 }, { "epoch": 7.520498934288564, "grad_norm": 1.1484375, "learning_rate": 7.830056281903986e-06, "loss": 1.0019598388671875, "step": 653200 }, { "epoch": 7.522801619363279, "grad_norm": 0.8984375, "learning_rate": 7.822784718081472e-06, "loss": 0.9844602966308593, "step": 653400 }, { "epoch": 7.525104304437994, "grad_norm": 0.50390625, "learning_rate": 7.815513154258956e-06, "loss": 0.9833013153076172, "step": 653600 }, { "epoch": 7.527406989512709, "grad_norm": 0.8359375, "learning_rate": 7.808241590436438e-06, "loss": 0.9813348388671875, "step": 653800 }, { "epoch": 7.529709674587424, "grad_norm": 0.6640625, "learning_rate": 7.800970026613924e-06, "loss": 0.9650066375732422, "step": 654000 }, { "epoch": 7.532012359662138, "grad_norm": 0.51953125, "learning_rate": 7.793698462791408e-06, "loss": 0.9807217407226563, "step": 654200 }, { "epoch": 7.534315044736854, "grad_norm": 0.65625, "learning_rate": 7.786426898968893e-06, "loss": 0.9870914459228516, "step": 654400 }, { "epoch": 7.536617729811568, "grad_norm": 0.76171875, "learning_rate": 7.779155335146377e-06, "loss": 0.9670613098144532, "step": 654600 }, { "epoch": 7.538920414886284, "grad_norm": 1.03125, "learning_rate": 7.771883771323861e-06, "loss": 0.9968564605712891, "step": 654800 }, { "epoch": 7.541223099960998, "grad_norm": 0.859375, "learning_rate": 7.764612207501345e-06, "loss": 1.0076090240478515, "step": 655000 }, { "epoch": 7.543525785035714, "grad_norm": 0.82421875, "learning_rate": 7.75734064367883e-06, "loss": 0.987034912109375, "step": 655200 }, { "epoch": 7.545828470110428, "grad_norm": 1.28125, "learning_rate": 7.750069079856314e-06, "loss": 0.9792374420166016, "step": 655400 }, { "epoch": 7.548131155185143, "grad_norm": 0.625, "learning_rate": 7.742797516033798e-06, "loss": 1.0022062683105468, "step": 655600 }, { "epoch": 7.550433840259858, "grad_norm": 0.88671875, "learning_rate": 7.735525952211282e-06, "loss": 0.9784234619140625, "step": 655800 }, { "epoch": 7.552736525334573, "grad_norm": 1.0078125, "learning_rate": 7.728254388388768e-06, "loss": 0.9708540344238281, "step": 656000 }, { "epoch": 7.555039210409288, "grad_norm": 0.5625, "learning_rate": 7.72098282456625e-06, "loss": 0.9731727600097656, "step": 656200 }, { "epoch": 7.557341895484003, "grad_norm": 0.5234375, "learning_rate": 7.713711260743735e-06, "loss": 0.9630989074707031, "step": 656400 }, { "epoch": 7.559644580558718, "grad_norm": 0.6953125, "learning_rate": 7.70643969692122e-06, "loss": 0.9803575134277344, "step": 656600 }, { "epoch": 7.561947265633433, "grad_norm": 0.486328125, "learning_rate": 7.699168133098705e-06, "loss": 0.9948880004882813, "step": 656800 }, { "epoch": 7.564249950708148, "grad_norm": 0.66015625, "learning_rate": 7.691896569276188e-06, "loss": 0.9783583068847657, "step": 657000 }, { "epoch": 7.5665526357828625, "grad_norm": 0.953125, "learning_rate": 7.684625005453673e-06, "loss": 0.9461773681640625, "step": 657200 }, { "epoch": 7.568855320857578, "grad_norm": 0.6875, "learning_rate": 7.677353441631158e-06, "loss": 0.981177978515625, "step": 657400 }, { "epoch": 7.5711580059322925, "grad_norm": 0.84375, "learning_rate": 7.670081877808642e-06, "loss": 0.9690900421142579, "step": 657600 }, { "epoch": 7.573460691007007, "grad_norm": 0.48828125, "learning_rate": 7.662810313986126e-06, "loss": 0.9845625305175781, "step": 657800 }, { "epoch": 7.5757633760817225, "grad_norm": 0.66015625, "learning_rate": 7.65553875016361e-06, "loss": 0.9893363952636719, "step": 658000 }, { "epoch": 7.578066061156437, "grad_norm": 0.9453125, "learning_rate": 7.648267186341095e-06, "loss": 0.9911522674560547, "step": 658200 }, { "epoch": 7.580368746231152, "grad_norm": 0.408203125, "learning_rate": 7.640995622518579e-06, "loss": 0.9923857116699218, "step": 658400 }, { "epoch": 7.582671431305867, "grad_norm": 0.6796875, "learning_rate": 7.633724058696065e-06, "loss": 0.9609416961669922, "step": 658600 }, { "epoch": 7.584974116380582, "grad_norm": 0.77734375, "learning_rate": 7.626452494873547e-06, "loss": 0.9927304077148438, "step": 658800 }, { "epoch": 7.587276801455297, "grad_norm": 0.470703125, "learning_rate": 7.619180931051032e-06, "loss": 0.9676020812988281, "step": 659000 }, { "epoch": 7.5895794865300115, "grad_norm": 0.9140625, "learning_rate": 7.6119093672285165e-06, "loss": 0.991962890625, "step": 659200 }, { "epoch": 7.591882171604727, "grad_norm": 0.80078125, "learning_rate": 7.604637803406e-06, "loss": 0.98235107421875, "step": 659400 }, { "epoch": 7.594184856679441, "grad_norm": 0.64453125, "learning_rate": 7.597366239583485e-06, "loss": 0.9749604034423828, "step": 659600 }, { "epoch": 7.596487541754157, "grad_norm": 0.66796875, "learning_rate": 7.59009467576097e-06, "loss": 0.9732862091064454, "step": 659800 }, { "epoch": 7.598790226828871, "grad_norm": 0.8125, "learning_rate": 7.582823111938454e-06, "loss": 0.9805200958251953, "step": 660000 }, { "epoch": 7.601092911903587, "grad_norm": 0.60546875, "learning_rate": 7.5755515481159376e-06, "loss": 0.9868666839599609, "step": 660200 }, { "epoch": 7.603395596978301, "grad_norm": 0.59375, "learning_rate": 7.568279984293423e-06, "loss": 1.0004676055908204, "step": 660400 }, { "epoch": 7.605698282053017, "grad_norm": 1.1953125, "learning_rate": 7.561008420470908e-06, "loss": 0.9936216735839843, "step": 660600 }, { "epoch": 7.608000967127731, "grad_norm": 0.76171875, "learning_rate": 7.55373685664839e-06, "loss": 0.9566283416748047, "step": 660800 }, { "epoch": 7.610303652202447, "grad_norm": 0.49609375, "learning_rate": 7.546465292825875e-06, "loss": 0.9897992706298828, "step": 661000 }, { "epoch": 7.612606337277161, "grad_norm": 1.171875, "learning_rate": 7.53919372900336e-06, "loss": 0.9802947998046875, "step": 661200 }, { "epoch": 7.614909022351876, "grad_norm": 0.51953125, "learning_rate": 7.531922165180844e-06, "loss": 0.9826642608642578, "step": 661400 }, { "epoch": 7.617211707426591, "grad_norm": 0.89453125, "learning_rate": 7.524650601358328e-06, "loss": 0.9850830841064453, "step": 661600 }, { "epoch": 7.619514392501306, "grad_norm": 0.5625, "learning_rate": 7.517379037535813e-06, "loss": 0.9891217803955078, "step": 661800 }, { "epoch": 7.621817077576021, "grad_norm": 0.578125, "learning_rate": 7.510107473713296e-06, "loss": 0.996153335571289, "step": 662000 }, { "epoch": 7.624119762650736, "grad_norm": 0.640625, "learning_rate": 7.5028359098907815e-06, "loss": 0.9904628753662109, "step": 662200 }, { "epoch": 7.626422447725451, "grad_norm": 1.5078125, "learning_rate": 7.495564346068266e-06, "loss": 0.9812112426757813, "step": 662400 }, { "epoch": 7.628725132800166, "grad_norm": 0.453125, "learning_rate": 7.48829278224575e-06, "loss": 0.9918553161621094, "step": 662600 }, { "epoch": 7.63102781787488, "grad_norm": 0.69921875, "learning_rate": 7.481021218423234e-06, "loss": 0.9850691986083985, "step": 662800 }, { "epoch": 7.633330502949596, "grad_norm": 0.78125, "learning_rate": 7.473749654600719e-06, "loss": 0.9833558654785156, "step": 663000 }, { "epoch": 7.63563318802431, "grad_norm": 0.55078125, "learning_rate": 7.4664780907782026e-06, "loss": 0.980711669921875, "step": 663200 }, { "epoch": 7.637935873099026, "grad_norm": 1.0859375, "learning_rate": 7.459206526955687e-06, "loss": 0.9675973510742187, "step": 663400 }, { "epoch": 7.64023855817374, "grad_norm": 0.83203125, "learning_rate": 7.451934963133172e-06, "loss": 0.9979064178466797, "step": 663600 }, { "epoch": 7.642541243248456, "grad_norm": 1.0625, "learning_rate": 7.444663399310656e-06, "loss": 0.996081314086914, "step": 663800 }, { "epoch": 7.64484392832317, "grad_norm": 0.63671875, "learning_rate": 7.43739183548814e-06, "loss": 0.9812240600585938, "step": 664000 }, { "epoch": 7.647146613397886, "grad_norm": 0.671875, "learning_rate": 7.4301202716656245e-06, "loss": 0.986427993774414, "step": 664200 }, { "epoch": 7.6494492984726, "grad_norm": 0.73828125, "learning_rate": 7.422848707843109e-06, "loss": 0.9837487030029297, "step": 664400 }, { "epoch": 7.651751983547316, "grad_norm": 0.65234375, "learning_rate": 7.415577144020594e-06, "loss": 0.9797900390625, "step": 664600 }, { "epoch": 7.65405466862203, "grad_norm": 0.53515625, "learning_rate": 7.408305580198077e-06, "loss": 1.005549087524414, "step": 664800 }, { "epoch": 7.656357353696745, "grad_norm": 0.6796875, "learning_rate": 7.401034016375561e-06, "loss": 0.9849571228027344, "step": 665000 }, { "epoch": 7.65866003877146, "grad_norm": 0.6640625, "learning_rate": 7.3937624525530464e-06, "loss": 0.96781494140625, "step": 665200 }, { "epoch": 7.660962723846175, "grad_norm": 0.66015625, "learning_rate": 7.386490888730531e-06, "loss": 1.0096734619140626, "step": 665400 }, { "epoch": 7.66326540892089, "grad_norm": 0.73046875, "learning_rate": 7.379219324908016e-06, "loss": 0.9794087219238281, "step": 665600 }, { "epoch": 7.665568093995605, "grad_norm": 0.69140625, "learning_rate": 7.371947761085499e-06, "loss": 0.992833251953125, "step": 665800 }, { "epoch": 7.66787077907032, "grad_norm": 0.80859375, "learning_rate": 7.364676197262983e-06, "loss": 0.9783699035644531, "step": 666000 }, { "epoch": 7.6701734641450345, "grad_norm": 0.9453125, "learning_rate": 7.357404633440468e-06, "loss": 1.0216586303710937, "step": 666200 }, { "epoch": 7.672476149219749, "grad_norm": 0.91015625, "learning_rate": 7.350133069617953e-06, "loss": 0.9817404174804687, "step": 666400 }, { "epoch": 7.6747788342944645, "grad_norm": 0.515625, "learning_rate": 7.342861505795436e-06, "loss": 0.9726050567626953, "step": 666600 }, { "epoch": 7.677081519369179, "grad_norm": 0.578125, "learning_rate": 7.335589941972921e-06, "loss": 1.0005302429199219, "step": 666800 }, { "epoch": 7.6793842044438945, "grad_norm": 0.447265625, "learning_rate": 7.328318378150405e-06, "loss": 0.976294937133789, "step": 667000 }, { "epoch": 7.681686889518609, "grad_norm": 0.5078125, "learning_rate": 7.3210468143278895e-06, "loss": 0.9913665771484375, "step": 667200 }, { "epoch": 7.683989574593324, "grad_norm": 0.58984375, "learning_rate": 7.313775250505374e-06, "loss": 0.9836793518066407, "step": 667400 }, { "epoch": 7.686292259668039, "grad_norm": 0.48828125, "learning_rate": 7.306503686682858e-06, "loss": 0.9918992614746094, "step": 667600 }, { "epoch": 7.688594944742754, "grad_norm": 0.828125, "learning_rate": 7.299232122860343e-06, "loss": 0.9827339935302735, "step": 667800 }, { "epoch": 7.690897629817469, "grad_norm": 0.4921875, "learning_rate": 7.291960559037827e-06, "loss": 0.979901351928711, "step": 668000 }, { "epoch": 7.693200314892184, "grad_norm": 0.53125, "learning_rate": 7.284688995215311e-06, "loss": 0.992957992553711, "step": 668200 }, { "epoch": 7.695502999966899, "grad_norm": 1.796875, "learning_rate": 7.277417431392796e-06, "loss": 0.981059799194336, "step": 668400 }, { "epoch": 7.697805685041613, "grad_norm": 0.6171875, "learning_rate": 7.27014586757028e-06, "loss": 0.9890800476074219, "step": 668600 }, { "epoch": 7.700108370116329, "grad_norm": 0.625, "learning_rate": 7.262874303747764e-06, "loss": 0.9820852661132813, "step": 668800 }, { "epoch": 7.702411055191043, "grad_norm": 0.55859375, "learning_rate": 7.255602739925248e-06, "loss": 0.9690668487548828, "step": 669000 }, { "epoch": 7.704713740265759, "grad_norm": 0.484375, "learning_rate": 7.2483311761027325e-06, "loss": 0.9957647705078125, "step": 669200 }, { "epoch": 7.707016425340473, "grad_norm": 1.0625, "learning_rate": 7.241059612280218e-06, "loss": 1.0044274139404297, "step": 669400 }, { "epoch": 7.709319110415189, "grad_norm": 0.6484375, "learning_rate": 7.233788048457702e-06, "loss": 1.0007498168945312, "step": 669600 }, { "epoch": 7.711621795489903, "grad_norm": 0.640625, "learning_rate": 7.226516484635185e-06, "loss": 0.98791748046875, "step": 669800 }, { "epoch": 7.713924480564619, "grad_norm": 1.1484375, "learning_rate": 7.21924492081267e-06, "loss": 0.9789481353759766, "step": 670000 }, { "epoch": 7.716227165639333, "grad_norm": 0.83984375, "learning_rate": 7.2119733569901545e-06, "loss": 0.978783187866211, "step": 670200 }, { "epoch": 7.718529850714049, "grad_norm": 0.63671875, "learning_rate": 7.204701793167639e-06, "loss": 0.9658313751220703, "step": 670400 }, { "epoch": 7.720832535788763, "grad_norm": 0.68359375, "learning_rate": 7.197430229345123e-06, "loss": 0.9662199401855469, "step": 670600 }, { "epoch": 7.723135220863478, "grad_norm": 1.2734375, "learning_rate": 7.190158665522607e-06, "loss": 0.9699585723876953, "step": 670800 }, { "epoch": 7.725437905938193, "grad_norm": 0.53515625, "learning_rate": 7.182887101700092e-06, "loss": 0.9652238464355469, "step": 671000 }, { "epoch": 7.727740591012908, "grad_norm": 1.09375, "learning_rate": 7.175615537877576e-06, "loss": 1.00942138671875, "step": 671200 }, { "epoch": 7.730043276087623, "grad_norm": 1.0703125, "learning_rate": 7.16834397405506e-06, "loss": 0.9876091003417968, "step": 671400 }, { "epoch": 7.732345961162338, "grad_norm": 0.478515625, "learning_rate": 7.161072410232545e-06, "loss": 0.9880516052246093, "step": 671600 }, { "epoch": 7.734648646237053, "grad_norm": 0.92578125, "learning_rate": 7.153800846410029e-06, "loss": 0.9689411926269531, "step": 671800 }, { "epoch": 7.736951331311768, "grad_norm": 0.87109375, "learning_rate": 7.146529282587513e-06, "loss": 0.9719631958007813, "step": 672000 }, { "epoch": 7.739254016386482, "grad_norm": 0.7421875, "learning_rate": 7.139257718764998e-06, "loss": 0.9924961853027344, "step": 672200 }, { "epoch": 7.741556701461198, "grad_norm": 0.765625, "learning_rate": 7.131986154942482e-06, "loss": 0.9704615020751953, "step": 672400 }, { "epoch": 7.743859386535912, "grad_norm": 0.44140625, "learning_rate": 7.124714591119967e-06, "loss": 0.9846534729003906, "step": 672600 }, { "epoch": 7.746162071610628, "grad_norm": 0.68359375, "learning_rate": 7.117443027297451e-06, "loss": 0.9816999053955078, "step": 672800 }, { "epoch": 7.748464756685342, "grad_norm": 1.578125, "learning_rate": 7.110171463474935e-06, "loss": 0.9916375732421875, "step": 673000 }, { "epoch": 7.750767441760058, "grad_norm": 0.609375, "learning_rate": 7.1028998996524195e-06, "loss": 1.0035631561279297, "step": 673200 }, { "epoch": 7.753070126834772, "grad_norm": 0.83984375, "learning_rate": 7.095628335829904e-06, "loss": 0.9929666900634766, "step": 673400 }, { "epoch": 7.755372811909488, "grad_norm": 0.51953125, "learning_rate": 7.088356772007388e-06, "loss": 0.9711143493652343, "step": 673600 }, { "epoch": 7.757675496984202, "grad_norm": 0.875, "learning_rate": 7.081085208184873e-06, "loss": 0.9745367431640625, "step": 673800 }, { "epoch": 7.7599781820589175, "grad_norm": 0.55078125, "learning_rate": 7.073813644362356e-06, "loss": 0.982524642944336, "step": 674000 }, { "epoch": 7.762280867133632, "grad_norm": 1.203125, "learning_rate": 7.066542080539841e-06, "loss": 0.984613037109375, "step": 674200 }, { "epoch": 7.764583552208347, "grad_norm": 1.203125, "learning_rate": 7.059270516717326e-06, "loss": 0.9818270874023437, "step": 674400 }, { "epoch": 7.766886237283062, "grad_norm": 0.8125, "learning_rate": 7.05199895289481e-06, "loss": 0.9911299896240234, "step": 674600 }, { "epoch": 7.769188922357777, "grad_norm": 0.5546875, "learning_rate": 7.044727389072294e-06, "loss": 0.9584814453125, "step": 674800 }, { "epoch": 7.771491607432492, "grad_norm": 0.60546875, "learning_rate": 7.037455825249778e-06, "loss": 0.984047622680664, "step": 675000 }, { "epoch": 7.7737942925072065, "grad_norm": 0.6796875, "learning_rate": 7.0301842614272625e-06, "loss": 0.968690414428711, "step": 675200 }, { "epoch": 7.776096977581922, "grad_norm": 0.5703125, "learning_rate": 7.0229126976047476e-06, "loss": 1.0027845764160157, "step": 675400 }, { "epoch": 7.7783996626566365, "grad_norm": 1.3125, "learning_rate": 7.015641133782231e-06, "loss": 0.9877825164794922, "step": 675600 }, { "epoch": 7.780702347731351, "grad_norm": 0.84375, "learning_rate": 7.008369569959716e-06, "loss": 0.9784912109375, "step": 675800 }, { "epoch": 7.7830050328060665, "grad_norm": 0.5625, "learning_rate": 7.0010980061372e-06, "loss": 0.9643284606933594, "step": 676000 }, { "epoch": 7.785307717880781, "grad_norm": 1.1796875, "learning_rate": 6.9938264423146844e-06, "loss": 0.9686238098144532, "step": 676200 }, { "epoch": 7.7876104029554964, "grad_norm": 0.88671875, "learning_rate": 6.986554878492169e-06, "loss": 0.9636341857910157, "step": 676400 }, { "epoch": 7.789913088030211, "grad_norm": 0.53515625, "learning_rate": 6.979283314669653e-06, "loss": 0.9681974029541016, "step": 676600 }, { "epoch": 7.792215773104926, "grad_norm": 0.4375, "learning_rate": 6.972011750847137e-06, "loss": 0.9814032745361329, "step": 676800 }, { "epoch": 7.794518458179641, "grad_norm": 0.625, "learning_rate": 6.964740187024622e-06, "loss": 0.9747649383544922, "step": 677000 }, { "epoch": 7.796821143254356, "grad_norm": 0.578125, "learning_rate": 6.9574686232021055e-06, "loss": 0.9751251220703125, "step": 677200 }, { "epoch": 7.799123828329071, "grad_norm": 0.78125, "learning_rate": 6.95019705937959e-06, "loss": 1.0097690582275392, "step": 677400 }, { "epoch": 7.801426513403786, "grad_norm": 0.88671875, "learning_rate": 6.942925495557075e-06, "loss": 0.97711669921875, "step": 677600 }, { "epoch": 7.803729198478501, "grad_norm": 1.4765625, "learning_rate": 6.935653931734559e-06, "loss": 0.9708983612060547, "step": 677800 }, { "epoch": 7.806031883553215, "grad_norm": 1.0234375, "learning_rate": 6.928382367912043e-06, "loss": 0.9763180541992188, "step": 678000 }, { "epoch": 7.808334568627931, "grad_norm": 1.3359375, "learning_rate": 6.9211108040895275e-06, "loss": 0.9944866180419922, "step": 678200 }, { "epoch": 7.810637253702645, "grad_norm": 0.82421875, "learning_rate": 6.913839240267012e-06, "loss": 0.9518258666992188, "step": 678400 }, { "epoch": 7.812939938777361, "grad_norm": 0.984375, "learning_rate": 6.906567676444497e-06, "loss": 0.9801985931396484, "step": 678600 }, { "epoch": 7.815242623852075, "grad_norm": 0.61328125, "learning_rate": 6.899296112621981e-06, "loss": 1.0015017700195312, "step": 678800 }, { "epoch": 7.817545308926791, "grad_norm": 0.53515625, "learning_rate": 6.892024548799464e-06, "loss": 0.9830785369873047, "step": 679000 }, { "epoch": 7.819847994001505, "grad_norm": 0.671875, "learning_rate": 6.8847529849769494e-06, "loss": 0.962328872680664, "step": 679200 }, { "epoch": 7.82215067907622, "grad_norm": 0.45703125, "learning_rate": 6.877481421154434e-06, "loss": 0.9914726257324219, "step": 679400 }, { "epoch": 7.824453364150935, "grad_norm": 0.63671875, "learning_rate": 6.870209857331919e-06, "loss": 0.995595703125, "step": 679600 }, { "epoch": 7.82675604922565, "grad_norm": 0.5, "learning_rate": 6.862938293509402e-06, "loss": 1.0089399719238281, "step": 679800 }, { "epoch": 7.829058734300365, "grad_norm": 0.79296875, "learning_rate": 6.855666729686886e-06, "loss": 0.975849609375, "step": 680000 }, { "epoch": 7.83136141937508, "grad_norm": 1.0078125, "learning_rate": 6.848395165864371e-06, "loss": 0.9750611114501954, "step": 680200 }, { "epoch": 7.833664104449795, "grad_norm": 0.6953125, "learning_rate": 6.841123602041856e-06, "loss": 0.9694293212890625, "step": 680400 }, { "epoch": 7.83596678952451, "grad_norm": 0.5, "learning_rate": 6.833852038219339e-06, "loss": 0.992059326171875, "step": 680600 }, { "epoch": 7.838269474599225, "grad_norm": 0.75390625, "learning_rate": 6.826580474396824e-06, "loss": 0.9736553192138672, "step": 680800 }, { "epoch": 7.84057215967394, "grad_norm": 0.63671875, "learning_rate": 6.819308910574308e-06, "loss": 0.9563919830322266, "step": 681000 }, { "epoch": 7.842874844748655, "grad_norm": 0.453125, "learning_rate": 6.812037346751793e-06, "loss": 0.9833192443847656, "step": 681200 }, { "epoch": 7.84517752982337, "grad_norm": 0.796875, "learning_rate": 6.804765782929277e-06, "loss": 0.9806179809570312, "step": 681400 }, { "epoch": 7.847480214898084, "grad_norm": 0.6171875, "learning_rate": 6.797494219106761e-06, "loss": 0.9624887847900391, "step": 681600 }, { "epoch": 7.8497828999728, "grad_norm": 1.0234375, "learning_rate": 6.790222655284246e-06, "loss": 1.0056896209716797, "step": 681800 }, { "epoch": 7.852085585047514, "grad_norm": 0.6875, "learning_rate": 6.78295109146173e-06, "loss": 0.9849835968017578, "step": 682000 }, { "epoch": 7.85438827012223, "grad_norm": 0.68359375, "learning_rate": 6.7756795276392136e-06, "loss": 0.9797569274902344, "step": 682200 }, { "epoch": 7.856690955196944, "grad_norm": 1.234375, "learning_rate": 6.768407963816699e-06, "loss": 0.9842268371582031, "step": 682400 }, { "epoch": 7.85899364027166, "grad_norm": 0.73046875, "learning_rate": 6.761136399994183e-06, "loss": 0.9827518463134766, "step": 682600 }, { "epoch": 7.861296325346374, "grad_norm": 0.7265625, "learning_rate": 6.753864836171668e-06, "loss": 0.9835359954833984, "step": 682800 }, { "epoch": 7.863599010421089, "grad_norm": 1.6640625, "learning_rate": 6.746593272349151e-06, "loss": 0.9827082061767578, "step": 683000 }, { "epoch": 7.865901695495804, "grad_norm": 1.0, "learning_rate": 6.7393217085266355e-06, "loss": 0.9873677825927735, "step": 683200 }, { "epoch": 7.868204380570519, "grad_norm": 0.640625, "learning_rate": 6.7320501447041206e-06, "loss": 0.9825727081298828, "step": 683400 }, { "epoch": 7.870507065645234, "grad_norm": 0.404296875, "learning_rate": 6.724778580881605e-06, "loss": 0.9821214294433593, "step": 683600 }, { "epoch": 7.872809750719949, "grad_norm": 0.79296875, "learning_rate": 6.717507017059088e-06, "loss": 0.9567387390136719, "step": 683800 }, { "epoch": 7.875112435794664, "grad_norm": 0.455078125, "learning_rate": 6.710235453236573e-06, "loss": 0.9816065979003906, "step": 684000 }, { "epoch": 7.877415120869379, "grad_norm": 1.1328125, "learning_rate": 6.7029638894140575e-06, "loss": 1.004992218017578, "step": 684200 }, { "epoch": 7.879717805944094, "grad_norm": 0.625, "learning_rate": 6.6956923255915425e-06, "loss": 0.9947642517089844, "step": 684400 }, { "epoch": 7.8820204910188085, "grad_norm": 0.7578125, "learning_rate": 6.688420761769026e-06, "loss": 0.9833740234375, "step": 684600 }, { "epoch": 7.884323176093524, "grad_norm": 0.9140625, "learning_rate": 6.68114919794651e-06, "loss": 0.978486328125, "step": 684800 }, { "epoch": 7.8866258611682385, "grad_norm": 0.828125, "learning_rate": 6.673877634123995e-06, "loss": 0.9901490020751953, "step": 685000 }, { "epoch": 7.888928546242953, "grad_norm": 0.59375, "learning_rate": 6.666606070301479e-06, "loss": 0.9926892852783203, "step": 685200 }, { "epoch": 7.8912312313176685, "grad_norm": 0.58984375, "learning_rate": 6.659334506478963e-06, "loss": 0.9790725708007812, "step": 685400 }, { "epoch": 7.893533916392383, "grad_norm": 0.498046875, "learning_rate": 6.652062942656448e-06, "loss": 0.9824659729003906, "step": 685600 }, { "epoch": 7.895836601467098, "grad_norm": 0.447265625, "learning_rate": 6.644791378833932e-06, "loss": 0.9952230834960938, "step": 685800 }, { "epoch": 7.898139286541813, "grad_norm": 1.1015625, "learning_rate": 6.637519815011417e-06, "loss": 0.9813288116455078, "step": 686000 }, { "epoch": 7.900441971616528, "grad_norm": 1.0546875, "learning_rate": 6.630248251188901e-06, "loss": 0.9603262329101563, "step": 686200 }, { "epoch": 7.902744656691243, "grad_norm": 0.66015625, "learning_rate": 6.622976687366385e-06, "loss": 0.9719887542724609, "step": 686400 }, { "epoch": 7.9050473417659575, "grad_norm": 0.65625, "learning_rate": 6.61570512354387e-06, "loss": 0.9816300964355469, "step": 686600 }, { "epoch": 7.907350026840673, "grad_norm": 0.62109375, "learning_rate": 6.608433559721354e-06, "loss": 0.9870523834228515, "step": 686800 }, { "epoch": 7.909652711915388, "grad_norm": 0.87109375, "learning_rate": 6.601161995898838e-06, "loss": 0.9839715576171875, "step": 687000 }, { "epoch": 7.911955396990103, "grad_norm": 1.046875, "learning_rate": 6.5938904320763224e-06, "loss": 0.9607354736328125, "step": 687200 }, { "epoch": 7.914258082064817, "grad_norm": 0.6875, "learning_rate": 6.586618868253807e-06, "loss": 0.9836206817626953, "step": 687400 }, { "epoch": 7.916560767139533, "grad_norm": 0.95703125, "learning_rate": 6.579347304431292e-06, "loss": 0.9973263549804687, "step": 687600 }, { "epoch": 7.918863452214247, "grad_norm": 0.6640625, "learning_rate": 6.572075740608776e-06, "loss": 0.9725442504882813, "step": 687800 }, { "epoch": 7.921166137288963, "grad_norm": 0.55078125, "learning_rate": 6.564804176786259e-06, "loss": 0.9735817718505859, "step": 688000 }, { "epoch": 7.923468822363677, "grad_norm": 0.498046875, "learning_rate": 6.557532612963744e-06, "loss": 0.9831144714355469, "step": 688200 }, { "epoch": 7.925771507438393, "grad_norm": 0.625, "learning_rate": 6.550261049141229e-06, "loss": 0.9740536499023438, "step": 688400 }, { "epoch": 7.928074192513107, "grad_norm": 0.75, "learning_rate": 6.542989485318713e-06, "loss": 0.9716651153564453, "step": 688600 }, { "epoch": 7.930376877587822, "grad_norm": 0.8359375, "learning_rate": 6.535717921496197e-06, "loss": 0.9694881439208984, "step": 688800 }, { "epoch": 7.932679562662537, "grad_norm": 0.9609375, "learning_rate": 6.528446357673681e-06, "loss": 0.9982528686523438, "step": 689000 }, { "epoch": 7.934982247737252, "grad_norm": 0.61328125, "learning_rate": 6.5211747938511655e-06, "loss": 0.9639457702636719, "step": 689200 }, { "epoch": 7.937284932811967, "grad_norm": 0.61328125, "learning_rate": 6.5139032300286505e-06, "loss": 0.9916056823730469, "step": 689400 }, { "epoch": 7.939587617886682, "grad_norm": 0.6171875, "learning_rate": 6.506631666206134e-06, "loss": 0.964366683959961, "step": 689600 }, { "epoch": 7.941890302961397, "grad_norm": 1.03125, "learning_rate": 6.499360102383619e-06, "loss": 0.998613510131836, "step": 689800 }, { "epoch": 7.944192988036112, "grad_norm": 0.388671875, "learning_rate": 6.492088538561103e-06, "loss": 0.9819116973876953, "step": 690000 }, { "epoch": 7.946495673110827, "grad_norm": 0.546875, "learning_rate": 6.484816974738587e-06, "loss": 0.992962875366211, "step": 690200 }, { "epoch": 7.948798358185542, "grad_norm": 0.490234375, "learning_rate": 6.477545410916072e-06, "loss": 0.9869437408447266, "step": 690400 }, { "epoch": 7.951101043260257, "grad_norm": 0.546875, "learning_rate": 6.470273847093556e-06, "loss": 0.9729832458496094, "step": 690600 }, { "epoch": 7.953403728334972, "grad_norm": 1.1171875, "learning_rate": 6.46300228327104e-06, "loss": 0.9928602600097656, "step": 690800 }, { "epoch": 7.955706413409686, "grad_norm": 1.0546875, "learning_rate": 6.455730719448525e-06, "loss": 0.9930166625976562, "step": 691000 }, { "epoch": 7.958009098484402, "grad_norm": 0.76953125, "learning_rate": 6.4484591556260085e-06, "loss": 0.9928379058837891, "step": 691200 }, { "epoch": 7.960311783559116, "grad_norm": 0.40234375, "learning_rate": 6.441187591803494e-06, "loss": 0.9737590026855468, "step": 691400 }, { "epoch": 7.962614468633832, "grad_norm": 0.64453125, "learning_rate": 6.433916027980978e-06, "loss": 0.9859085845947265, "step": 691600 }, { "epoch": 7.964917153708546, "grad_norm": 0.578125, "learning_rate": 6.426644464158462e-06, "loss": 0.9696751403808593, "step": 691800 }, { "epoch": 7.967219838783262, "grad_norm": 0.78515625, "learning_rate": 6.419372900335946e-06, "loss": 0.9876094818115234, "step": 692000 }, { "epoch": 7.969522523857976, "grad_norm": 0.828125, "learning_rate": 6.4121013365134305e-06, "loss": 0.9785052490234375, "step": 692200 }, { "epoch": 7.971825208932691, "grad_norm": 0.74609375, "learning_rate": 6.404829772690915e-06, "loss": 0.9876641082763672, "step": 692400 }, { "epoch": 7.974127894007406, "grad_norm": 0.63671875, "learning_rate": 6.3975582088684e-06, "loss": 0.9774613189697265, "step": 692600 }, { "epoch": 7.976430579082121, "grad_norm": 0.5234375, "learning_rate": 6.390286645045884e-06, "loss": 1.0123577880859376, "step": 692800 }, { "epoch": 7.978733264156836, "grad_norm": 0.98046875, "learning_rate": 6.383015081223368e-06, "loss": 0.9731853485107422, "step": 693000 }, { "epoch": 7.981035949231551, "grad_norm": 0.83203125, "learning_rate": 6.375743517400852e-06, "loss": 0.9835764312744141, "step": 693200 }, { "epoch": 7.983338634306266, "grad_norm": 0.8359375, "learning_rate": 6.368471953578337e-06, "loss": 0.9932479095458985, "step": 693400 }, { "epoch": 7.9856413193809805, "grad_norm": 0.6875, "learning_rate": 6.361200389755822e-06, "loss": 0.950868911743164, "step": 693600 }, { "epoch": 7.987944004455696, "grad_norm": 1.15625, "learning_rate": 6.353928825933305e-06, "loss": 0.9951741027832032, "step": 693800 }, { "epoch": 7.9902466895304105, "grad_norm": 0.50390625, "learning_rate": 6.346657262110789e-06, "loss": 1.0014451599121095, "step": 694000 }, { "epoch": 7.992549374605126, "grad_norm": 0.81640625, "learning_rate": 6.339385698288274e-06, "loss": 0.989116439819336, "step": 694200 }, { "epoch": 7.9948520596798405, "grad_norm": 0.59765625, "learning_rate": 6.3321141344657586e-06, "loss": 0.9893257904052735, "step": 694400 }, { "epoch": 7.997154744754555, "grad_norm": 3.4375, "learning_rate": 6.324842570643243e-06, "loss": 0.9822025299072266, "step": 694600 }, { "epoch": 7.99945742982927, "grad_norm": 0.51171875, "learning_rate": 6.317571006820727e-06, "loss": 0.9817815399169922, "step": 694800 }, { "epoch": 8.0, "eval_loss": NaN, "eval_runtime": 428.7338, "eval_samples_per_second": 66.151, "eval_steps_per_second": 33.076, "step": 694848 }, { "epoch": 8.001750040656784, "grad_norm": 0.76953125, "learning_rate": 6.310299442998211e-06, "loss": 0.9696829223632812, "step": 695000 }, { "epoch": 8.004052725731498, "grad_norm": 0.61328125, "learning_rate": 6.303027879175696e-06, "loss": 0.9977623748779297, "step": 695200 }, { "epoch": 8.006355410806213, "grad_norm": 0.439453125, "learning_rate": 6.29575631535318e-06, "loss": 0.9823947143554688, "step": 695400 }, { "epoch": 8.008658095880929, "grad_norm": 0.65234375, "learning_rate": 6.288484751530664e-06, "loss": 0.9951921081542969, "step": 695600 }, { "epoch": 8.010960780955642, "grad_norm": 0.546875, "learning_rate": 6.281213187708149e-06, "loss": 0.9983968353271484, "step": 695800 }, { "epoch": 8.013263466030358, "grad_norm": 0.76953125, "learning_rate": 6.273941623885633e-06, "loss": 0.9798602294921875, "step": 696000 }, { "epoch": 8.015566151105073, "grad_norm": 0.578125, "learning_rate": 6.266670060063117e-06, "loss": 1.0001656341552734, "step": 696200 }, { "epoch": 8.017868836179789, "grad_norm": 0.70703125, "learning_rate": 6.259398496240602e-06, "loss": 0.9662248229980469, "step": 696400 }, { "epoch": 8.020171521254502, "grad_norm": 0.54296875, "learning_rate": 6.252126932418086e-06, "loss": 0.9670308685302734, "step": 696600 }, { "epoch": 8.022474206329218, "grad_norm": 0.71484375, "learning_rate": 6.244855368595571e-06, "loss": 0.9894591522216797, "step": 696800 }, { "epoch": 8.024776891403933, "grad_norm": 0.5625, "learning_rate": 6.237583804773054e-06, "loss": 0.9984318542480469, "step": 697000 }, { "epoch": 8.027079576478648, "grad_norm": 0.98828125, "learning_rate": 6.2303122409505385e-06, "loss": 0.9907484436035157, "step": 697200 }, { "epoch": 8.029382261553362, "grad_norm": 0.74609375, "learning_rate": 6.2230406771280236e-06, "loss": 0.9838898468017578, "step": 697400 }, { "epoch": 8.031684946628078, "grad_norm": 0.51953125, "learning_rate": 6.215769113305508e-06, "loss": 0.9810810852050781, "step": 697600 }, { "epoch": 8.033987631702793, "grad_norm": 0.5703125, "learning_rate": 6.208497549482992e-06, "loss": 0.968192138671875, "step": 697800 }, { "epoch": 8.036290316777507, "grad_norm": 0.50390625, "learning_rate": 6.201225985660476e-06, "loss": 0.9575815582275391, "step": 698000 }, { "epoch": 8.038593001852222, "grad_norm": 0.84765625, "learning_rate": 6.1939544218379604e-06, "loss": 0.9703910827636719, "step": 698200 }, { "epoch": 8.040895686926937, "grad_norm": 1.15625, "learning_rate": 6.1866828580154455e-06, "loss": 0.989373779296875, "step": 698400 }, { "epoch": 8.043198372001653, "grad_norm": 1.0234375, "learning_rate": 6.179411294192929e-06, "loss": 0.9677561950683594, "step": 698600 }, { "epoch": 8.045501057076367, "grad_norm": 0.6484375, "learning_rate": 6.172139730370413e-06, "loss": 0.9914716339111328, "step": 698800 }, { "epoch": 8.047803742151082, "grad_norm": 1.0546875, "learning_rate": 6.164868166547898e-06, "loss": 0.9957130432128907, "step": 699000 }, { "epoch": 8.050106427225797, "grad_norm": 0.6640625, "learning_rate": 6.157596602725382e-06, "loss": 0.9571633148193359, "step": 699200 }, { "epoch": 8.052409112300511, "grad_norm": 0.59765625, "learning_rate": 6.150325038902867e-06, "loss": 0.9698536682128907, "step": 699400 }, { "epoch": 8.054711797375226, "grad_norm": 0.48828125, "learning_rate": 6.143053475080351e-06, "loss": 0.965628662109375, "step": 699600 }, { "epoch": 8.057014482449942, "grad_norm": 0.5078125, "learning_rate": 6.135781911257835e-06, "loss": 0.9815982818603516, "step": 699800 }, { "epoch": 8.059317167524657, "grad_norm": 0.8828125, "learning_rate": 6.12851034743532e-06, "loss": 0.9958517456054687, "step": 700000 }, { "epoch": 8.061619852599371, "grad_norm": 0.9375, "learning_rate": 6.121238783612804e-06, "loss": 0.9758916473388672, "step": 700200 }, { "epoch": 8.063922537674086, "grad_norm": 0.984375, "learning_rate": 6.113967219790288e-06, "loss": 0.9970526123046874, "step": 700400 }, { "epoch": 8.066225222748802, "grad_norm": 0.76953125, "learning_rate": 6.106695655967773e-06, "loss": 0.9790088653564453, "step": 700600 }, { "epoch": 8.068527907823517, "grad_norm": 0.5, "learning_rate": 6.099424092145257e-06, "loss": 0.9624451446533203, "step": 700800 }, { "epoch": 8.070830592898231, "grad_norm": 0.58984375, "learning_rate": 6.092152528322741e-06, "loss": 0.9581060028076172, "step": 701000 }, { "epoch": 8.073133277972946, "grad_norm": 0.87890625, "learning_rate": 6.084880964500225e-06, "loss": 0.9783612060546875, "step": 701200 }, { "epoch": 8.075435963047662, "grad_norm": 1.2578125, "learning_rate": 6.07760940067771e-06, "loss": 1.001886444091797, "step": 701400 }, { "epoch": 8.077738648122375, "grad_norm": 0.46484375, "learning_rate": 6.070337836855195e-06, "loss": 0.9688577270507812, "step": 701600 }, { "epoch": 8.08004133319709, "grad_norm": 0.83984375, "learning_rate": 6.063066273032679e-06, "loss": 0.96413330078125, "step": 701800 }, { "epoch": 8.082344018271806, "grad_norm": 0.66796875, "learning_rate": 6.055794709210162e-06, "loss": 0.9906436157226562, "step": 702000 }, { "epoch": 8.084646703346522, "grad_norm": 0.62109375, "learning_rate": 6.048523145387647e-06, "loss": 0.9788544464111328, "step": 702200 }, { "epoch": 8.086949388421235, "grad_norm": 0.6171875, "learning_rate": 6.041251581565132e-06, "loss": 0.9843678283691406, "step": 702400 }, { "epoch": 8.08925207349595, "grad_norm": 0.59375, "learning_rate": 6.033980017742616e-06, "loss": 0.9825135040283203, "step": 702600 }, { "epoch": 8.091554758570666, "grad_norm": 0.96875, "learning_rate": 6.0267084539201e-06, "loss": 0.991893310546875, "step": 702800 }, { "epoch": 8.093857443645382, "grad_norm": 0.765625, "learning_rate": 6.019436890097584e-06, "loss": 0.987342300415039, "step": 703000 }, { "epoch": 8.096160128720095, "grad_norm": 0.65625, "learning_rate": 6.012165326275069e-06, "loss": 1.0043768310546874, "step": 703200 }, { "epoch": 8.09846281379481, "grad_norm": 0.73046875, "learning_rate": 6.0048937624525535e-06, "loss": 0.979031753540039, "step": 703400 }, { "epoch": 8.100765498869526, "grad_norm": 0.75, "learning_rate": 5.997622198630037e-06, "loss": 0.9823381805419922, "step": 703600 }, { "epoch": 8.10306818394424, "grad_norm": 1.625, "learning_rate": 5.990350634807522e-06, "loss": 0.9878911590576172, "step": 703800 }, { "epoch": 8.105370869018955, "grad_norm": 0.921875, "learning_rate": 5.983079070985006e-06, "loss": 0.981031265258789, "step": 704000 }, { "epoch": 8.10767355409367, "grad_norm": 1.046875, "learning_rate": 5.97580750716249e-06, "loss": 0.9635255432128906, "step": 704200 }, { "epoch": 8.109976239168386, "grad_norm": 2.71875, "learning_rate": 5.968535943339975e-06, "loss": 0.9721682739257812, "step": 704400 }, { "epoch": 8.1122789242431, "grad_norm": 0.7265625, "learning_rate": 5.961264379517459e-06, "loss": 0.987343521118164, "step": 704600 }, { "epoch": 8.114581609317815, "grad_norm": 0.51953125, "learning_rate": 5.953992815694944e-06, "loss": 0.9890452575683594, "step": 704800 }, { "epoch": 8.11688429439253, "grad_norm": 0.890625, "learning_rate": 5.946721251872428e-06, "loss": 0.9851099395751953, "step": 705000 }, { "epoch": 8.119186979467244, "grad_norm": 0.73046875, "learning_rate": 5.9394496880499115e-06, "loss": 0.9777668762207031, "step": 705200 }, { "epoch": 8.12148966454196, "grad_norm": 0.578125, "learning_rate": 5.9321781242273966e-06, "loss": 0.9775521087646485, "step": 705400 }, { "epoch": 8.123792349616675, "grad_norm": 0.51953125, "learning_rate": 5.924906560404881e-06, "loss": 0.9734044647216797, "step": 705600 }, { "epoch": 8.12609503469139, "grad_norm": 0.8515625, "learning_rate": 5.917634996582365e-06, "loss": 0.9939882659912109, "step": 705800 }, { "epoch": 8.128397719766104, "grad_norm": 0.6171875, "learning_rate": 5.910363432759849e-06, "loss": 0.9817446899414063, "step": 706000 }, { "epoch": 8.13070040484082, "grad_norm": 0.79296875, "learning_rate": 5.9030918689373334e-06, "loss": 0.9877121734619141, "step": 706200 }, { "epoch": 8.133003089915535, "grad_norm": 0.8046875, "learning_rate": 5.8958203051148185e-06, "loss": 0.9951105499267578, "step": 706400 }, { "epoch": 8.13530577499025, "grad_norm": 0.609375, "learning_rate": 5.888548741292303e-06, "loss": 0.9965312194824218, "step": 706600 }, { "epoch": 8.137608460064964, "grad_norm": 0.61328125, "learning_rate": 5.881277177469787e-06, "loss": 0.9727510833740234, "step": 706800 }, { "epoch": 8.13991114513968, "grad_norm": 0.72265625, "learning_rate": 5.874005613647271e-06, "loss": 0.9715268707275391, "step": 707000 }, { "epoch": 8.142213830214395, "grad_norm": 0.58203125, "learning_rate": 5.866734049824755e-06, "loss": 0.9857926940917969, "step": 707200 }, { "epoch": 8.144516515289109, "grad_norm": 0.81640625, "learning_rate": 5.85946248600224e-06, "loss": 0.9734233093261718, "step": 707400 }, { "epoch": 8.146819200363824, "grad_norm": 0.76171875, "learning_rate": 5.852190922179725e-06, "loss": 0.9755318450927735, "step": 707600 }, { "epoch": 8.14912188543854, "grad_norm": 0.5234375, "learning_rate": 5.844919358357208e-06, "loss": 0.9818879699707032, "step": 707800 }, { "epoch": 8.151424570513255, "grad_norm": 1.1015625, "learning_rate": 5.837647794534693e-06, "loss": 0.9886809539794922, "step": 708000 }, { "epoch": 8.153727255587969, "grad_norm": 0.734375, "learning_rate": 5.830376230712177e-06, "loss": 0.981470947265625, "step": 708200 }, { "epoch": 8.156029940662684, "grad_norm": 0.6015625, "learning_rate": 5.8231046668896616e-06, "loss": 0.9918637084960937, "step": 708400 }, { "epoch": 8.1583326257374, "grad_norm": 0.69921875, "learning_rate": 5.815833103067146e-06, "loss": 1.0077804565429687, "step": 708600 }, { "epoch": 8.160635310812113, "grad_norm": 0.5078125, "learning_rate": 5.80856153924463e-06, "loss": 1.0214208984375, "step": 708800 }, { "epoch": 8.162937995886828, "grad_norm": 1.3359375, "learning_rate": 5.801289975422114e-06, "loss": 0.9646558380126953, "step": 709000 }, { "epoch": 8.165240680961544, "grad_norm": 0.86328125, "learning_rate": 5.794018411599599e-06, "loss": 0.9757888031005859, "step": 709200 }, { "epoch": 8.16754336603626, "grad_norm": 0.59765625, "learning_rate": 5.786746847777083e-06, "loss": 0.9735916900634766, "step": 709400 }, { "epoch": 8.169846051110973, "grad_norm": 0.8984375, "learning_rate": 5.779475283954568e-06, "loss": 1.012173843383789, "step": 709600 }, { "epoch": 8.172148736185688, "grad_norm": 0.6328125, "learning_rate": 5.772203720132052e-06, "loss": 0.9869450378417969, "step": 709800 }, { "epoch": 8.174451421260404, "grad_norm": 1.1015625, "learning_rate": 5.764932156309536e-06, "loss": 0.9860933685302734, "step": 710000 }, { "epoch": 8.17675410633512, "grad_norm": 0.640625, "learning_rate": 5.75766059248702e-06, "loss": 0.9633110809326172, "step": 710200 }, { "epoch": 8.179056791409833, "grad_norm": 0.6796875, "learning_rate": 5.750389028664505e-06, "loss": 0.9767103576660157, "step": 710400 }, { "epoch": 8.181359476484548, "grad_norm": 0.96484375, "learning_rate": 5.743117464841989e-06, "loss": 0.9685611724853516, "step": 710600 }, { "epoch": 8.183662161559264, "grad_norm": 0.66796875, "learning_rate": 5.735845901019474e-06, "loss": 0.9771729278564453, "step": 710800 }, { "epoch": 8.185964846633977, "grad_norm": 1.0, "learning_rate": 5.728574337196957e-06, "loss": 0.9966614532470703, "step": 711000 }, { "epoch": 8.188267531708693, "grad_norm": 0.56640625, "learning_rate": 5.721302773374442e-06, "loss": 0.9915567779541016, "step": 711200 }, { "epoch": 8.190570216783408, "grad_norm": 0.69921875, "learning_rate": 5.7140312095519265e-06, "loss": 0.9702359771728516, "step": 711400 }, { "epoch": 8.192872901858124, "grad_norm": 1.296875, "learning_rate": 5.706759645729411e-06, "loss": 0.9778258514404297, "step": 711600 }, { "epoch": 8.195175586932837, "grad_norm": 0.8359375, "learning_rate": 5.699488081906895e-06, "loss": 0.9641788482666016, "step": 711800 }, { "epoch": 8.197478272007553, "grad_norm": 0.462890625, "learning_rate": 5.692216518084379e-06, "loss": 0.9780941009521484, "step": 712000 }, { "epoch": 8.199780957082268, "grad_norm": 0.55078125, "learning_rate": 5.684944954261863e-06, "loss": 0.9986826324462891, "step": 712200 }, { "epoch": 8.202083642156982, "grad_norm": 0.984375, "learning_rate": 5.6776733904393485e-06, "loss": 0.980475082397461, "step": 712400 }, { "epoch": 8.204386327231697, "grad_norm": 0.74609375, "learning_rate": 5.670401826616832e-06, "loss": 0.9819741058349609, "step": 712600 }, { "epoch": 8.206689012306413, "grad_norm": 0.68359375, "learning_rate": 5.663130262794316e-06, "loss": 0.9808096313476562, "step": 712800 }, { "epoch": 8.208991697381128, "grad_norm": 1.328125, "learning_rate": 5.655858698971801e-06, "loss": 0.9706039428710938, "step": 713000 }, { "epoch": 8.211294382455842, "grad_norm": 0.74609375, "learning_rate": 5.648587135149285e-06, "loss": 0.9784176635742188, "step": 713200 }, { "epoch": 8.213597067530557, "grad_norm": 0.66796875, "learning_rate": 5.64131557132677e-06, "loss": 0.9678997039794922, "step": 713400 }, { "epoch": 8.215899752605273, "grad_norm": 0.78515625, "learning_rate": 5.634044007504254e-06, "loss": 0.9841072082519531, "step": 713600 }, { "epoch": 8.218202437679988, "grad_norm": 0.59375, "learning_rate": 5.626772443681738e-06, "loss": 0.9815675354003907, "step": 713800 }, { "epoch": 8.220505122754702, "grad_norm": 0.51171875, "learning_rate": 5.619500879859223e-06, "loss": 0.9935374450683594, "step": 714000 }, { "epoch": 8.222807807829417, "grad_norm": 0.51953125, "learning_rate": 5.612229316036707e-06, "loss": 0.9976025390625, "step": 714200 }, { "epoch": 8.225110492904133, "grad_norm": 0.431640625, "learning_rate": 5.604957752214191e-06, "loss": 0.9853916931152343, "step": 714400 }, { "epoch": 8.227413177978846, "grad_norm": 0.51953125, "learning_rate": 5.597686188391676e-06, "loss": 0.9812276458740234, "step": 714600 }, { "epoch": 8.229715863053562, "grad_norm": 0.61328125, "learning_rate": 5.59041462456916e-06, "loss": 0.9623724365234375, "step": 714800 }, { "epoch": 8.232018548128277, "grad_norm": 0.66796875, "learning_rate": 5.583143060746645e-06, "loss": 0.9900458526611328, "step": 715000 }, { "epoch": 8.234321233202992, "grad_norm": 0.73828125, "learning_rate": 5.575871496924128e-06, "loss": 0.995158920288086, "step": 715200 }, { "epoch": 8.236623918277706, "grad_norm": 0.75390625, "learning_rate": 5.568599933101613e-06, "loss": 0.9949196624755859, "step": 715400 }, { "epoch": 8.238926603352422, "grad_norm": 1.5625, "learning_rate": 5.561328369279098e-06, "loss": 0.9860065460205079, "step": 715600 }, { "epoch": 8.241229288427137, "grad_norm": 0.94921875, "learning_rate": 5.554056805456582e-06, "loss": 0.972602767944336, "step": 715800 }, { "epoch": 8.24353197350185, "grad_norm": 0.54296875, "learning_rate": 5.546785241634065e-06, "loss": 0.9766617584228515, "step": 716000 }, { "epoch": 8.245834658576566, "grad_norm": 0.54296875, "learning_rate": 5.53951367781155e-06, "loss": 0.9807737731933593, "step": 716200 }, { "epoch": 8.248137343651281, "grad_norm": 0.68359375, "learning_rate": 5.5322421139890346e-06, "loss": 0.9466493988037109, "step": 716400 }, { "epoch": 8.250440028725997, "grad_norm": 0.59765625, "learning_rate": 5.52497055016652e-06, "loss": 0.9830075836181641, "step": 716600 }, { "epoch": 8.25274271380071, "grad_norm": 0.6015625, "learning_rate": 5.517698986344003e-06, "loss": 0.9652910614013672, "step": 716800 }, { "epoch": 8.255045398875426, "grad_norm": 1.03125, "learning_rate": 5.510427422521487e-06, "loss": 0.9870015716552735, "step": 717000 }, { "epoch": 8.257348083950141, "grad_norm": 0.57421875, "learning_rate": 5.503155858698972e-06, "loss": 0.9680076599121094, "step": 717200 }, { "epoch": 8.259650769024857, "grad_norm": 0.52734375, "learning_rate": 5.4958842948764565e-06, "loss": 0.9882659912109375, "step": 717400 }, { "epoch": 8.26195345409957, "grad_norm": 0.578125, "learning_rate": 5.48861273105394e-06, "loss": 0.98557373046875, "step": 717600 }, { "epoch": 8.264256139174286, "grad_norm": 0.6328125, "learning_rate": 5.481341167231425e-06, "loss": 0.9993340301513672, "step": 717800 }, { "epoch": 8.266558824249001, "grad_norm": 0.83203125, "learning_rate": 5.474069603408909e-06, "loss": 0.9662551879882812, "step": 718000 }, { "epoch": 8.268861509323715, "grad_norm": 0.6171875, "learning_rate": 5.466798039586394e-06, "loss": 0.9752616119384766, "step": 718200 }, { "epoch": 8.27116419439843, "grad_norm": 0.62890625, "learning_rate": 5.459526475763878e-06, "loss": 0.9850730133056641, "step": 718400 }, { "epoch": 8.273466879473146, "grad_norm": 1.1484375, "learning_rate": 5.452254911941362e-06, "loss": 0.9840998840332031, "step": 718600 }, { "epoch": 8.275769564547861, "grad_norm": 2.0625, "learning_rate": 5.444983348118847e-06, "loss": 0.9916070556640625, "step": 718800 }, { "epoch": 8.278072249622575, "grad_norm": 0.78515625, "learning_rate": 5.437711784296331e-06, "loss": 0.969988021850586, "step": 719000 }, { "epoch": 8.28037493469729, "grad_norm": 0.58984375, "learning_rate": 5.4304402204738145e-06, "loss": 0.9657275390625, "step": 719200 }, { "epoch": 8.282677619772006, "grad_norm": 0.859375, "learning_rate": 5.4231686566512995e-06, "loss": 1.0001145172119141, "step": 719400 }, { "epoch": 8.28498030484672, "grad_norm": 0.57421875, "learning_rate": 5.415897092828784e-06, "loss": 0.9815138244628906, "step": 719600 }, { "epoch": 8.287282989921435, "grad_norm": 0.91015625, "learning_rate": 5.408625529006269e-06, "loss": 0.9896107482910156, "step": 719800 }, { "epoch": 8.28958567499615, "grad_norm": 1.4375, "learning_rate": 5.401353965183753e-06, "loss": 0.9785402679443359, "step": 720000 }, { "epoch": 8.291888360070866, "grad_norm": 0.51953125, "learning_rate": 5.394082401361236e-06, "loss": 0.9890270233154297, "step": 720200 }, { "epoch": 8.29419104514558, "grad_norm": 0.82421875, "learning_rate": 5.3868108375387215e-06, "loss": 0.9779497528076172, "step": 720400 }, { "epoch": 8.296493730220295, "grad_norm": 0.82421875, "learning_rate": 5.379539273716206e-06, "loss": 0.9936688995361328, "step": 720600 }, { "epoch": 8.29879641529501, "grad_norm": 0.61328125, "learning_rate": 5.37226770989369e-06, "loss": 0.9549921417236328, "step": 720800 }, { "epoch": 8.301099100369726, "grad_norm": 0.5234375, "learning_rate": 5.364996146071174e-06, "loss": 0.9940463256835937, "step": 721000 }, { "epoch": 8.30340178544444, "grad_norm": 0.486328125, "learning_rate": 5.357724582248658e-06, "loss": 0.9849036407470703, "step": 721200 }, { "epoch": 8.305704470519155, "grad_norm": 0.73046875, "learning_rate": 5.3504530184261434e-06, "loss": 0.9826818084716797, "step": 721400 }, { "epoch": 8.30800715559387, "grad_norm": 0.455078125, "learning_rate": 5.343181454603628e-06, "loss": 0.9915721130371093, "step": 721600 }, { "epoch": 8.310309840668584, "grad_norm": 0.66796875, "learning_rate": 5.335909890781111e-06, "loss": 0.9841053771972657, "step": 721800 }, { "epoch": 8.3126125257433, "grad_norm": 0.7109375, "learning_rate": 5.328638326958596e-06, "loss": 0.9658685302734376, "step": 722000 }, { "epoch": 8.314915210818015, "grad_norm": 0.66015625, "learning_rate": 5.32136676313608e-06, "loss": 0.9773105621337891, "step": 722200 }, { "epoch": 8.31721789589273, "grad_norm": 0.62109375, "learning_rate": 5.3140951993135645e-06, "loss": 0.9766971588134765, "step": 722400 }, { "epoch": 8.319520580967444, "grad_norm": 0.81640625, "learning_rate": 5.306823635491049e-06, "loss": 0.9907508850097656, "step": 722600 }, { "epoch": 8.32182326604216, "grad_norm": 0.7265625, "learning_rate": 5.299552071668533e-06, "loss": 0.9931290435791016, "step": 722800 }, { "epoch": 8.324125951116875, "grad_norm": 0.58203125, "learning_rate": 5.292280507846018e-06, "loss": 1.004654541015625, "step": 723000 }, { "epoch": 8.32642863619159, "grad_norm": 0.6875, "learning_rate": 5.285008944023502e-06, "loss": 0.9720559692382813, "step": 723200 }, { "epoch": 8.328731321266304, "grad_norm": 0.72265625, "learning_rate": 5.277737380200986e-06, "loss": 0.9656230163574219, "step": 723400 }, { "epoch": 8.331034006341019, "grad_norm": 0.474609375, "learning_rate": 5.270465816378471e-06, "loss": 0.9970842742919922, "step": 723600 }, { "epoch": 8.333336691415735, "grad_norm": 0.40234375, "learning_rate": 5.263194252555955e-06, "loss": 0.9868692016601562, "step": 723800 }, { "epoch": 8.335639376490448, "grad_norm": 0.85546875, "learning_rate": 5.255922688733439e-06, "loss": 0.9869068145751954, "step": 724000 }, { "epoch": 8.337942061565164, "grad_norm": 0.59375, "learning_rate": 5.248651124910923e-06, "loss": 0.9860624694824218, "step": 724200 }, { "epoch": 8.340244746639879, "grad_norm": 1.265625, "learning_rate": 5.2413795610884076e-06, "loss": 0.9691709899902343, "step": 724400 }, { "epoch": 8.342547431714594, "grad_norm": 0.70703125, "learning_rate": 5.234107997265892e-06, "loss": 0.9740015411376953, "step": 724600 }, { "epoch": 8.344850116789308, "grad_norm": 0.75390625, "learning_rate": 5.226836433443377e-06, "loss": 1.0019692230224608, "step": 724800 }, { "epoch": 8.347152801864024, "grad_norm": 0.890625, "learning_rate": 5.21956486962086e-06, "loss": 0.9928291320800782, "step": 725000 }, { "epoch": 8.349455486938739, "grad_norm": 0.72265625, "learning_rate": 5.212293305798345e-06, "loss": 0.9705638885498047, "step": 725200 }, { "epoch": 8.351758172013453, "grad_norm": 0.6171875, "learning_rate": 5.2050217419758295e-06, "loss": 0.9696398162841797, "step": 725400 }, { "epoch": 8.354060857088168, "grad_norm": 0.8125, "learning_rate": 5.197750178153314e-06, "loss": 0.9995099639892578, "step": 725600 }, { "epoch": 8.356363542162883, "grad_norm": 1.3515625, "learning_rate": 5.190478614330798e-06, "loss": 0.9892217254638672, "step": 725800 }, { "epoch": 8.358666227237599, "grad_norm": 0.423828125, "learning_rate": 5.183207050508282e-06, "loss": 0.983095474243164, "step": 726000 }, { "epoch": 8.360968912312313, "grad_norm": 0.82421875, "learning_rate": 5.175935486685766e-06, "loss": 0.9840006256103515, "step": 726200 }, { "epoch": 8.363271597387028, "grad_norm": 0.482421875, "learning_rate": 5.1686639228632515e-06, "loss": 1.0099681854248046, "step": 726400 }, { "epoch": 8.365574282461743, "grad_norm": 0.72265625, "learning_rate": 5.161392359040735e-06, "loss": 0.9920525360107422, "step": 726600 }, { "epoch": 8.367876967536459, "grad_norm": 0.86328125, "learning_rate": 5.15412079521822e-06, "loss": 0.9998994445800782, "step": 726800 }, { "epoch": 8.370179652611172, "grad_norm": 0.482421875, "learning_rate": 5.146849231395704e-06, "loss": 0.9936015319824218, "step": 727000 }, { "epoch": 8.372482337685888, "grad_norm": 0.73046875, "learning_rate": 5.139577667573188e-06, "loss": 0.9726751708984375, "step": 727200 }, { "epoch": 8.374785022760603, "grad_norm": 0.80859375, "learning_rate": 5.132306103750673e-06, "loss": 0.9772026824951172, "step": 727400 }, { "epoch": 8.377087707835317, "grad_norm": 0.92578125, "learning_rate": 5.125034539928157e-06, "loss": 0.9934384918212891, "step": 727600 }, { "epoch": 8.379390392910032, "grad_norm": 0.5, "learning_rate": 5.117762976105641e-06, "loss": 0.9848506927490235, "step": 727800 }, { "epoch": 8.381693077984748, "grad_norm": 0.59375, "learning_rate": 5.110491412283126e-06, "loss": 0.970640869140625, "step": 728000 }, { "epoch": 8.383995763059463, "grad_norm": 1.0625, "learning_rate": 5.10321984846061e-06, "loss": 0.9867308807373046, "step": 728200 }, { "epoch": 8.386298448134177, "grad_norm": 0.53515625, "learning_rate": 5.0959482846380945e-06, "loss": 0.9939826965332031, "step": 728400 }, { "epoch": 8.388601133208892, "grad_norm": 0.52734375, "learning_rate": 5.088676720815579e-06, "loss": 1.0018857574462892, "step": 728600 }, { "epoch": 8.390903818283608, "grad_norm": 0.80078125, "learning_rate": 5.081405156993063e-06, "loss": 0.9786152648925781, "step": 728800 }, { "epoch": 8.393206503358321, "grad_norm": 1.1484375, "learning_rate": 5.074133593170548e-06, "loss": 0.9753307342529297, "step": 729000 }, { "epoch": 8.395509188433037, "grad_norm": 0.78125, "learning_rate": 5.066862029348031e-06, "loss": 0.9845266723632813, "step": 729200 }, { "epoch": 8.397811873507752, "grad_norm": 0.86328125, "learning_rate": 5.059590465525516e-06, "loss": 0.9853861236572266, "step": 729400 }, { "epoch": 8.400114558582468, "grad_norm": 0.56640625, "learning_rate": 5.052318901703001e-06, "loss": 0.9771392822265625, "step": 729600 }, { "epoch": 8.402417243657181, "grad_norm": 0.70703125, "learning_rate": 5.045047337880485e-06, "loss": 0.9864144134521484, "step": 729800 }, { "epoch": 8.404719928731897, "grad_norm": 0.734375, "learning_rate": 5.037775774057969e-06, "loss": 0.9801872253417969, "step": 730000 }, { "epoch": 8.407022613806612, "grad_norm": 0.66015625, "learning_rate": 5.030504210235453e-06, "loss": 0.9925270843505859, "step": 730200 }, { "epoch": 8.409325298881328, "grad_norm": 0.7578125, "learning_rate": 5.0232326464129375e-06, "loss": 0.9811373138427735, "step": 730400 }, { "epoch": 8.411627983956041, "grad_norm": 0.59375, "learning_rate": 5.015961082590423e-06, "loss": 0.9967536926269531, "step": 730600 }, { "epoch": 8.413930669030757, "grad_norm": 0.80078125, "learning_rate": 5.008689518767906e-06, "loss": 1.0077542877197265, "step": 730800 }, { "epoch": 8.416233354105472, "grad_norm": 1.0859375, "learning_rate": 5.00141795494539e-06, "loss": 0.9968529510498046, "step": 731000 }, { "epoch": 8.418536039180186, "grad_norm": 0.92578125, "learning_rate": 4.994146391122875e-06, "loss": 0.9632941436767578, "step": 731200 }, { "epoch": 8.420838724254901, "grad_norm": 0.54296875, "learning_rate": 4.9868748273003595e-06, "loss": 0.9997820281982421, "step": 731400 }, { "epoch": 8.423141409329617, "grad_norm": 0.484375, "learning_rate": 4.979603263477844e-06, "loss": 0.9839828491210938, "step": 731600 }, { "epoch": 8.425444094404332, "grad_norm": 0.77734375, "learning_rate": 4.972331699655328e-06, "loss": 0.9684250640869141, "step": 731800 }, { "epoch": 8.427746779479046, "grad_norm": 0.4609375, "learning_rate": 4.965060135832812e-06, "loss": 0.9693086242675781, "step": 732000 }, { "epoch": 8.430049464553761, "grad_norm": 0.68359375, "learning_rate": 4.957788572010297e-06, "loss": 0.9741654205322265, "step": 732200 }, { "epoch": 8.432352149628477, "grad_norm": 0.74609375, "learning_rate": 4.950517008187781e-06, "loss": 0.9970919799804687, "step": 732400 }, { "epoch": 8.434654834703192, "grad_norm": 0.7109375, "learning_rate": 4.943245444365265e-06, "loss": 0.9704073333740234, "step": 732600 }, { "epoch": 8.436957519777906, "grad_norm": 1.0390625, "learning_rate": 4.93597388054275e-06, "loss": 1.0041982269287109, "step": 732800 }, { "epoch": 8.439260204852621, "grad_norm": 0.494140625, "learning_rate": 4.928702316720234e-06, "loss": 0.9678970336914062, "step": 733000 }, { "epoch": 8.441562889927336, "grad_norm": 0.75390625, "learning_rate": 4.921430752897718e-06, "loss": 0.986545181274414, "step": 733200 }, { "epoch": 8.44386557500205, "grad_norm": 0.59375, "learning_rate": 4.9141591890752025e-06, "loss": 0.9558411407470703, "step": 733400 }, { "epoch": 8.446168260076766, "grad_norm": 0.408203125, "learning_rate": 4.906887625252687e-06, "loss": 0.9802081298828125, "step": 733600 }, { "epoch": 8.448470945151481, "grad_norm": 0.75, "learning_rate": 4.899616061430172e-06, "loss": 0.9869933319091797, "step": 733800 }, { "epoch": 8.450773630226196, "grad_norm": 0.76171875, "learning_rate": 4.892344497607656e-06, "loss": 0.9878524780273438, "step": 734000 }, { "epoch": 8.45307631530091, "grad_norm": 0.6328125, "learning_rate": 4.885072933785139e-06, "loss": 0.9893035125732422, "step": 734200 }, { "epoch": 8.455379000375626, "grad_norm": 0.55078125, "learning_rate": 4.8778013699626245e-06, "loss": 0.9825079345703125, "step": 734400 }, { "epoch": 8.457681685450341, "grad_norm": 0.7109375, "learning_rate": 4.870529806140109e-06, "loss": 0.9930937194824219, "step": 734600 }, { "epoch": 8.459984370525055, "grad_norm": 0.734375, "learning_rate": 4.863258242317593e-06, "loss": 0.961860580444336, "step": 734800 }, { "epoch": 8.46228705559977, "grad_norm": 0.62109375, "learning_rate": 4.855986678495077e-06, "loss": 1.0016260528564453, "step": 735000 }, { "epoch": 8.464589740674485, "grad_norm": 0.78515625, "learning_rate": 4.848715114672561e-06, "loss": 0.9752246856689453, "step": 735200 }, { "epoch": 8.4668924257492, "grad_norm": 0.9375, "learning_rate": 4.841443550850046e-06, "loss": 0.9766324615478515, "step": 735400 }, { "epoch": 8.469195110823915, "grad_norm": 0.53515625, "learning_rate": 4.834171987027531e-06, "loss": 0.9969155883789063, "step": 735600 }, { "epoch": 8.47149779589863, "grad_norm": 0.56640625, "learning_rate": 4.826900423205014e-06, "loss": 0.9860860443115235, "step": 735800 }, { "epoch": 8.473800480973345, "grad_norm": 0.70703125, "learning_rate": 4.819628859382499e-06, "loss": 0.9745457458496094, "step": 736000 }, { "epoch": 8.476103166048059, "grad_norm": 0.9453125, "learning_rate": 4.812357295559983e-06, "loss": 1.0002130889892578, "step": 736200 }, { "epoch": 8.478405851122774, "grad_norm": 0.6875, "learning_rate": 4.8050857317374675e-06, "loss": 0.98840087890625, "step": 736400 }, { "epoch": 8.48070853619749, "grad_norm": 1.3984375, "learning_rate": 4.797814167914952e-06, "loss": 1.0051963806152344, "step": 736600 }, { "epoch": 8.483011221272205, "grad_norm": 0.451171875, "learning_rate": 4.790542604092436e-06, "loss": 1.006302032470703, "step": 736800 }, { "epoch": 8.485313906346919, "grad_norm": 0.703125, "learning_rate": 4.783271040269921e-06, "loss": 0.9928652954101562, "step": 737000 }, { "epoch": 8.487616591421634, "grad_norm": 0.6640625, "learning_rate": 4.775999476447405e-06, "loss": 0.9688255310058593, "step": 737200 }, { "epoch": 8.48991927649635, "grad_norm": 0.58203125, "learning_rate": 4.768727912624889e-06, "loss": 0.9724116516113281, "step": 737400 }, { "epoch": 8.492221961571065, "grad_norm": 1.2109375, "learning_rate": 4.761456348802374e-06, "loss": 0.9784508514404296, "step": 737600 }, { "epoch": 8.494524646645779, "grad_norm": 0.73828125, "learning_rate": 4.754184784979858e-06, "loss": 0.9876103973388672, "step": 737800 }, { "epoch": 8.496827331720494, "grad_norm": 0.484375, "learning_rate": 4.746913221157342e-06, "loss": 0.9536474609375, "step": 738000 }, { "epoch": 8.49913001679521, "grad_norm": 0.62890625, "learning_rate": 4.739641657334826e-06, "loss": 1.0035865020751953, "step": 738200 }, { "epoch": 8.501432701869923, "grad_norm": 0.458984375, "learning_rate": 4.7323700935123106e-06, "loss": 0.9735746765136719, "step": 738400 }, { "epoch": 8.503735386944639, "grad_norm": 0.93359375, "learning_rate": 4.725098529689796e-06, "loss": 0.9690022277832031, "step": 738600 }, { "epoch": 8.506038072019354, "grad_norm": 0.953125, "learning_rate": 4.71782696586728e-06, "loss": 0.9983604431152344, "step": 738800 }, { "epoch": 8.50834075709407, "grad_norm": 0.484375, "learning_rate": 4.710555402044763e-06, "loss": 0.9797876739501953, "step": 739000 }, { "epoch": 8.510643442168783, "grad_norm": 0.48828125, "learning_rate": 4.703283838222248e-06, "loss": 0.9583721923828125, "step": 739200 }, { "epoch": 8.512946127243499, "grad_norm": 0.80859375, "learning_rate": 4.6960122743997325e-06, "loss": 0.9663965606689453, "step": 739400 }, { "epoch": 8.515248812318214, "grad_norm": 0.55859375, "learning_rate": 4.688740710577217e-06, "loss": 0.9920121002197265, "step": 739600 }, { "epoch": 8.51755149739293, "grad_norm": 0.5859375, "learning_rate": 4.681469146754701e-06, "loss": 0.9966871643066406, "step": 739800 }, { "epoch": 8.519854182467643, "grad_norm": 0.91015625, "learning_rate": 4.674197582932185e-06, "loss": 0.9799186706542968, "step": 740000 }, { "epoch": 8.522156867542359, "grad_norm": 0.5703125, "learning_rate": 4.66692601910967e-06, "loss": 1.0063607788085938, "step": 740200 }, { "epoch": 8.524459552617074, "grad_norm": 0.96484375, "learning_rate": 4.6596544552871544e-06, "loss": 0.976033935546875, "step": 740400 }, { "epoch": 8.526762237691788, "grad_norm": 0.6328125, "learning_rate": 4.652382891464639e-06, "loss": 0.964898681640625, "step": 740600 }, { "epoch": 8.529064922766503, "grad_norm": 0.4609375, "learning_rate": 4.645111327642123e-06, "loss": 0.9735550689697265, "step": 740800 }, { "epoch": 8.531367607841219, "grad_norm": 0.79296875, "learning_rate": 4.637839763819607e-06, "loss": 0.9649169921875, "step": 741000 }, { "epoch": 8.533670292915934, "grad_norm": 0.4453125, "learning_rate": 4.630568199997091e-06, "loss": 0.96186279296875, "step": 741200 }, { "epoch": 8.535972977990648, "grad_norm": 0.88671875, "learning_rate": 4.623296636174576e-06, "loss": 1.0031502532958985, "step": 741400 }, { "epoch": 8.538275663065363, "grad_norm": 1.3828125, "learning_rate": 4.61602507235206e-06, "loss": 0.9780646514892578, "step": 741600 }, { "epoch": 8.540578348140079, "grad_norm": 0.53125, "learning_rate": 4.608753508529545e-06, "loss": 0.9804470825195313, "step": 741800 }, { "epoch": 8.542881033214792, "grad_norm": 0.66015625, "learning_rate": 4.601481944707029e-06, "loss": 0.9616146087646484, "step": 742000 }, { "epoch": 8.545183718289508, "grad_norm": 0.875, "learning_rate": 4.594210380884513e-06, "loss": 0.9716793060302734, "step": 742200 }, { "epoch": 8.547486403364223, "grad_norm": 0.53125, "learning_rate": 4.5869388170619975e-06, "loss": 0.9809304809570313, "step": 742400 }, { "epoch": 8.549789088438938, "grad_norm": 0.6171875, "learning_rate": 4.579667253239482e-06, "loss": 0.9804471588134765, "step": 742600 }, { "epoch": 8.552091773513652, "grad_norm": 0.61328125, "learning_rate": 4.572395689416966e-06, "loss": 0.9672725677490235, "step": 742800 }, { "epoch": 8.554394458588368, "grad_norm": 0.68359375, "learning_rate": 4.565124125594451e-06, "loss": 1.0129902648925782, "step": 743000 }, { "epoch": 8.556697143663083, "grad_norm": 0.765625, "learning_rate": 4.557852561771934e-06, "loss": 0.9989830017089844, "step": 743200 }, { "epoch": 8.558999828737797, "grad_norm": 0.7890625, "learning_rate": 4.550580997949419e-06, "loss": 0.9873731994628906, "step": 743400 }, { "epoch": 8.561302513812512, "grad_norm": 0.50390625, "learning_rate": 4.543309434126904e-06, "loss": 0.9832039642333984, "step": 743600 }, { "epoch": 8.563605198887227, "grad_norm": 0.59375, "learning_rate": 4.536037870304388e-06, "loss": 0.9728511810302735, "step": 743800 }, { "epoch": 8.565907883961943, "grad_norm": 0.5859375, "learning_rate": 4.528766306481872e-06, "loss": 0.9821251678466797, "step": 744000 }, { "epoch": 8.568210569036657, "grad_norm": 0.75, "learning_rate": 4.521494742659356e-06, "loss": 0.9702672576904297, "step": 744200 }, { "epoch": 8.570513254111372, "grad_norm": 0.72265625, "learning_rate": 4.5142231788368405e-06, "loss": 0.9961418151855469, "step": 744400 }, { "epoch": 8.572815939186087, "grad_norm": 1.125, "learning_rate": 4.506951615014326e-06, "loss": 0.9817313385009766, "step": 744600 }, { "epoch": 8.575118624260803, "grad_norm": 1.2734375, "learning_rate": 4.499680051191809e-06, "loss": 0.985406494140625, "step": 744800 }, { "epoch": 8.577421309335516, "grad_norm": 0.53125, "learning_rate": 4.492408487369294e-06, "loss": 0.9726136779785156, "step": 745000 }, { "epoch": 8.579723994410232, "grad_norm": 1.3671875, "learning_rate": 4.485136923546778e-06, "loss": 0.9817514038085937, "step": 745200 }, { "epoch": 8.582026679484947, "grad_norm": 0.94921875, "learning_rate": 4.4778653597242625e-06, "loss": 0.9874824523925781, "step": 745400 }, { "epoch": 8.584329364559661, "grad_norm": 0.921875, "learning_rate": 4.470593795901747e-06, "loss": 0.9865628051757812, "step": 745600 }, { "epoch": 8.586632049634376, "grad_norm": 1.1796875, "learning_rate": 4.463322232079231e-06, "loss": 0.9929932403564453, "step": 745800 }, { "epoch": 8.588934734709092, "grad_norm": 0.890625, "learning_rate": 4.456050668256715e-06, "loss": 1.007845687866211, "step": 746000 }, { "epoch": 8.591237419783807, "grad_norm": 1.0234375, "learning_rate": 4.4487791044342e-06, "loss": 0.9824122619628907, "step": 746200 }, { "epoch": 8.593540104858521, "grad_norm": 0.515625, "learning_rate": 4.4415075406116836e-06, "loss": 0.9818960571289063, "step": 746400 }, { "epoch": 8.595842789933236, "grad_norm": 1.234375, "learning_rate": 4.434235976789168e-06, "loss": 0.9791338348388672, "step": 746600 }, { "epoch": 8.598145475007952, "grad_norm": 0.71875, "learning_rate": 4.426964412966653e-06, "loss": 0.9939133453369141, "step": 746800 }, { "epoch": 8.600448160082667, "grad_norm": 0.9609375, "learning_rate": 4.419692849144137e-06, "loss": 0.9964035797119141, "step": 747000 }, { "epoch": 8.60275084515738, "grad_norm": 0.7578125, "learning_rate": 4.412421285321621e-06, "loss": 0.9719769287109375, "step": 747200 }, { "epoch": 8.605053530232096, "grad_norm": 0.78515625, "learning_rate": 4.4051497214991055e-06, "loss": 0.9511328887939453, "step": 747400 }, { "epoch": 8.607356215306812, "grad_norm": 1.1484375, "learning_rate": 4.39787815767659e-06, "loss": 0.987777099609375, "step": 747600 }, { "epoch": 8.609658900381525, "grad_norm": 0.5234375, "learning_rate": 4.390606593854075e-06, "loss": 0.99900634765625, "step": 747800 }, { "epoch": 8.61196158545624, "grad_norm": 0.431640625, "learning_rate": 4.383335030031559e-06, "loss": 0.9555909729003906, "step": 748000 }, { "epoch": 8.614264270530956, "grad_norm": 0.64453125, "learning_rate": 4.376063466209042e-06, "loss": 0.9895748901367187, "step": 748200 }, { "epoch": 8.616566955605672, "grad_norm": 0.5234375, "learning_rate": 4.3687919023865274e-06, "loss": 0.9897019958496094, "step": 748400 }, { "epoch": 8.618869640680385, "grad_norm": 0.984375, "learning_rate": 4.361520338564012e-06, "loss": 0.9821299743652344, "step": 748600 }, { "epoch": 8.6211723257551, "grad_norm": 0.75390625, "learning_rate": 4.354248774741497e-06, "loss": 0.9836980438232422, "step": 748800 }, { "epoch": 8.623475010829816, "grad_norm": 0.62890625, "learning_rate": 4.34697721091898e-06, "loss": 0.9656773376464843, "step": 749000 }, { "epoch": 8.625777695904532, "grad_norm": 0.93359375, "learning_rate": 4.339705647096464e-06, "loss": 0.9764061737060546, "step": 749200 }, { "epoch": 8.628080380979245, "grad_norm": 0.5859375, "learning_rate": 4.332434083273949e-06, "loss": 0.9941240692138672, "step": 749400 }, { "epoch": 8.63038306605396, "grad_norm": 0.6015625, "learning_rate": 4.325162519451434e-06, "loss": 0.9832437896728515, "step": 749600 }, { "epoch": 8.632685751128676, "grad_norm": 0.5625, "learning_rate": 4.317890955628917e-06, "loss": 0.9863040161132812, "step": 749800 }, { "epoch": 8.63498843620339, "grad_norm": 0.6953125, "learning_rate": 4.310619391806402e-06, "loss": 0.9784996795654297, "step": 750000 }, { "epoch": 8.637291121278105, "grad_norm": 0.68359375, "learning_rate": 4.303347827983886e-06, "loss": 0.9644253540039063, "step": 750200 }, { "epoch": 8.63959380635282, "grad_norm": 0.796875, "learning_rate": 4.296076264161371e-06, "loss": 0.9938349151611328, "step": 750400 }, { "epoch": 8.641896491427536, "grad_norm": 0.65625, "learning_rate": 4.288804700338855e-06, "loss": 0.9900470733642578, "step": 750600 }, { "epoch": 8.64419917650225, "grad_norm": 0.39453125, "learning_rate": 4.281533136516339e-06, "loss": 0.992398452758789, "step": 750800 }, { "epoch": 8.646501861576965, "grad_norm": 1.40625, "learning_rate": 4.274261572693824e-06, "loss": 0.9773881530761719, "step": 751000 }, { "epoch": 8.64880454665168, "grad_norm": 0.75390625, "learning_rate": 4.266990008871308e-06, "loss": 0.9816563415527344, "step": 751200 }, { "epoch": 8.651107231726394, "grad_norm": 0.7109375, "learning_rate": 4.259718445048792e-06, "loss": 0.9742191314697266, "step": 751400 }, { "epoch": 8.65340991680111, "grad_norm": 0.75, "learning_rate": 4.252446881226277e-06, "loss": 0.983070297241211, "step": 751600 }, { "epoch": 8.655712601875825, "grad_norm": 0.5234375, "learning_rate": 4.245175317403761e-06, "loss": 0.9570191955566406, "step": 751800 }, { "epoch": 8.65801528695054, "grad_norm": 0.65234375, "learning_rate": 4.237903753581246e-06, "loss": 0.9718711853027344, "step": 752000 }, { "epoch": 8.660317972025254, "grad_norm": 0.5390625, "learning_rate": 4.230632189758729e-06, "loss": 0.9831970977783203, "step": 752200 }, { "epoch": 8.66262065709997, "grad_norm": 0.43359375, "learning_rate": 4.2233606259362135e-06, "loss": 0.9732750701904297, "step": 752400 }, { "epoch": 8.664923342174685, "grad_norm": 0.69140625, "learning_rate": 4.216089062113699e-06, "loss": 0.9819364166259765, "step": 752600 }, { "epoch": 8.667226027249399, "grad_norm": 0.98046875, "learning_rate": 4.208817498291183e-06, "loss": 1.0118328094482423, "step": 752800 }, { "epoch": 8.669528712324114, "grad_norm": 1.3046875, "learning_rate": 4.201545934468666e-06, "loss": 0.9904637145996094, "step": 753000 }, { "epoch": 8.67183139739883, "grad_norm": 0.75, "learning_rate": 4.194274370646151e-06, "loss": 0.972322769165039, "step": 753200 }, { "epoch": 8.674134082473545, "grad_norm": 0.6015625, "learning_rate": 4.1870028068236355e-06, "loss": 0.9820072174072265, "step": 753400 }, { "epoch": 8.676436767548259, "grad_norm": 0.5625, "learning_rate": 4.1797312430011205e-06, "loss": 0.9733422088623047, "step": 753600 }, { "epoch": 8.678739452622974, "grad_norm": 0.9453125, "learning_rate": 4.172459679178604e-06, "loss": 0.9668608856201172, "step": 753800 }, { "epoch": 8.68104213769769, "grad_norm": 0.80859375, "learning_rate": 4.165188115356088e-06, "loss": 0.9491535186767578, "step": 754000 }, { "epoch": 8.683344822772405, "grad_norm": 0.671875, "learning_rate": 4.157916551533573e-06, "loss": 0.972203369140625, "step": 754200 }, { "epoch": 8.685647507847118, "grad_norm": 1.1484375, "learning_rate": 4.150644987711057e-06, "loss": 0.983939208984375, "step": 754400 }, { "epoch": 8.687950192921834, "grad_norm": 0.412109375, "learning_rate": 4.143373423888542e-06, "loss": 0.9967646789550781, "step": 754600 }, { "epoch": 8.69025287799655, "grad_norm": 0.84375, "learning_rate": 4.136101860066026e-06, "loss": 0.9793635559082031, "step": 754800 }, { "epoch": 8.692555563071263, "grad_norm": 0.8203125, "learning_rate": 4.12883029624351e-06, "loss": 0.9769644927978516, "step": 755000 }, { "epoch": 8.694858248145978, "grad_norm": 0.46875, "learning_rate": 4.121558732420995e-06, "loss": 0.9760430145263672, "step": 755200 }, { "epoch": 8.697160933220694, "grad_norm": 0.66015625, "learning_rate": 4.114287168598479e-06, "loss": 0.975523681640625, "step": 755400 }, { "epoch": 8.69946361829541, "grad_norm": 0.640625, "learning_rate": 4.107015604775963e-06, "loss": 0.9740261840820312, "step": 755600 }, { "epoch": 8.701766303370123, "grad_norm": 1.2734375, "learning_rate": 4.099744040953448e-06, "loss": 0.9879347229003906, "step": 755800 }, { "epoch": 8.704068988444838, "grad_norm": 0.5859375, "learning_rate": 4.092472477130932e-06, "loss": 0.9873762512207032, "step": 756000 }, { "epoch": 8.706371673519554, "grad_norm": 0.6796875, "learning_rate": 4.085200913308416e-06, "loss": 0.9697098541259765, "step": 756200 }, { "epoch": 8.70867435859427, "grad_norm": 0.609375, "learning_rate": 4.0779293494859005e-06, "loss": 0.9750542449951172, "step": 756400 }, { "epoch": 8.710977043668983, "grad_norm": 0.515625, "learning_rate": 4.070657785663385e-06, "loss": 0.9895989227294922, "step": 756600 }, { "epoch": 8.713279728743698, "grad_norm": 0.71484375, "learning_rate": 4.06338622184087e-06, "loss": 0.9877436828613281, "step": 756800 }, { "epoch": 8.715582413818414, "grad_norm": 0.56640625, "learning_rate": 4.056114658018354e-06, "loss": 0.9801091766357422, "step": 757000 }, { "epoch": 8.717885098893127, "grad_norm": 0.5, "learning_rate": 4.048843094195837e-06, "loss": 0.9831630706787109, "step": 757200 }, { "epoch": 8.720187783967843, "grad_norm": 0.423828125, "learning_rate": 4.041571530373322e-06, "loss": 0.9879035949707031, "step": 757400 }, { "epoch": 8.722490469042558, "grad_norm": 0.65625, "learning_rate": 4.034299966550807e-06, "loss": 0.9739523315429688, "step": 757600 }, { "epoch": 8.724793154117274, "grad_norm": 0.74609375, "learning_rate": 4.027028402728291e-06, "loss": 0.9841912078857422, "step": 757800 }, { "epoch": 8.727095839191987, "grad_norm": 0.80078125, "learning_rate": 4.019756838905775e-06, "loss": 0.9674013519287109, "step": 758000 }, { "epoch": 8.729398524266703, "grad_norm": 0.59375, "learning_rate": 4.012485275083259e-06, "loss": 1.0047560119628907, "step": 758200 }, { "epoch": 8.731701209341418, "grad_norm": 0.5625, "learning_rate": 4.0052137112607435e-06, "loss": 0.9761631774902344, "step": 758400 }, { "epoch": 8.734003894416132, "grad_norm": 0.671875, "learning_rate": 3.9979421474382286e-06, "loss": 0.9929995727539063, "step": 758600 }, { "epoch": 8.736306579490847, "grad_norm": 0.7421875, "learning_rate": 3.990670583615712e-06, "loss": 0.9686499786376953, "step": 758800 }, { "epoch": 8.738609264565563, "grad_norm": 0.609375, "learning_rate": 3.983399019793197e-06, "loss": 0.9847555541992188, "step": 759000 }, { "epoch": 8.740911949640278, "grad_norm": 0.625, "learning_rate": 3.976127455970681e-06, "loss": 0.9836019134521484, "step": 759200 }, { "epoch": 8.743214634714992, "grad_norm": 0.462890625, "learning_rate": 3.9688558921481654e-06, "loss": 0.98874755859375, "step": 759400 }, { "epoch": 8.745517319789707, "grad_norm": 0.4609375, "learning_rate": 3.96158432832565e-06, "loss": 0.9745330810546875, "step": 759600 }, { "epoch": 8.747820004864423, "grad_norm": 0.8203125, "learning_rate": 3.954312764503134e-06, "loss": 0.9955284881591797, "step": 759800 }, { "epoch": 8.750122689939136, "grad_norm": 0.640625, "learning_rate": 3.947041200680618e-06, "loss": 0.9717284393310547, "step": 760000 }, { "epoch": 8.752425375013852, "grad_norm": 0.77734375, "learning_rate": 3.939769636858103e-06, "loss": 0.9807109832763672, "step": 760200 }, { "epoch": 8.754728060088567, "grad_norm": 0.61328125, "learning_rate": 3.9324980730355865e-06, "loss": 0.9712101745605469, "step": 760400 }, { "epoch": 8.757030745163283, "grad_norm": 0.484375, "learning_rate": 3.925226509213072e-06, "loss": 0.9616006469726562, "step": 760600 }, { "epoch": 8.759333430237996, "grad_norm": 0.70703125, "learning_rate": 3.917954945390556e-06, "loss": 0.9621672058105468, "step": 760800 }, { "epoch": 8.761636115312712, "grad_norm": 0.57421875, "learning_rate": 3.91068338156804e-06, "loss": 0.9885343170166015, "step": 761000 }, { "epoch": 8.763938800387427, "grad_norm": 0.392578125, "learning_rate": 3.903411817745525e-06, "loss": 0.9749143981933593, "step": 761200 }, { "epoch": 8.766241485462142, "grad_norm": 1.265625, "learning_rate": 3.8961402539230085e-06, "loss": 0.9841162872314453, "step": 761400 }, { "epoch": 8.768544170536856, "grad_norm": 0.50390625, "learning_rate": 3.888868690100493e-06, "loss": 0.9840245056152344, "step": 761600 }, { "epoch": 8.770846855611572, "grad_norm": 0.439453125, "learning_rate": 3.881597126277978e-06, "loss": 0.9939464569091797, "step": 761800 }, { "epoch": 8.773149540686287, "grad_norm": 0.53515625, "learning_rate": 3.874325562455462e-06, "loss": 0.9811724090576172, "step": 762000 }, { "epoch": 8.775452225761, "grad_norm": 3.734375, "learning_rate": 3.867053998632946e-06, "loss": 0.9716242980957032, "step": 762200 }, { "epoch": 8.777754910835716, "grad_norm": 0.77734375, "learning_rate": 3.8597824348104304e-06, "loss": 0.9963446807861328, "step": 762400 }, { "epoch": 8.780057595910431, "grad_norm": 0.99609375, "learning_rate": 3.852510870987915e-06, "loss": 0.9831389617919922, "step": 762600 }, { "epoch": 8.782360280985147, "grad_norm": 0.69140625, "learning_rate": 3.8452393071654e-06, "loss": 0.9837663269042969, "step": 762800 }, { "epoch": 8.78466296605986, "grad_norm": 0.7890625, "learning_rate": 3.837967743342883e-06, "loss": 0.9864227294921875, "step": 763000 }, { "epoch": 8.786965651134576, "grad_norm": 0.890625, "learning_rate": 3.830696179520367e-06, "loss": 1.002994384765625, "step": 763200 }, { "epoch": 8.789268336209291, "grad_norm": 0.71484375, "learning_rate": 3.823424615697852e-06, "loss": 0.9955747222900391, "step": 763400 }, { "epoch": 8.791571021284007, "grad_norm": 0.91796875, "learning_rate": 3.816153051875337e-06, "loss": 0.975970458984375, "step": 763600 }, { "epoch": 8.79387370635872, "grad_norm": 0.64453125, "learning_rate": 3.8088814880528212e-06, "loss": 0.9739787292480468, "step": 763800 }, { "epoch": 8.796176391433436, "grad_norm": 0.890625, "learning_rate": 3.801609924230305e-06, "loss": 0.9904090881347656, "step": 764000 }, { "epoch": 8.798479076508151, "grad_norm": 0.67578125, "learning_rate": 3.7943383604077892e-06, "loss": 0.9814543914794922, "step": 764200 }, { "epoch": 8.800781761582865, "grad_norm": 0.71484375, "learning_rate": 3.787066796585274e-06, "loss": 0.9868421936035157, "step": 764400 }, { "epoch": 8.80308444665758, "grad_norm": 0.5390625, "learning_rate": 3.779795232762758e-06, "loss": 0.9769282531738281, "step": 764600 }, { "epoch": 8.805387131732296, "grad_norm": 0.478515625, "learning_rate": 3.772523668940242e-06, "loss": 0.9739444732666016, "step": 764800 }, { "epoch": 8.807689816807011, "grad_norm": 0.80859375, "learning_rate": 3.765252105117727e-06, "loss": 0.9981250762939453, "step": 765000 }, { "epoch": 8.809992501881725, "grad_norm": 0.484375, "learning_rate": 3.7579805412952108e-06, "loss": 0.9787905120849609, "step": 765200 }, { "epoch": 8.81229518695644, "grad_norm": 1.0390625, "learning_rate": 3.750708977472696e-06, "loss": 0.9816758728027344, "step": 765400 }, { "epoch": 8.814597872031156, "grad_norm": 0.490234375, "learning_rate": 3.7434374136501796e-06, "loss": 0.9940653228759766, "step": 765600 }, { "epoch": 8.816900557105871, "grad_norm": 0.546875, "learning_rate": 3.7361658498276643e-06, "loss": 0.9731235504150391, "step": 765800 }, { "epoch": 8.819203242180585, "grad_norm": 0.71875, "learning_rate": 3.728894286005148e-06, "loss": 0.9854316711425781, "step": 766000 }, { "epoch": 8.8215059272553, "grad_norm": 0.8828125, "learning_rate": 3.7216227221826327e-06, "loss": 0.9703307342529297, "step": 766200 }, { "epoch": 8.823808612330016, "grad_norm": 0.474609375, "learning_rate": 3.714351158360117e-06, "loss": 0.9908853149414063, "step": 766400 }, { "epoch": 8.82611129740473, "grad_norm": 0.65234375, "learning_rate": 3.7070795945376016e-06, "loss": 0.9777758026123047, "step": 766600 }, { "epoch": 8.828413982479445, "grad_norm": 0.578125, "learning_rate": 3.6998080307150854e-06, "loss": 0.9859429931640625, "step": 766800 }, { "epoch": 8.83071666755416, "grad_norm": 0.89453125, "learning_rate": 3.69253646689257e-06, "loss": 0.9925715637207031, "step": 767000 }, { "epoch": 8.833019352628876, "grad_norm": 0.388671875, "learning_rate": 3.6852649030700542e-06, "loss": 0.9771989440917969, "step": 767200 }, { "epoch": 8.83532203770359, "grad_norm": 0.73046875, "learning_rate": 3.677993339247539e-06, "loss": 0.9750688934326172, "step": 767400 }, { "epoch": 8.837624722778305, "grad_norm": 0.81640625, "learning_rate": 3.6707217754250227e-06, "loss": 0.9724152374267578, "step": 767600 }, { "epoch": 8.83992740785302, "grad_norm": 0.5390625, "learning_rate": 3.6634502116025073e-06, "loss": 0.982885971069336, "step": 767800 }, { "epoch": 8.842230092927734, "grad_norm": 0.60546875, "learning_rate": 3.656178647779992e-06, "loss": 0.9649812316894532, "step": 768000 }, { "epoch": 8.84453277800245, "grad_norm": 0.796875, "learning_rate": 3.648907083957476e-06, "loss": 1.0030159759521484, "step": 768200 }, { "epoch": 8.846835463077165, "grad_norm": 0.7890625, "learning_rate": 3.6416355201349604e-06, "loss": 0.9977754211425781, "step": 768400 }, { "epoch": 8.84913814815188, "grad_norm": 0.7109375, "learning_rate": 3.6343639563124446e-06, "loss": 0.9839167785644531, "step": 768600 }, { "epoch": 8.851440833226594, "grad_norm": 0.8984375, "learning_rate": 3.6270923924899293e-06, "loss": 0.9640473175048828, "step": 768800 }, { "epoch": 8.85374351830131, "grad_norm": 0.7421875, "learning_rate": 3.6198208286674135e-06, "loss": 0.9928032684326172, "step": 769000 }, { "epoch": 8.856046203376025, "grad_norm": 1.140625, "learning_rate": 3.6125492648448977e-06, "loss": 0.9882096099853516, "step": 769200 }, { "epoch": 8.858348888450738, "grad_norm": 0.65625, "learning_rate": 3.605277701022382e-06, "loss": 0.9933953857421876, "step": 769400 }, { "epoch": 8.860651573525454, "grad_norm": 0.54296875, "learning_rate": 3.5980061371998666e-06, "loss": 0.9875212097167969, "step": 769600 }, { "epoch": 8.862954258600169, "grad_norm": 0.98828125, "learning_rate": 3.5907345733773504e-06, "loss": 0.9890708160400391, "step": 769800 }, { "epoch": 8.865256943674884, "grad_norm": 0.86328125, "learning_rate": 3.583463009554835e-06, "loss": 0.9977067565917969, "step": 770000 }, { "epoch": 8.867559628749598, "grad_norm": 1.078125, "learning_rate": 3.5761914457323192e-06, "loss": 0.9735486602783203, "step": 770200 }, { "epoch": 8.869862313824314, "grad_norm": 1.1171875, "learning_rate": 3.568919881909804e-06, "loss": 0.9656082916259766, "step": 770400 }, { "epoch": 8.872164998899029, "grad_norm": 0.5703125, "learning_rate": 3.5616483180872877e-06, "loss": 0.9706471252441407, "step": 770600 }, { "epoch": 8.874467683973744, "grad_norm": 0.75, "learning_rate": 3.5543767542647723e-06, "loss": 1.0011856079101562, "step": 770800 }, { "epoch": 8.876770369048458, "grad_norm": 0.69140625, "learning_rate": 3.5471051904422565e-06, "loss": 0.9597758483886719, "step": 771000 }, { "epoch": 8.879073054123173, "grad_norm": 0.68359375, "learning_rate": 3.539833626619741e-06, "loss": 0.9833696746826172, "step": 771200 }, { "epoch": 8.881375739197889, "grad_norm": 1.171875, "learning_rate": 3.532562062797225e-06, "loss": 0.9873859405517578, "step": 771400 }, { "epoch": 8.883678424272603, "grad_norm": 0.8046875, "learning_rate": 3.5252904989747096e-06, "loss": 0.9804158020019531, "step": 771600 }, { "epoch": 8.885981109347318, "grad_norm": 0.65234375, "learning_rate": 3.518018935152194e-06, "loss": 0.9784156036376953, "step": 771800 }, { "epoch": 8.888283794422033, "grad_norm": 0.66796875, "learning_rate": 3.5107473713296785e-06, "loss": 0.9803633117675781, "step": 772000 }, { "epoch": 8.890586479496749, "grad_norm": 0.494140625, "learning_rate": 3.5034758075071623e-06, "loss": 0.9750108337402343, "step": 772200 }, { "epoch": 8.892889164571463, "grad_norm": 0.5078125, "learning_rate": 3.496204243684647e-06, "loss": 0.9871961975097656, "step": 772400 }, { "epoch": 8.895191849646178, "grad_norm": 0.69140625, "learning_rate": 3.488932679862131e-06, "loss": 0.9883628082275391, "step": 772600 }, { "epoch": 8.897494534720893, "grad_norm": 0.6171875, "learning_rate": 3.4816611160396158e-06, "loss": 0.9762785339355469, "step": 772800 }, { "epoch": 8.899797219795609, "grad_norm": 0.546875, "learning_rate": 3.4743895522170996e-06, "loss": 0.979869384765625, "step": 773000 }, { "epoch": 8.902099904870322, "grad_norm": 1.15625, "learning_rate": 3.467117988394584e-06, "loss": 0.9955022430419922, "step": 773200 }, { "epoch": 8.904402589945038, "grad_norm": 0.72265625, "learning_rate": 3.4598464245720684e-06, "loss": 0.9861965179443359, "step": 773400 }, { "epoch": 8.906705275019753, "grad_norm": 0.5234375, "learning_rate": 3.452574860749553e-06, "loss": 0.9948319244384766, "step": 773600 }, { "epoch": 8.909007960094467, "grad_norm": 1.2734375, "learning_rate": 3.445303296927037e-06, "loss": 0.9853091430664063, "step": 773800 }, { "epoch": 8.911310645169182, "grad_norm": 0.498046875, "learning_rate": 3.4380317331045215e-06, "loss": 0.9895594787597656, "step": 774000 }, { "epoch": 8.913613330243898, "grad_norm": 0.609375, "learning_rate": 3.4307601692820057e-06, "loss": 0.9816792297363282, "step": 774200 }, { "epoch": 8.915916015318613, "grad_norm": 0.73828125, "learning_rate": 3.4234886054594904e-06, "loss": 0.984228515625, "step": 774400 }, { "epoch": 8.918218700393327, "grad_norm": 0.7890625, "learning_rate": 3.4162170416369746e-06, "loss": 0.9908686828613281, "step": 774600 }, { "epoch": 8.920521385468042, "grad_norm": 0.67578125, "learning_rate": 3.408945477814459e-06, "loss": 0.9926894378662109, "step": 774800 }, { "epoch": 8.922824070542758, "grad_norm": 0.69921875, "learning_rate": 3.4016739139919434e-06, "loss": 0.9694911956787109, "step": 775000 }, { "epoch": 8.925126755617471, "grad_norm": 1.1796875, "learning_rate": 3.3944023501694277e-06, "loss": 0.9806173706054687, "step": 775200 }, { "epoch": 8.927429440692187, "grad_norm": 0.671875, "learning_rate": 3.387130786346912e-06, "loss": 0.9553947448730469, "step": 775400 }, { "epoch": 8.929732125766902, "grad_norm": 0.78515625, "learning_rate": 3.379859222524396e-06, "loss": 0.9826571655273437, "step": 775600 }, { "epoch": 8.932034810841618, "grad_norm": 0.7109375, "learning_rate": 3.3725876587018808e-06, "loss": 0.9717965698242188, "step": 775800 }, { "epoch": 8.934337495916331, "grad_norm": 1.3203125, "learning_rate": 3.365316094879365e-06, "loss": 1.011261215209961, "step": 776000 }, { "epoch": 8.936640180991047, "grad_norm": 0.875, "learning_rate": 3.358044531056849e-06, "loss": 0.99462158203125, "step": 776200 }, { "epoch": 8.938942866065762, "grad_norm": 0.89453125, "learning_rate": 3.3507729672343334e-06, "loss": 0.9862718200683593, "step": 776400 }, { "epoch": 8.941245551140476, "grad_norm": 0.546875, "learning_rate": 3.343501403411818e-06, "loss": 0.958528823852539, "step": 776600 }, { "epoch": 8.943548236215191, "grad_norm": 0.8984375, "learning_rate": 3.3362298395893023e-06, "loss": 0.996722183227539, "step": 776800 }, { "epoch": 8.945850921289907, "grad_norm": 0.765625, "learning_rate": 3.3289582757667865e-06, "loss": 0.9624080657958984, "step": 777000 }, { "epoch": 8.948153606364622, "grad_norm": 0.39453125, "learning_rate": 3.3216867119442707e-06, "loss": 0.9863372039794922, "step": 777200 }, { "epoch": 8.950456291439336, "grad_norm": 0.63671875, "learning_rate": 3.3144151481217554e-06, "loss": 0.9881964111328125, "step": 777400 }, { "epoch": 8.952758976514051, "grad_norm": 0.88671875, "learning_rate": 3.3071435842992396e-06, "loss": 0.9761305999755859, "step": 777600 }, { "epoch": 8.955061661588767, "grad_norm": 0.703125, "learning_rate": 3.299872020476724e-06, "loss": 0.9757279968261718, "step": 777800 }, { "epoch": 8.957364346663482, "grad_norm": 0.765625, "learning_rate": 3.292600456654208e-06, "loss": 0.971686782836914, "step": 778000 }, { "epoch": 8.959667031738196, "grad_norm": 0.68359375, "learning_rate": 3.2853288928316927e-06, "loss": 0.9756494903564453, "step": 778200 }, { "epoch": 8.961969716812911, "grad_norm": 0.6875, "learning_rate": 3.278057329009177e-06, "loss": 0.9671916198730469, "step": 778400 }, { "epoch": 8.964272401887627, "grad_norm": 0.62109375, "learning_rate": 3.270785765186661e-06, "loss": 0.9700312042236328, "step": 778600 }, { "epoch": 8.96657508696234, "grad_norm": 0.69921875, "learning_rate": 3.2635142013641453e-06, "loss": 1.0189725494384765, "step": 778800 }, { "epoch": 8.968877772037056, "grad_norm": 0.90625, "learning_rate": 3.25624263754163e-06, "loss": 0.9961846923828125, "step": 779000 }, { "epoch": 8.971180457111771, "grad_norm": 0.486328125, "learning_rate": 3.248971073719114e-06, "loss": 0.9650535583496094, "step": 779200 }, { "epoch": 8.973483142186486, "grad_norm": 0.625, "learning_rate": 3.2416995098965984e-06, "loss": 1.0100181579589844, "step": 779400 }, { "epoch": 8.9757858272612, "grad_norm": 0.53125, "learning_rate": 3.2344279460740826e-06, "loss": 0.9652468872070312, "step": 779600 }, { "epoch": 8.978088512335916, "grad_norm": 1.0390625, "learning_rate": 3.2271563822515673e-06, "loss": 0.9727928161621093, "step": 779800 }, { "epoch": 8.980391197410631, "grad_norm": 0.7578125, "learning_rate": 3.2198848184290515e-06, "loss": 0.9928997802734375, "step": 780000 }, { "epoch": 8.982693882485346, "grad_norm": 0.83984375, "learning_rate": 3.2126132546065357e-06, "loss": 1.0174883270263673, "step": 780200 }, { "epoch": 8.98499656756006, "grad_norm": 0.828125, "learning_rate": 3.20534169078402e-06, "loss": 0.994881591796875, "step": 780400 }, { "epoch": 8.987299252634775, "grad_norm": 0.37109375, "learning_rate": 3.1980701269615046e-06, "loss": 0.9750624847412109, "step": 780600 }, { "epoch": 8.989601937709491, "grad_norm": 0.63671875, "learning_rate": 3.1907985631389884e-06, "loss": 0.998040771484375, "step": 780800 }, { "epoch": 8.991904622784205, "grad_norm": 0.74609375, "learning_rate": 3.183526999316473e-06, "loss": 0.9677017974853516, "step": 781000 }, { "epoch": 8.99420730785892, "grad_norm": 0.40625, "learning_rate": 3.1762554354939572e-06, "loss": 0.9724453735351563, "step": 781200 }, { "epoch": 8.996509992933635, "grad_norm": 0.44921875, "learning_rate": 3.168983871671442e-06, "loss": 0.9718405151367188, "step": 781400 }, { "epoch": 8.99881267800835, "grad_norm": 0.64453125, "learning_rate": 3.161712307848926e-06, "loss": 0.9822624969482422, "step": 781600 }, { "epoch": 9.0, "eval_loss": NaN, "eval_runtime": 429.8804, "eval_samples_per_second": 65.974, "eval_steps_per_second": 32.988, "step": 781704 }, { "epoch": 9.001105288835863, "grad_norm": 0.84765625, "learning_rate": 3.1544407440264103e-06, "loss": 0.9588357543945313, "step": 781800 }, { "epoch": 9.003407973910578, "grad_norm": 0.80859375, "learning_rate": 3.147169180203895e-06, "loss": 0.9717916870117187, "step": 782000 }, { "epoch": 9.005710658985294, "grad_norm": 0.71484375, "learning_rate": 3.139897616381379e-06, "loss": 0.9799015045166015, "step": 782200 }, { "epoch": 9.008013344060007, "grad_norm": 0.515625, "learning_rate": 3.1326260525588634e-06, "loss": 0.9933222198486328, "step": 782400 }, { "epoch": 9.010316029134723, "grad_norm": 0.6171875, "learning_rate": 3.1253544887363476e-06, "loss": 0.972984390258789, "step": 782600 }, { "epoch": 9.012618714209438, "grad_norm": 0.69921875, "learning_rate": 3.1180829249138322e-06, "loss": 0.9755500030517578, "step": 782800 }, { "epoch": 9.014921399284153, "grad_norm": 1.03125, "learning_rate": 3.1108113610913165e-06, "loss": 0.9731624603271485, "step": 783000 }, { "epoch": 9.017224084358867, "grad_norm": 0.90234375, "learning_rate": 3.1035397972688007e-06, "loss": 0.9951696014404297, "step": 783200 }, { "epoch": 9.019526769433583, "grad_norm": 0.41015625, "learning_rate": 3.096268233446285e-06, "loss": 0.9952273559570313, "step": 783400 }, { "epoch": 9.021829454508298, "grad_norm": 0.7265625, "learning_rate": 3.0889966696237695e-06, "loss": 0.989826431274414, "step": 783600 }, { "epoch": 9.024132139583012, "grad_norm": 0.515625, "learning_rate": 3.0817251058012538e-06, "loss": 0.9967062377929687, "step": 783800 }, { "epoch": 9.026434824657727, "grad_norm": 0.78515625, "learning_rate": 3.074453541978738e-06, "loss": 0.9919381713867188, "step": 784000 }, { "epoch": 9.028737509732442, "grad_norm": 0.5, "learning_rate": 3.067181978156222e-06, "loss": 0.9788978576660157, "step": 784200 }, { "epoch": 9.031040194807158, "grad_norm": 0.47265625, "learning_rate": 3.059910414333707e-06, "loss": 0.9845250701904297, "step": 784400 }, { "epoch": 9.033342879881872, "grad_norm": 0.7421875, "learning_rate": 3.052638850511191e-06, "loss": 0.9908609008789062, "step": 784600 }, { "epoch": 9.035645564956587, "grad_norm": 1.3046875, "learning_rate": 3.0453672866886753e-06, "loss": 0.979962387084961, "step": 784800 }, { "epoch": 9.037948250031302, "grad_norm": 0.55078125, "learning_rate": 3.0380957228661595e-06, "loss": 0.9913197326660156, "step": 785000 }, { "epoch": 9.040250935106018, "grad_norm": 1.265625, "learning_rate": 3.030824159043644e-06, "loss": 0.9811695098876954, "step": 785200 }, { "epoch": 9.042553620180731, "grad_norm": 0.69140625, "learning_rate": 3.0235525952211284e-06, "loss": 0.9808423614501953, "step": 785400 }, { "epoch": 9.044856305255447, "grad_norm": 0.7890625, "learning_rate": 3.0162810313986126e-06, "loss": 0.9801983642578125, "step": 785600 }, { "epoch": 9.047158990330162, "grad_norm": 1.0703125, "learning_rate": 3.009009467576097e-06, "loss": 0.9870307159423828, "step": 785800 }, { "epoch": 9.049461675404876, "grad_norm": 1.0703125, "learning_rate": 3.0017379037535814e-06, "loss": 0.9723702239990234, "step": 786000 }, { "epoch": 9.051764360479591, "grad_norm": 0.67578125, "learning_rate": 2.9944663399310657e-06, "loss": 0.9945685577392578, "step": 786200 }, { "epoch": 9.054067045554307, "grad_norm": 0.5546875, "learning_rate": 2.98719477610855e-06, "loss": 0.9849127197265625, "step": 786400 }, { "epoch": 9.056369730629022, "grad_norm": 0.6015625, "learning_rate": 2.979923212286034e-06, "loss": 0.9685233306884765, "step": 786600 }, { "epoch": 9.058672415703736, "grad_norm": 0.62109375, "learning_rate": 2.9726516484635187e-06, "loss": 0.9885980987548828, "step": 786800 }, { "epoch": 9.060975100778451, "grad_norm": 0.82421875, "learning_rate": 2.965380084641003e-06, "loss": 0.9755864715576172, "step": 787000 }, { "epoch": 9.063277785853167, "grad_norm": 0.490234375, "learning_rate": 2.958108520818487e-06, "loss": 0.9793693542480468, "step": 787200 }, { "epoch": 9.065580470927882, "grad_norm": 0.7109375, "learning_rate": 2.9508369569959714e-06, "loss": 0.9743875885009765, "step": 787400 }, { "epoch": 9.067883156002596, "grad_norm": 0.6015625, "learning_rate": 2.943565393173456e-06, "loss": 0.987215576171875, "step": 787600 }, { "epoch": 9.070185841077311, "grad_norm": 0.53515625, "learning_rate": 2.9362938293509403e-06, "loss": 0.9882207489013672, "step": 787800 }, { "epoch": 9.072488526152027, "grad_norm": 0.474609375, "learning_rate": 2.9290222655284245e-06, "loss": 0.9898771667480468, "step": 788000 }, { "epoch": 9.07479121122674, "grad_norm": 0.87890625, "learning_rate": 2.9217507017059087e-06, "loss": 0.9595680999755859, "step": 788200 }, { "epoch": 9.077093896301456, "grad_norm": 0.380859375, "learning_rate": 2.9144791378833933e-06, "loss": 0.9669092559814453, "step": 788400 }, { "epoch": 9.079396581376171, "grad_norm": 0.50390625, "learning_rate": 2.907207574060878e-06, "loss": 0.9772784423828125, "step": 788600 }, { "epoch": 9.081699266450887, "grad_norm": 1.3828125, "learning_rate": 2.8999360102383618e-06, "loss": 0.9737366485595703, "step": 788800 }, { "epoch": 9.0840019515256, "grad_norm": 0.55078125, "learning_rate": 2.8926644464158464e-06, "loss": 0.9656417083740234, "step": 789000 }, { "epoch": 9.086304636600316, "grad_norm": 0.5234375, "learning_rate": 2.8853928825933306e-06, "loss": 0.9802579498291015, "step": 789200 }, { "epoch": 9.088607321675031, "grad_norm": 0.447265625, "learning_rate": 2.8781213187708153e-06, "loss": 0.9718341827392578, "step": 789400 }, { "epoch": 9.090910006749745, "grad_norm": 0.66796875, "learning_rate": 2.870849754948299e-06, "loss": 0.9539443206787109, "step": 789600 }, { "epoch": 9.09321269182446, "grad_norm": 0.51953125, "learning_rate": 2.8635781911257837e-06, "loss": 0.9921604919433594, "step": 789800 }, { "epoch": 9.095515376899176, "grad_norm": 0.75, "learning_rate": 2.856306627303268e-06, "loss": 0.9690369415283203, "step": 790000 }, { "epoch": 9.097818061973891, "grad_norm": 0.494140625, "learning_rate": 2.8490350634807526e-06, "loss": 0.9706679534912109, "step": 790200 }, { "epoch": 9.100120747048605, "grad_norm": 0.9375, "learning_rate": 2.8417634996582364e-06, "loss": 1.0010890197753906, "step": 790400 }, { "epoch": 9.10242343212332, "grad_norm": 0.462890625, "learning_rate": 2.834491935835721e-06, "loss": 0.9859672546386719, "step": 790600 }, { "epoch": 9.104726117198036, "grad_norm": 0.53125, "learning_rate": 2.8272203720132053e-06, "loss": 0.9713872528076172, "step": 790800 }, { "epoch": 9.107028802272751, "grad_norm": 0.83203125, "learning_rate": 2.81994880819069e-06, "loss": 0.9894600677490234, "step": 791000 }, { "epoch": 9.109331487347465, "grad_norm": 1.3671875, "learning_rate": 2.8126772443681737e-06, "loss": 0.9755573272705078, "step": 791200 }, { "epoch": 9.11163417242218, "grad_norm": 0.703125, "learning_rate": 2.8054056805456583e-06, "loss": 0.9854010772705079, "step": 791400 }, { "epoch": 9.113936857496896, "grad_norm": 0.443359375, "learning_rate": 2.7981341167231426e-06, "loss": 0.9738497161865234, "step": 791600 }, { "epoch": 9.11623954257161, "grad_norm": 1.203125, "learning_rate": 2.790862552900627e-06, "loss": 0.9824601745605469, "step": 791800 }, { "epoch": 9.118542227646325, "grad_norm": 0.73828125, "learning_rate": 2.783590989078111e-06, "loss": 0.9630702209472656, "step": 792000 }, { "epoch": 9.12084491272104, "grad_norm": 0.5390625, "learning_rate": 2.7763194252555956e-06, "loss": 0.9746056365966796, "step": 792200 }, { "epoch": 9.123147597795755, "grad_norm": 0.6953125, "learning_rate": 2.76904786143308e-06, "loss": 0.9801070404052734, "step": 792400 }, { "epoch": 9.125450282870469, "grad_norm": 0.703125, "learning_rate": 2.761776297610564e-06, "loss": 0.9643087005615234, "step": 792600 }, { "epoch": 9.127752967945185, "grad_norm": 1.3671875, "learning_rate": 2.7545047337880483e-06, "loss": 0.9930847930908203, "step": 792800 }, { "epoch": 9.1300556530199, "grad_norm": 0.65625, "learning_rate": 2.747233169965533e-06, "loss": 0.9791233825683594, "step": 793000 }, { "epoch": 9.132358338094614, "grad_norm": 0.67578125, "learning_rate": 2.739961606143017e-06, "loss": 0.9894448852539063, "step": 793200 }, { "epoch": 9.134661023169329, "grad_norm": 0.86328125, "learning_rate": 2.7326900423205014e-06, "loss": 0.9905043792724609, "step": 793400 }, { "epoch": 9.136963708244044, "grad_norm": 1.3671875, "learning_rate": 2.7254184784979856e-06, "loss": 0.9656953430175781, "step": 793600 }, { "epoch": 9.13926639331876, "grad_norm": 0.75390625, "learning_rate": 2.7181469146754702e-06, "loss": 0.9717328643798828, "step": 793800 }, { "epoch": 9.141569078393474, "grad_norm": 0.8359375, "learning_rate": 2.7108753508529545e-06, "loss": 0.9814446258544922, "step": 794000 }, { "epoch": 9.143871763468189, "grad_norm": 0.8203125, "learning_rate": 2.7036037870304387e-06, "loss": 0.9948249816894531, "step": 794200 }, { "epoch": 9.146174448542904, "grad_norm": 0.640625, "learning_rate": 2.696332223207923e-06, "loss": 0.9781787109375, "step": 794400 }, { "epoch": 9.14847713361762, "grad_norm": 0.76953125, "learning_rate": 2.6890606593854075e-06, "loss": 0.9804864501953126, "step": 794600 }, { "epoch": 9.150779818692333, "grad_norm": 0.69921875, "learning_rate": 2.6817890955628918e-06, "loss": 0.9924549102783203, "step": 794800 }, { "epoch": 9.153082503767049, "grad_norm": 0.515625, "learning_rate": 2.674517531740376e-06, "loss": 0.9628752899169922, "step": 795000 }, { "epoch": 9.155385188841764, "grad_norm": 0.5234375, "learning_rate": 2.6672459679178606e-06, "loss": 0.994937744140625, "step": 795200 }, { "epoch": 9.157687873916478, "grad_norm": 0.484375, "learning_rate": 2.659974404095345e-06, "loss": 0.9820407104492187, "step": 795400 }, { "epoch": 9.159990558991193, "grad_norm": 0.72265625, "learning_rate": 2.6527028402728295e-06, "loss": 1.0036585998535157, "step": 795600 }, { "epoch": 9.162293244065909, "grad_norm": 0.9296875, "learning_rate": 2.6454312764503133e-06, "loss": 0.9978278350830078, "step": 795800 }, { "epoch": 9.164595929140624, "grad_norm": 0.9609375, "learning_rate": 2.638159712627798e-06, "loss": 0.9959989929199219, "step": 796000 }, { "epoch": 9.166898614215338, "grad_norm": 0.5078125, "learning_rate": 2.630888148805282e-06, "loss": 0.9977657318115234, "step": 796200 }, { "epoch": 9.169201299290053, "grad_norm": 0.58984375, "learning_rate": 2.6236165849827668e-06, "loss": 0.9684986877441406, "step": 796400 }, { "epoch": 9.171503984364769, "grad_norm": 1.0, "learning_rate": 2.6163450211602506e-06, "loss": 1.0095248413085938, "step": 796600 }, { "epoch": 9.173806669439482, "grad_norm": 0.65625, "learning_rate": 2.6090734573377352e-06, "loss": 0.9658311462402344, "step": 796800 }, { "epoch": 9.176109354514198, "grad_norm": 0.87890625, "learning_rate": 2.6018018935152194e-06, "loss": 0.9893347930908203, "step": 797000 }, { "epoch": 9.178412039588913, "grad_norm": 0.48828125, "learning_rate": 2.594530329692704e-06, "loss": 0.9784815216064453, "step": 797200 }, { "epoch": 9.180714724663629, "grad_norm": 0.490234375, "learning_rate": 2.587258765870188e-06, "loss": 0.984940185546875, "step": 797400 }, { "epoch": 9.183017409738342, "grad_norm": 1.515625, "learning_rate": 2.5799872020476725e-06, "loss": 0.9787003326416016, "step": 797600 }, { "epoch": 9.185320094813058, "grad_norm": 0.66015625, "learning_rate": 2.5727156382251567e-06, "loss": 0.9814534759521485, "step": 797800 }, { "epoch": 9.187622779887773, "grad_norm": 0.65234375, "learning_rate": 2.5654440744026414e-06, "loss": 0.9823260498046875, "step": 798000 }, { "epoch": 9.189925464962489, "grad_norm": 0.54296875, "learning_rate": 2.558172510580125e-06, "loss": 0.9531006622314453, "step": 798200 }, { "epoch": 9.192228150037202, "grad_norm": 0.82421875, "learning_rate": 2.55090094675761e-06, "loss": 0.9803681182861328, "step": 798400 }, { "epoch": 9.194530835111918, "grad_norm": 0.5859375, "learning_rate": 2.543629382935094e-06, "loss": 0.962587890625, "step": 798600 }, { "epoch": 9.196833520186633, "grad_norm": 0.76171875, "learning_rate": 2.5363578191125787e-06, "loss": 0.9822435760498047, "step": 798800 }, { "epoch": 9.199136205261347, "grad_norm": 0.70703125, "learning_rate": 2.5290862552900625e-06, "loss": 0.9760208129882812, "step": 799000 }, { "epoch": 9.201438890336062, "grad_norm": 0.5625, "learning_rate": 2.521814691467547e-06, "loss": 0.9792575836181641, "step": 799200 }, { "epoch": 9.203741575410778, "grad_norm": 0.59375, "learning_rate": 2.5145431276450313e-06, "loss": 0.9941600036621093, "step": 799400 }, { "epoch": 9.206044260485493, "grad_norm": 1.21875, "learning_rate": 2.507271563822516e-06, "loss": 0.9764888763427735, "step": 799600 }, { "epoch": 9.208346945560207, "grad_norm": 0.71484375, "learning_rate": 2.4999999999999998e-06, "loss": 0.9621796417236328, "step": 799800 }, { "epoch": 9.210649630634922, "grad_norm": 1.6640625, "learning_rate": 2.4927284361774844e-06, "loss": 0.9800115203857422, "step": 800000 }, { "epoch": 9.212952315709638, "grad_norm": 0.58984375, "learning_rate": 2.4854568723549686e-06, "loss": 0.9602899169921875, "step": 800200 }, { "epoch": 9.215255000784353, "grad_norm": 0.5, "learning_rate": 2.4781853085324533e-06, "loss": 0.9630294036865235, "step": 800400 }, { "epoch": 9.217557685859067, "grad_norm": 0.6640625, "learning_rate": 2.470913744709937e-06, "loss": 0.9817597961425781, "step": 800600 }, { "epoch": 9.219860370933782, "grad_norm": 0.86328125, "learning_rate": 2.4636421808874217e-06, "loss": 0.9933039093017578, "step": 800800 }, { "epoch": 9.222163056008498, "grad_norm": 0.6953125, "learning_rate": 2.456370617064906e-06, "loss": 0.9749951171875, "step": 801000 }, { "epoch": 9.224465741083211, "grad_norm": 0.99609375, "learning_rate": 2.4490990532423906e-06, "loss": 0.9645835113525391, "step": 801200 }, { "epoch": 9.226768426157927, "grad_norm": 0.7578125, "learning_rate": 2.4418274894198744e-06, "loss": 0.9951029968261719, "step": 801400 }, { "epoch": 9.229071111232642, "grad_norm": 0.984375, "learning_rate": 2.434555925597359e-06, "loss": 0.9582917785644531, "step": 801600 }, { "epoch": 9.231373796307357, "grad_norm": 0.8203125, "learning_rate": 2.4272843617748432e-06, "loss": 0.9795014953613281, "step": 801800 }, { "epoch": 9.233676481382071, "grad_norm": 1.015625, "learning_rate": 2.420012797952328e-06, "loss": 0.9806991577148437, "step": 802000 }, { "epoch": 9.235979166456787, "grad_norm": 0.70703125, "learning_rate": 2.412741234129812e-06, "loss": 0.9899074554443359, "step": 802200 }, { "epoch": 9.238281851531502, "grad_norm": 0.61328125, "learning_rate": 2.4054696703072963e-06, "loss": 0.9765318298339843, "step": 802400 }, { "epoch": 9.240584536606216, "grad_norm": 0.85546875, "learning_rate": 2.398198106484781e-06, "loss": 1.0049002075195312, "step": 802600 }, { "epoch": 9.242887221680931, "grad_norm": 1.1484375, "learning_rate": 2.390926542662265e-06, "loss": 1.0022148895263672, "step": 802800 }, { "epoch": 9.245189906755646, "grad_norm": 0.54296875, "learning_rate": 2.3836549788397494e-06, "loss": 0.9906528472900391, "step": 803000 }, { "epoch": 9.247492591830362, "grad_norm": 0.60546875, "learning_rate": 2.3763834150172336e-06, "loss": 0.9908769989013672, "step": 803200 }, { "epoch": 9.249795276905076, "grad_norm": 0.73046875, "learning_rate": 2.3691118511947183e-06, "loss": 0.9784947967529297, "step": 803400 }, { "epoch": 9.252097961979791, "grad_norm": 1.0703125, "learning_rate": 2.3618402873722025e-06, "loss": 0.9808582305908203, "step": 803600 }, { "epoch": 9.254400647054506, "grad_norm": 0.4765625, "learning_rate": 2.3545687235496867e-06, "loss": 0.9718049621582031, "step": 803800 }, { "epoch": 9.25670333212922, "grad_norm": 0.6015625, "learning_rate": 2.347297159727171e-06, "loss": 0.999382095336914, "step": 804000 }, { "epoch": 9.259006017203935, "grad_norm": 1.0390625, "learning_rate": 2.3400255959046556e-06, "loss": 0.9925857543945312, "step": 804200 }, { "epoch": 9.26130870227865, "grad_norm": 0.4921875, "learning_rate": 2.3327540320821394e-06, "loss": 0.9597567749023438, "step": 804400 }, { "epoch": 9.263611387353366, "grad_norm": 0.83984375, "learning_rate": 2.325482468259624e-06, "loss": 0.9851140594482422, "step": 804600 }, { "epoch": 9.26591407242808, "grad_norm": 0.78125, "learning_rate": 2.3182109044371082e-06, "loss": 0.9718254089355469, "step": 804800 }, { "epoch": 9.268216757502795, "grad_norm": 1.0859375, "learning_rate": 2.310939340614593e-06, "loss": 0.9673877716064453, "step": 805000 }, { "epoch": 9.27051944257751, "grad_norm": 0.765625, "learning_rate": 2.3036677767920767e-06, "loss": 0.9953539276123047, "step": 805200 }, { "epoch": 9.272822127652226, "grad_norm": 0.57421875, "learning_rate": 2.2963962129695613e-06, "loss": 0.9628050231933594, "step": 805400 }, { "epoch": 9.27512481272694, "grad_norm": 0.427734375, "learning_rate": 2.2891246491470455e-06, "loss": 0.9810200500488281, "step": 805600 }, { "epoch": 9.277427497801655, "grad_norm": 0.59765625, "learning_rate": 2.28185308532453e-06, "loss": 0.9924951171875, "step": 805800 }, { "epoch": 9.27973018287637, "grad_norm": 0.92578125, "learning_rate": 2.274581521502014e-06, "loss": 0.9816727447509765, "step": 806000 }, { "epoch": 9.282032867951084, "grad_norm": 0.9765625, "learning_rate": 2.2673099576794986e-06, "loss": 0.9924248504638672, "step": 806200 }, { "epoch": 9.2843355530258, "grad_norm": 0.62109375, "learning_rate": 2.260038393856983e-06, "loss": 0.9997078704833985, "step": 806400 }, { "epoch": 9.286638238100515, "grad_norm": 0.578125, "learning_rate": 2.2527668300344675e-06, "loss": 0.9612949371337891, "step": 806600 }, { "epoch": 9.28894092317523, "grad_norm": 0.80078125, "learning_rate": 2.2454952662119513e-06, "loss": 0.9775658416748046, "step": 806800 }, { "epoch": 9.291243608249944, "grad_norm": 0.83203125, "learning_rate": 2.238223702389436e-06, "loss": 0.9638466644287109, "step": 807000 }, { "epoch": 9.29354629332466, "grad_norm": 0.640625, "learning_rate": 2.23095213856692e-06, "loss": 0.9751538848876953, "step": 807200 }, { "epoch": 9.295848978399375, "grad_norm": 0.96875, "learning_rate": 2.2236805747444048e-06, "loss": 0.986815185546875, "step": 807400 }, { "epoch": 9.29815166347409, "grad_norm": 0.70703125, "learning_rate": 2.2164090109218886e-06, "loss": 0.9854920959472656, "step": 807600 }, { "epoch": 9.300454348548804, "grad_norm": 0.427734375, "learning_rate": 2.2091374470993732e-06, "loss": 0.997869873046875, "step": 807800 }, { "epoch": 9.30275703362352, "grad_norm": 0.78125, "learning_rate": 2.2018658832768574e-06, "loss": 0.975609130859375, "step": 808000 }, { "epoch": 9.305059718698235, "grad_norm": 0.75, "learning_rate": 2.194594319454342e-06, "loss": 1.0007555389404297, "step": 808200 }, { "epoch": 9.307362403772949, "grad_norm": 1.203125, "learning_rate": 2.187322755631826e-06, "loss": 0.9574895477294922, "step": 808400 }, { "epoch": 9.309665088847664, "grad_norm": 0.5390625, "learning_rate": 2.1800511918093105e-06, "loss": 0.9769926452636719, "step": 808600 }, { "epoch": 9.31196777392238, "grad_norm": 0.49609375, "learning_rate": 2.1727796279867947e-06, "loss": 0.9835977935791016, "step": 808800 }, { "epoch": 9.314270458997095, "grad_norm": 0.65625, "learning_rate": 2.1655080641642794e-06, "loss": 0.98232421875, "step": 809000 }, { "epoch": 9.316573144071809, "grad_norm": 0.53125, "learning_rate": 2.1582365003417636e-06, "loss": 0.9904391479492187, "step": 809200 }, { "epoch": 9.318875829146524, "grad_norm": 0.8828125, "learning_rate": 2.150964936519248e-06, "loss": 0.977032470703125, "step": 809400 }, { "epoch": 9.32117851422124, "grad_norm": 0.6171875, "learning_rate": 2.1436933726967325e-06, "loss": 0.9892449188232422, "step": 809600 }, { "epoch": 9.323481199295953, "grad_norm": 0.578125, "learning_rate": 2.1364218088742167e-06, "loss": 0.9981741333007812, "step": 809800 }, { "epoch": 9.325783884370669, "grad_norm": 0.484375, "learning_rate": 2.129150245051701e-06, "loss": 0.9746675109863281, "step": 810000 }, { "epoch": 9.328086569445384, "grad_norm": 0.71875, "learning_rate": 2.121878681229185e-06, "loss": 0.9943876647949219, "step": 810200 }, { "epoch": 9.3303892545201, "grad_norm": 0.73828125, "learning_rate": 2.1146071174066698e-06, "loss": 0.9812979888916016, "step": 810400 }, { "epoch": 9.332691939594813, "grad_norm": 0.625, "learning_rate": 2.107335553584154e-06, "loss": 0.9795059967041015, "step": 810600 }, { "epoch": 9.334994624669529, "grad_norm": 0.9765625, "learning_rate": 2.100063989761638e-06, "loss": 0.9666686248779297, "step": 810800 }, { "epoch": 9.337297309744244, "grad_norm": 0.6171875, "learning_rate": 2.0927924259391224e-06, "loss": 0.9806160736083984, "step": 811000 }, { "epoch": 9.33959999481896, "grad_norm": 0.72265625, "learning_rate": 2.085520862116607e-06, "loss": 0.9875475311279297, "step": 811200 }, { "epoch": 9.341902679893673, "grad_norm": 0.85546875, "learning_rate": 2.0782492982940913e-06, "loss": 0.9789799499511719, "step": 811400 }, { "epoch": 9.344205364968388, "grad_norm": 0.7109375, "learning_rate": 2.0709777344715755e-06, "loss": 0.9655042266845704, "step": 811600 }, { "epoch": 9.346508050043104, "grad_norm": 0.447265625, "learning_rate": 2.0637061706490597e-06, "loss": 0.9765595245361328, "step": 811800 }, { "epoch": 9.348810735117818, "grad_norm": 0.5546875, "learning_rate": 2.0564346068265444e-06, "loss": 0.9863420867919922, "step": 812000 }, { "epoch": 9.351113420192533, "grad_norm": 0.435546875, "learning_rate": 2.0491630430040286e-06, "loss": 0.987475357055664, "step": 812200 }, { "epoch": 9.353416105267248, "grad_norm": 0.671875, "learning_rate": 2.041891479181513e-06, "loss": 0.9715730285644532, "step": 812400 }, { "epoch": 9.355718790341964, "grad_norm": 0.498046875, "learning_rate": 2.034619915358997e-06, "loss": 0.9703129577636719, "step": 812600 }, { "epoch": 9.358021475416678, "grad_norm": 1.28125, "learning_rate": 2.0273483515364817e-06, "loss": 0.9737438201904297, "step": 812800 }, { "epoch": 9.360324160491393, "grad_norm": 0.81640625, "learning_rate": 2.020076787713966e-06, "loss": 0.9923829650878906, "step": 813000 }, { "epoch": 9.362626845566108, "grad_norm": 0.68359375, "learning_rate": 2.01280522389145e-06, "loss": 0.9827593994140625, "step": 813200 }, { "epoch": 9.364929530640822, "grad_norm": 0.6015625, "learning_rate": 2.0055336600689343e-06, "loss": 0.9942121887207032, "step": 813400 }, { "epoch": 9.367232215715537, "grad_norm": 0.53515625, "learning_rate": 1.998262096246419e-06, "loss": 0.9751979064941406, "step": 813600 }, { "epoch": 9.369534900790253, "grad_norm": 0.84765625, "learning_rate": 1.990990532423903e-06, "loss": 0.9989577484130859, "step": 813800 }, { "epoch": 9.371837585864968, "grad_norm": 0.48828125, "learning_rate": 1.9837189686013874e-06, "loss": 0.9913412475585938, "step": 814000 }, { "epoch": 9.374140270939682, "grad_norm": 0.6171875, "learning_rate": 1.9764474047788716e-06, "loss": 0.99336669921875, "step": 814200 }, { "epoch": 9.376442956014397, "grad_norm": 1.9296875, "learning_rate": 1.9691758409563563e-06, "loss": 0.9956826782226562, "step": 814400 }, { "epoch": 9.378745641089113, "grad_norm": 0.5234375, "learning_rate": 1.9619042771338405e-06, "loss": 0.9798301696777344, "step": 814600 }, { "epoch": 9.381048326163828, "grad_norm": 0.54296875, "learning_rate": 1.9546327133113247e-06, "loss": 0.9882535552978515, "step": 814800 }, { "epoch": 9.383351011238542, "grad_norm": 1.1484375, "learning_rate": 1.947361149488809e-06, "loss": 0.9871403503417969, "step": 815000 }, { "epoch": 9.385653696313257, "grad_norm": 0.58984375, "learning_rate": 1.9400895856662936e-06, "loss": 0.9676121520996094, "step": 815200 }, { "epoch": 9.387956381387973, "grad_norm": 0.7265625, "learning_rate": 1.9328180218437774e-06, "loss": 0.9921231842041016, "step": 815400 }, { "epoch": 9.390259066462686, "grad_norm": 0.66796875, "learning_rate": 1.925546458021262e-06, "loss": 0.9892926025390625, "step": 815600 }, { "epoch": 9.392561751537402, "grad_norm": 0.8359375, "learning_rate": 1.9182748941987466e-06, "loss": 1.0030435943603515, "step": 815800 }, { "epoch": 9.394864436612117, "grad_norm": 0.49609375, "learning_rate": 1.911003330376231e-06, "loss": 0.9686942291259766, "step": 816000 }, { "epoch": 9.397167121686833, "grad_norm": 0.921875, "learning_rate": 1.9037317665537149e-06, "loss": 0.9933390808105469, "step": 816200 }, { "epoch": 9.399469806761546, "grad_norm": 0.640625, "learning_rate": 1.8964602027311993e-06, "loss": 0.9900911712646484, "step": 816400 }, { "epoch": 9.401772491836262, "grad_norm": 0.49609375, "learning_rate": 1.8891886389086837e-06, "loss": 0.9867049407958984, "step": 816600 }, { "epoch": 9.404075176910977, "grad_norm": 1.2890625, "learning_rate": 1.8819170750861682e-06, "loss": 0.9971127319335937, "step": 816800 }, { "epoch": 9.406377861985693, "grad_norm": 0.61328125, "learning_rate": 1.8746455112636524e-06, "loss": 0.9814208221435546, "step": 817000 }, { "epoch": 9.408680547060406, "grad_norm": 0.671875, "learning_rate": 1.8673739474411366e-06, "loss": 0.9804402160644531, "step": 817200 }, { "epoch": 9.410983232135122, "grad_norm": 0.828125, "learning_rate": 1.860102383618621e-06, "loss": 0.9882728576660156, "step": 817400 }, { "epoch": 9.413285917209837, "grad_norm": 0.6171875, "learning_rate": 1.8528308197961053e-06, "loss": 0.9980832672119141, "step": 817600 }, { "epoch": 9.41558860228455, "grad_norm": 0.625, "learning_rate": 1.8455592559735897e-06, "loss": 0.984637222290039, "step": 817800 }, { "epoch": 9.417891287359266, "grad_norm": 0.84765625, "learning_rate": 1.838287692151074e-06, "loss": 0.9878707885742187, "step": 818000 }, { "epoch": 9.420193972433982, "grad_norm": 0.6328125, "learning_rate": 1.8310161283285583e-06, "loss": 0.9839839935302734, "step": 818200 }, { "epoch": 9.422496657508697, "grad_norm": 0.490234375, "learning_rate": 1.8237445645060426e-06, "loss": 0.9818657684326172, "step": 818400 }, { "epoch": 9.42479934258341, "grad_norm": 0.640625, "learning_rate": 1.816473000683527e-06, "loss": 0.982414779663086, "step": 818600 }, { "epoch": 9.427102027658126, "grad_norm": 0.69140625, "learning_rate": 1.8092014368610112e-06, "loss": 0.9848974609375, "step": 818800 }, { "epoch": 9.429404712732842, "grad_norm": 0.703125, "learning_rate": 1.8019298730384956e-06, "loss": 0.9848900604248046, "step": 819000 }, { "epoch": 9.431707397807555, "grad_norm": 0.5546875, "learning_rate": 1.79465830921598e-06, "loss": 0.9777683258056641, "step": 819200 }, { "epoch": 9.43401008288227, "grad_norm": 0.69140625, "learning_rate": 1.7873867453934645e-06, "loss": 0.9755431365966797, "step": 819400 }, { "epoch": 9.436312767956986, "grad_norm": 0.640625, "learning_rate": 1.7801151815709487e-06, "loss": 1.0023635864257812, "step": 819600 }, { "epoch": 9.438615453031701, "grad_norm": 0.419921875, "learning_rate": 1.7728436177484332e-06, "loss": 0.9739385223388672, "step": 819800 }, { "epoch": 9.440918138106415, "grad_norm": 0.70703125, "learning_rate": 1.7655720539259174e-06, "loss": 0.9773667907714844, "step": 820000 }, { "epoch": 9.44322082318113, "grad_norm": 0.890625, "learning_rate": 1.7583004901034018e-06, "loss": 0.9598074340820313, "step": 820200 }, { "epoch": 9.445523508255846, "grad_norm": 0.380859375, "learning_rate": 1.751028926280886e-06, "loss": 0.9942584228515625, "step": 820400 }, { "epoch": 9.44782619333056, "grad_norm": 0.65234375, "learning_rate": 1.7437573624583705e-06, "loss": 0.9610377502441406, "step": 820600 }, { "epoch": 9.450128878405275, "grad_norm": 0.44921875, "learning_rate": 1.7364857986358547e-06, "loss": 0.984643325805664, "step": 820800 }, { "epoch": 9.45243156347999, "grad_norm": 0.69140625, "learning_rate": 1.729214234813339e-06, "loss": 0.9934852600097657, "step": 821000 }, { "epoch": 9.454734248554706, "grad_norm": 0.60546875, "learning_rate": 1.7219426709908233e-06, "loss": 0.9818549346923828, "step": 821200 }, { "epoch": 9.45703693362942, "grad_norm": 0.76171875, "learning_rate": 1.7146711071683078e-06, "loss": 0.9730079650878907, "step": 821400 }, { "epoch": 9.459339618704135, "grad_norm": 0.486328125, "learning_rate": 1.707399543345792e-06, "loss": 0.9771785736083984, "step": 821600 }, { "epoch": 9.46164230377885, "grad_norm": 0.77734375, "learning_rate": 1.7001279795232764e-06, "loss": 0.9868184661865235, "step": 821800 }, { "epoch": 9.463944988853566, "grad_norm": 0.7109375, "learning_rate": 1.6928564157007606e-06, "loss": 0.9857994079589844, "step": 822000 }, { "epoch": 9.46624767392828, "grad_norm": 0.9453125, "learning_rate": 1.685584851878245e-06, "loss": 0.9687263488769531, "step": 822200 }, { "epoch": 9.468550359002995, "grad_norm": 0.640625, "learning_rate": 1.6783132880557293e-06, "loss": 0.9900286102294922, "step": 822400 }, { "epoch": 9.47085304407771, "grad_norm": 0.87109375, "learning_rate": 1.6710417242332137e-06, "loss": 0.9791419219970703, "step": 822600 }, { "epoch": 9.473155729152424, "grad_norm": 0.9921875, "learning_rate": 1.663770160410698e-06, "loss": 0.9795015716552734, "step": 822800 }, { "epoch": 9.47545841422714, "grad_norm": 0.640625, "learning_rate": 1.6564985965881824e-06, "loss": 0.9941027069091797, "step": 823000 }, { "epoch": 9.477761099301855, "grad_norm": 0.478515625, "learning_rate": 1.6492270327656666e-06, "loss": 0.9751151275634765, "step": 823200 }, { "epoch": 9.48006378437657, "grad_norm": 0.65625, "learning_rate": 1.641955468943151e-06, "loss": 0.974825668334961, "step": 823400 }, { "epoch": 9.482366469451284, "grad_norm": 0.71484375, "learning_rate": 1.6346839051206352e-06, "loss": 0.9874494934082031, "step": 823600 }, { "epoch": 9.484669154526, "grad_norm": 0.859375, "learning_rate": 1.6274123412981197e-06, "loss": 0.9932949066162109, "step": 823800 }, { "epoch": 9.486971839600715, "grad_norm": 0.70703125, "learning_rate": 1.6201407774756039e-06, "loss": 0.9929389953613281, "step": 824000 }, { "epoch": 9.48927452467543, "grad_norm": 0.65234375, "learning_rate": 1.6128692136530883e-06, "loss": 0.9867328643798828, "step": 824200 }, { "epoch": 9.491577209750144, "grad_norm": 0.7421875, "learning_rate": 1.6055976498305725e-06, "loss": 0.9870306396484375, "step": 824400 }, { "epoch": 9.49387989482486, "grad_norm": 0.609375, "learning_rate": 1.598326086008057e-06, "loss": 0.9809159088134766, "step": 824600 }, { "epoch": 9.496182579899575, "grad_norm": 1.015625, "learning_rate": 1.5910545221855412e-06, "loss": 0.9663616943359375, "step": 824800 }, { "epoch": 9.498485264974288, "grad_norm": 0.953125, "learning_rate": 1.5837829583630256e-06, "loss": 0.976966323852539, "step": 825000 }, { "epoch": 9.500787950049004, "grad_norm": 0.58984375, "learning_rate": 1.5765113945405098e-06, "loss": 0.9969239807128907, "step": 825200 }, { "epoch": 9.50309063512372, "grad_norm": 0.7421875, "learning_rate": 1.5692398307179943e-06, "loss": 0.9940318298339844, "step": 825400 }, { "epoch": 9.505393320198435, "grad_norm": 0.5703125, "learning_rate": 1.5619682668954785e-06, "loss": 0.9804867553710938, "step": 825600 }, { "epoch": 9.507696005273148, "grad_norm": 0.83984375, "learning_rate": 1.554696703072963e-06, "loss": 0.979859848022461, "step": 825800 }, { "epoch": 9.509998690347864, "grad_norm": 0.65625, "learning_rate": 1.5474251392504471e-06, "loss": 0.9958170318603515, "step": 826000 }, { "epoch": 9.51230137542258, "grad_norm": 0.54296875, "learning_rate": 1.5401535754279318e-06, "loss": 0.9820123291015626, "step": 826200 }, { "epoch": 9.514604060497295, "grad_norm": 0.62109375, "learning_rate": 1.532882011605416e-06, "loss": 0.9946317291259765, "step": 826400 }, { "epoch": 9.516906745572008, "grad_norm": 0.4765625, "learning_rate": 1.5256104477829002e-06, "loss": 0.9823373413085937, "step": 826600 }, { "epoch": 9.519209430646724, "grad_norm": 0.59765625, "learning_rate": 1.5183388839603846e-06, "loss": 0.97361328125, "step": 826800 }, { "epoch": 9.521512115721439, "grad_norm": 0.59765625, "learning_rate": 1.5110673201378689e-06, "loss": 0.9896958160400391, "step": 827000 }, { "epoch": 9.523814800796153, "grad_norm": 0.49609375, "learning_rate": 1.5037957563153533e-06, "loss": 0.9637728881835937, "step": 827200 }, { "epoch": 9.526117485870868, "grad_norm": 0.67578125, "learning_rate": 1.4965241924928375e-06, "loss": 0.9915892028808594, "step": 827400 }, { "epoch": 9.528420170945584, "grad_norm": 0.6640625, "learning_rate": 1.489252628670322e-06, "loss": 0.9733876800537109, "step": 827600 }, { "epoch": 9.530722856020297, "grad_norm": 0.498046875, "learning_rate": 1.4819810648478062e-06, "loss": 0.9952828216552735, "step": 827800 }, { "epoch": 9.533025541095013, "grad_norm": 0.56640625, "learning_rate": 1.4747095010252906e-06, "loss": 1.0074019622802735, "step": 828000 }, { "epoch": 9.535328226169728, "grad_norm": 0.9375, "learning_rate": 1.4674379372027748e-06, "loss": 0.9821954345703126, "step": 828200 }, { "epoch": 9.537630911244444, "grad_norm": 0.388671875, "learning_rate": 1.4601663733802592e-06, "loss": 0.9739497375488281, "step": 828400 }, { "epoch": 9.539933596319157, "grad_norm": 0.65625, "learning_rate": 1.4528948095577435e-06, "loss": 0.9812117004394532, "step": 828600 }, { "epoch": 9.542236281393873, "grad_norm": 0.58203125, "learning_rate": 1.445623245735228e-06, "loss": 1.0017292022705078, "step": 828800 }, { "epoch": 9.544538966468588, "grad_norm": 0.78125, "learning_rate": 1.4383516819127121e-06, "loss": 0.9692825317382813, "step": 829000 }, { "epoch": 9.546841651543303, "grad_norm": 0.76171875, "learning_rate": 1.4310801180901965e-06, "loss": 0.9848232269287109, "step": 829200 }, { "epoch": 9.549144336618017, "grad_norm": 0.94140625, "learning_rate": 1.4238085542676808e-06, "loss": 0.9496469116210937, "step": 829400 }, { "epoch": 9.551447021692733, "grad_norm": 0.99609375, "learning_rate": 1.4165369904451652e-06, "loss": 0.9722937774658204, "step": 829600 }, { "epoch": 9.553749706767448, "grad_norm": 0.96484375, "learning_rate": 1.4092654266226494e-06, "loss": 0.9781289672851563, "step": 829800 }, { "epoch": 9.556052391842162, "grad_norm": 0.6484375, "learning_rate": 1.4019938628001338e-06, "loss": 1.0032569885253906, "step": 830000 }, { "epoch": 9.558355076916877, "grad_norm": 0.7890625, "learning_rate": 1.394722298977618e-06, "loss": 0.9749464416503906, "step": 830200 }, { "epoch": 9.560657761991592, "grad_norm": 0.74609375, "learning_rate": 1.3874507351551025e-06, "loss": 0.9686476135253906, "step": 830400 }, { "epoch": 9.562960447066308, "grad_norm": 0.6953125, "learning_rate": 1.3801791713325867e-06, "loss": 0.9786281585693359, "step": 830600 }, { "epoch": 9.565263132141022, "grad_norm": 0.466796875, "learning_rate": 1.3729076075100711e-06, "loss": 0.9751205444335938, "step": 830800 }, { "epoch": 9.567565817215737, "grad_norm": 1.0625, "learning_rate": 1.3656360436875554e-06, "loss": 0.9922896575927734, "step": 831000 }, { "epoch": 9.569868502290452, "grad_norm": 0.94921875, "learning_rate": 1.3583644798650398e-06, "loss": 0.9657626342773438, "step": 831200 }, { "epoch": 9.572171187365168, "grad_norm": 0.5234375, "learning_rate": 1.351092916042524e-06, "loss": 0.969854736328125, "step": 831400 }, { "epoch": 9.574473872439881, "grad_norm": 0.6328125, "learning_rate": 1.3438213522200084e-06, "loss": 0.998516845703125, "step": 831600 }, { "epoch": 9.576776557514597, "grad_norm": 0.5234375, "learning_rate": 1.3365497883974927e-06, "loss": 0.99427001953125, "step": 831800 }, { "epoch": 9.579079242589312, "grad_norm": 0.8046875, "learning_rate": 1.329278224574977e-06, "loss": 0.9744255065917968, "step": 832000 }, { "epoch": 9.581381927664026, "grad_norm": 0.66796875, "learning_rate": 1.3220066607524613e-06, "loss": 0.9698799133300782, "step": 832200 }, { "epoch": 9.583684612738741, "grad_norm": 0.62890625, "learning_rate": 1.3147350969299458e-06, "loss": 1.000227508544922, "step": 832400 }, { "epoch": 9.585987297813457, "grad_norm": 1.09375, "learning_rate": 1.30746353310743e-06, "loss": 1.012973861694336, "step": 832600 }, { "epoch": 9.588289982888172, "grad_norm": 0.515625, "learning_rate": 1.3001919692849144e-06, "loss": 0.9542025756835938, "step": 832800 }, { "epoch": 9.590592667962886, "grad_norm": 0.56640625, "learning_rate": 1.2929204054623988e-06, "loss": 1.001008071899414, "step": 833000 }, { "epoch": 9.592895353037601, "grad_norm": 0.640625, "learning_rate": 1.2856488416398833e-06, "loss": 0.9920815277099609, "step": 833200 }, { "epoch": 9.595198038112317, "grad_norm": 0.515625, "learning_rate": 1.2783772778173675e-06, "loss": 0.9846733856201172, "step": 833400 }, { "epoch": 9.597500723187032, "grad_norm": 0.53515625, "learning_rate": 1.271105713994852e-06, "loss": 0.9644556427001953, "step": 833600 }, { "epoch": 9.599803408261746, "grad_norm": 0.61328125, "learning_rate": 1.2638341501723361e-06, "loss": 0.9778141021728516, "step": 833800 }, { "epoch": 9.602106093336461, "grad_norm": 0.625, "learning_rate": 1.2565625863498206e-06, "loss": 0.9689984130859375, "step": 834000 }, { "epoch": 9.604408778411177, "grad_norm": 1.3359375, "learning_rate": 1.2492910225273048e-06, "loss": 0.9787627410888672, "step": 834200 }, { "epoch": 9.60671146348589, "grad_norm": 0.5390625, "learning_rate": 1.2420194587047892e-06, "loss": 1.011881103515625, "step": 834400 }, { "epoch": 9.609014148560606, "grad_norm": 0.9375, "learning_rate": 1.2347478948822734e-06, "loss": 0.9822531127929688, "step": 834600 }, { "epoch": 9.611316833635321, "grad_norm": 1.0078125, "learning_rate": 1.2274763310597579e-06, "loss": 0.9833524322509766, "step": 834800 }, { "epoch": 9.613619518710037, "grad_norm": 0.484375, "learning_rate": 1.220204767237242e-06, "loss": 0.9715459442138672, "step": 835000 }, { "epoch": 9.61592220378475, "grad_norm": 0.9296875, "learning_rate": 1.2129332034147265e-06, "loss": 0.9895572662353516, "step": 835200 }, { "epoch": 9.618224888859466, "grad_norm": 0.609375, "learning_rate": 1.2056616395922107e-06, "loss": 0.9693475341796876, "step": 835400 }, { "epoch": 9.620527573934181, "grad_norm": 1.1328125, "learning_rate": 1.1983900757696952e-06, "loss": 0.9663648223876953, "step": 835600 }, { "epoch": 9.622830259008895, "grad_norm": 0.4140625, "learning_rate": 1.1911185119471794e-06, "loss": 0.999940414428711, "step": 835800 }, { "epoch": 9.62513294408361, "grad_norm": 1.265625, "learning_rate": 1.1838469481246638e-06, "loss": 0.9695598602294921, "step": 836000 }, { "epoch": 9.627435629158326, "grad_norm": 1.140625, "learning_rate": 1.176575384302148e-06, "loss": 0.9636432647705078, "step": 836200 }, { "epoch": 9.629738314233041, "grad_norm": 0.58203125, "learning_rate": 1.1693038204796325e-06, "loss": 0.963818588256836, "step": 836400 }, { "epoch": 9.632040999307755, "grad_norm": 0.71875, "learning_rate": 1.1620322566571167e-06, "loss": 0.9796644592285156, "step": 836600 }, { "epoch": 9.63434368438247, "grad_norm": 0.890625, "learning_rate": 1.1547606928346011e-06, "loss": 0.9926264190673828, "step": 836800 }, { "epoch": 9.636646369457186, "grad_norm": 0.734375, "learning_rate": 1.1474891290120853e-06, "loss": 0.982134017944336, "step": 837000 }, { "epoch": 9.6389490545319, "grad_norm": 0.515625, "learning_rate": 1.1402175651895698e-06, "loss": 0.9629191589355469, "step": 837200 }, { "epoch": 9.641251739606615, "grad_norm": 0.6328125, "learning_rate": 1.132946001367054e-06, "loss": 0.9919446563720703, "step": 837400 }, { "epoch": 9.64355442468133, "grad_norm": 0.80859375, "learning_rate": 1.1256744375445384e-06, "loss": 0.9850608825683593, "step": 837600 }, { "epoch": 9.645857109756045, "grad_norm": 0.765625, "learning_rate": 1.1184028737220226e-06, "loss": 0.9781081390380859, "step": 837800 }, { "epoch": 9.64815979483076, "grad_norm": 0.7734375, "learning_rate": 1.111131309899507e-06, "loss": 0.993724365234375, "step": 838000 }, { "epoch": 9.650462479905475, "grad_norm": 0.60546875, "learning_rate": 1.1038597460769913e-06, "loss": 0.9846406555175782, "step": 838200 }, { "epoch": 9.65276516498019, "grad_norm": 0.61328125, "learning_rate": 1.0965881822544755e-06, "loss": 0.9925849151611328, "step": 838400 }, { "epoch": 9.655067850054905, "grad_norm": 0.66015625, "learning_rate": 1.08931661843196e-06, "loss": 0.9630934143066406, "step": 838600 }, { "epoch": 9.657370535129619, "grad_norm": 1.0390625, "learning_rate": 1.0820450546094442e-06, "loss": 0.9670571899414062, "step": 838800 }, { "epoch": 9.659673220204334, "grad_norm": 0.74609375, "learning_rate": 1.0747734907869286e-06, "loss": 0.9866361236572265, "step": 839000 }, { "epoch": 9.66197590527905, "grad_norm": 1.046875, "learning_rate": 1.0675019269644128e-06, "loss": 0.9836607360839844, "step": 839200 }, { "epoch": 9.664278590353764, "grad_norm": 0.953125, "learning_rate": 1.0602303631418972e-06, "loss": 0.9988703155517578, "step": 839400 }, { "epoch": 9.666581275428479, "grad_norm": 0.5390625, "learning_rate": 1.0529587993193815e-06, "loss": 0.9767841339111328, "step": 839600 }, { "epoch": 9.668883960503194, "grad_norm": 0.51171875, "learning_rate": 1.045687235496866e-06, "loss": 0.9695176696777343, "step": 839800 }, { "epoch": 9.67118664557791, "grad_norm": 0.984375, "learning_rate": 1.0384156716743503e-06, "loss": 0.9947758483886718, "step": 840000 }, { "epoch": 9.673489330652624, "grad_norm": 1.0546875, "learning_rate": 1.0311441078518348e-06, "loss": 0.9972378540039063, "step": 840200 }, { "epoch": 9.675792015727339, "grad_norm": 0.78125, "learning_rate": 1.023872544029319e-06, "loss": 1.0000531768798828, "step": 840400 }, { "epoch": 9.678094700802054, "grad_norm": 0.6953125, "learning_rate": 1.0166009802068034e-06, "loss": 0.9775434875488281, "step": 840600 }, { "epoch": 9.68039738587677, "grad_norm": 0.84375, "learning_rate": 1.0093294163842876e-06, "loss": 0.9801913452148437, "step": 840800 }, { "epoch": 9.682700070951483, "grad_norm": 0.7109375, "learning_rate": 1.002057852561772e-06, "loss": 1.0049404144287108, "step": 841000 }, { "epoch": 9.685002756026199, "grad_norm": 0.80078125, "learning_rate": 9.947862887392563e-07, "loss": 0.9907779693603516, "step": 841200 }, { "epoch": 9.687305441100914, "grad_norm": 0.76953125, "learning_rate": 9.875147249167407e-07, "loss": 0.9752469635009766, "step": 841400 }, { "epoch": 9.689608126175628, "grad_norm": 0.640625, "learning_rate": 9.80243161094225e-07, "loss": 0.9838815307617188, "step": 841600 }, { "epoch": 9.691910811250343, "grad_norm": 0.93359375, "learning_rate": 9.729715972717094e-07, "loss": 0.9889019012451172, "step": 841800 }, { "epoch": 9.694213496325059, "grad_norm": 0.7109375, "learning_rate": 9.657000334491936e-07, "loss": 0.9789157104492188, "step": 842000 }, { "epoch": 9.696516181399774, "grad_norm": 0.78515625, "learning_rate": 9.58428469626678e-07, "loss": 0.9792619323730469, "step": 842200 }, { "epoch": 9.698818866474488, "grad_norm": 0.7578125, "learning_rate": 9.511569058041622e-07, "loss": 0.9853229522705078, "step": 842400 }, { "epoch": 9.701121551549203, "grad_norm": 0.78515625, "learning_rate": 9.438853419816467e-07, "loss": 0.9715174102783203, "step": 842600 }, { "epoch": 9.703424236623919, "grad_norm": 0.85546875, "learning_rate": 9.36613778159131e-07, "loss": 0.9615935516357422, "step": 842800 }, { "epoch": 9.705726921698632, "grad_norm": 1.0078125, "learning_rate": 9.293422143366153e-07, "loss": 0.9686674499511718, "step": 843000 }, { "epoch": 9.708029606773348, "grad_norm": 0.5859375, "learning_rate": 9.220706505140996e-07, "loss": 0.9705300140380859, "step": 843200 }, { "epoch": 9.710332291848063, "grad_norm": 0.8125, "learning_rate": 9.14799086691584e-07, "loss": 0.9872032165527344, "step": 843400 }, { "epoch": 9.712634976922779, "grad_norm": 0.6015625, "learning_rate": 9.075275228690683e-07, "loss": 0.9720492553710938, "step": 843600 }, { "epoch": 9.714937661997492, "grad_norm": 0.6328125, "learning_rate": 9.002559590465526e-07, "loss": 0.9982711791992187, "step": 843800 }, { "epoch": 9.717240347072208, "grad_norm": 0.6171875, "learning_rate": 8.929843952240368e-07, "loss": 0.9764456939697266, "step": 844000 }, { "epoch": 9.719543032146923, "grad_norm": 0.7734375, "learning_rate": 8.857128314015212e-07, "loss": 0.9976146697998047, "step": 844200 }, { "epoch": 9.721845717221637, "grad_norm": 0.8671875, "learning_rate": 8.784412675790055e-07, "loss": 0.9691112518310547, "step": 844400 }, { "epoch": 9.724148402296352, "grad_norm": 0.6796875, "learning_rate": 8.711697037564898e-07, "loss": 0.9843009948730469, "step": 844600 }, { "epoch": 9.726451087371068, "grad_norm": 0.578125, "learning_rate": 8.638981399339741e-07, "loss": 0.9929389190673829, "step": 844800 }, { "epoch": 9.728753772445783, "grad_norm": 0.984375, "learning_rate": 8.566265761114586e-07, "loss": 0.95454345703125, "step": 845000 }, { "epoch": 9.731056457520497, "grad_norm": 0.96484375, "learning_rate": 8.493550122889429e-07, "loss": 0.9873353576660157, "step": 845200 }, { "epoch": 9.733359142595212, "grad_norm": 0.466796875, "learning_rate": 8.420834484664272e-07, "loss": 0.985777587890625, "step": 845400 }, { "epoch": 9.735661827669928, "grad_norm": 0.458984375, "learning_rate": 8.348118846439115e-07, "loss": 1.007764129638672, "step": 845600 }, { "epoch": 9.737964512744643, "grad_norm": 0.62109375, "learning_rate": 8.275403208213959e-07, "loss": 0.9851364135742188, "step": 845800 }, { "epoch": 9.740267197819357, "grad_norm": 0.609375, "learning_rate": 8.202687569988802e-07, "loss": 0.9813011169433594, "step": 846000 }, { "epoch": 9.742569882894072, "grad_norm": 0.55078125, "learning_rate": 8.129971931763645e-07, "loss": 0.9733602905273437, "step": 846200 }, { "epoch": 9.744872567968788, "grad_norm": 0.75, "learning_rate": 8.057256293538488e-07, "loss": 0.9741603851318359, "step": 846400 }, { "epoch": 9.747175253043501, "grad_norm": 1.0078125, "learning_rate": 7.984540655313332e-07, "loss": 0.9832783508300781, "step": 846600 }, { "epoch": 9.749477938118217, "grad_norm": 0.56640625, "learning_rate": 7.911825017088175e-07, "loss": 1.0015650177001953, "step": 846800 }, { "epoch": 9.751780623192932, "grad_norm": 0.4609375, "learning_rate": 7.839109378863018e-07, "loss": 0.9919761657714844, "step": 847000 }, { "epoch": 9.754083308267647, "grad_norm": 0.69921875, "learning_rate": 7.766393740637861e-07, "loss": 0.9678952789306641, "step": 847200 }, { "epoch": 9.756385993342361, "grad_norm": 1.09375, "learning_rate": 7.693678102412705e-07, "loss": 0.9774272918701172, "step": 847400 }, { "epoch": 9.758688678417077, "grad_norm": 0.8046875, "learning_rate": 7.620962464187548e-07, "loss": 0.9884217071533203, "step": 847600 }, { "epoch": 9.760991363491792, "grad_norm": 0.69921875, "learning_rate": 7.548246825962391e-07, "loss": 0.9622210693359375, "step": 847800 }, { "epoch": 9.763294048566507, "grad_norm": 0.6015625, "learning_rate": 7.475531187737234e-07, "loss": 0.9797222900390625, "step": 848000 }, { "epoch": 9.765596733641221, "grad_norm": 0.9375, "learning_rate": 7.402815549512078e-07, "loss": 0.9862091827392578, "step": 848200 }, { "epoch": 9.767899418715936, "grad_norm": 1.0703125, "learning_rate": 7.330099911286922e-07, "loss": 0.9772564697265625, "step": 848400 }, { "epoch": 9.770202103790652, "grad_norm": 0.90234375, "learning_rate": 7.257384273061765e-07, "loss": 0.9882775115966796, "step": 848600 }, { "epoch": 9.772504788865366, "grad_norm": 0.6171875, "learning_rate": 7.184668634836608e-07, "loss": 0.9722277069091797, "step": 848800 }, { "epoch": 9.774807473940081, "grad_norm": 0.61328125, "learning_rate": 7.111952996611452e-07, "loss": 1.0243209075927735, "step": 849000 }, { "epoch": 9.777110159014796, "grad_norm": 0.64453125, "learning_rate": 7.039237358386295e-07, "loss": 0.9980621337890625, "step": 849200 }, { "epoch": 9.779412844089512, "grad_norm": 0.8515625, "learning_rate": 6.966521720161138e-07, "loss": 1.0021202850341797, "step": 849400 }, { "epoch": 9.781715529164225, "grad_norm": 0.7578125, "learning_rate": 6.893806081935981e-07, "loss": 0.9711225128173828, "step": 849600 }, { "epoch": 9.784018214238941, "grad_norm": 0.63671875, "learning_rate": 6.821090443710825e-07, "loss": 0.97218505859375, "step": 849800 }, { "epoch": 9.786320899313656, "grad_norm": 0.53515625, "learning_rate": 6.748374805485668e-07, "loss": 0.9849751281738282, "step": 850000 }, { "epoch": 9.788623584388372, "grad_norm": 0.94921875, "learning_rate": 6.675659167260511e-07, "loss": 0.9899353790283203, "step": 850200 }, { "epoch": 9.790926269463085, "grad_norm": 0.53515625, "learning_rate": 6.602943529035354e-07, "loss": 0.9618595886230469, "step": 850400 }, { "epoch": 9.7932289545378, "grad_norm": 0.75, "learning_rate": 6.530227890810198e-07, "loss": 0.9787592315673828, "step": 850600 }, { "epoch": 9.795531639612516, "grad_norm": 0.6484375, "learning_rate": 6.457512252585041e-07, "loss": 0.980878677368164, "step": 850800 }, { "epoch": 9.79783432468723, "grad_norm": 1.0546875, "learning_rate": 6.384796614359884e-07, "loss": 0.994683837890625, "step": 851000 }, { "epoch": 9.800137009761945, "grad_norm": 0.6171875, "learning_rate": 6.312080976134727e-07, "loss": 0.9969705200195312, "step": 851200 }, { "epoch": 9.80243969483666, "grad_norm": 0.5546875, "learning_rate": 6.239365337909571e-07, "loss": 0.9933558654785156, "step": 851400 }, { "epoch": 9.804742379911376, "grad_norm": 0.8046875, "learning_rate": 6.166649699684414e-07, "loss": 0.9854070281982422, "step": 851600 }, { "epoch": 9.80704506498609, "grad_norm": 0.6015625, "learning_rate": 6.093934061459258e-07, "loss": 0.986405029296875, "step": 851800 }, { "epoch": 9.809347750060805, "grad_norm": 1.0234375, "learning_rate": 6.021218423234102e-07, "loss": 0.9843788909912109, "step": 852000 }, { "epoch": 9.81165043513552, "grad_norm": 0.5859375, "learning_rate": 5.948502785008945e-07, "loss": 0.9770623779296875, "step": 852200 }, { "epoch": 9.813953120210234, "grad_norm": 0.81640625, "learning_rate": 5.875787146783788e-07, "loss": 0.9609633636474609, "step": 852400 }, { "epoch": 9.81625580528495, "grad_norm": 1.90625, "learning_rate": 5.803071508558631e-07, "loss": 1.0110892486572265, "step": 852600 }, { "epoch": 9.818558490359665, "grad_norm": 0.90625, "learning_rate": 5.730355870333475e-07, "loss": 0.9992935180664062, "step": 852800 }, { "epoch": 9.82086117543438, "grad_norm": 0.62890625, "learning_rate": 5.657640232108318e-07, "loss": 0.9737750244140625, "step": 853000 }, { "epoch": 9.823163860509094, "grad_norm": 0.515625, "learning_rate": 5.584924593883161e-07, "loss": 0.9821039581298828, "step": 853200 }, { "epoch": 9.82546654558381, "grad_norm": 0.578125, "learning_rate": 5.512208955658004e-07, "loss": 0.9867521667480469, "step": 853400 }, { "epoch": 9.827769230658525, "grad_norm": 0.60546875, "learning_rate": 5.439493317432848e-07, "loss": 0.9823966979980469, "step": 853600 }, { "epoch": 9.830071915733239, "grad_norm": 0.6796875, "learning_rate": 5.366777679207691e-07, "loss": 0.9842733764648437, "step": 853800 }, { "epoch": 9.832374600807954, "grad_norm": 0.671875, "learning_rate": 5.294062040982534e-07, "loss": 0.9998354339599609, "step": 854000 }, { "epoch": 9.83467728588267, "grad_norm": 0.72265625, "learning_rate": 5.221346402757377e-07, "loss": 0.998682861328125, "step": 854200 }, { "epoch": 9.836979970957385, "grad_norm": 0.578125, "learning_rate": 5.148630764532221e-07, "loss": 0.9682182312011719, "step": 854400 }, { "epoch": 9.839282656032099, "grad_norm": 0.7265625, "learning_rate": 5.075915126307064e-07, "loss": 0.9853717041015625, "step": 854600 }, { "epoch": 9.841585341106814, "grad_norm": 0.76953125, "learning_rate": 5.003199488081907e-07, "loss": 0.9746234130859375, "step": 854800 }, { "epoch": 9.84388802618153, "grad_norm": 0.8671875, "learning_rate": 4.93048384985675e-07, "loss": 0.976443099975586, "step": 855000 }, { "epoch": 9.846190711256245, "grad_norm": 0.76171875, "learning_rate": 4.857768211631595e-07, "loss": 0.9782569122314453, "step": 855200 }, { "epoch": 9.848493396330959, "grad_norm": 0.828125, "learning_rate": 4.785052573406437e-07, "loss": 0.9826511383056641, "step": 855400 }, { "epoch": 9.850796081405674, "grad_norm": 0.5625, "learning_rate": 4.7123369351812796e-07, "loss": 0.9919064331054688, "step": 855600 }, { "epoch": 9.85309876648039, "grad_norm": 0.9296875, "learning_rate": 4.6396212969561234e-07, "loss": 0.979754409790039, "step": 855800 }, { "epoch": 9.855401451555103, "grad_norm": 0.53125, "learning_rate": 4.5669056587309666e-07, "loss": 0.9738344573974609, "step": 856000 }, { "epoch": 9.857704136629819, "grad_norm": 1.0859375, "learning_rate": 4.4941900205058104e-07, "loss": 0.9660050964355469, "step": 856200 }, { "epoch": 9.860006821704534, "grad_norm": 0.703125, "learning_rate": 4.4214743822806536e-07, "loss": 0.9862245941162109, "step": 856400 }, { "epoch": 9.86230950677925, "grad_norm": 0.91796875, "learning_rate": 4.348758744055497e-07, "loss": 0.9857429504394531, "step": 856600 }, { "epoch": 9.864612191853963, "grad_norm": 0.6953125, "learning_rate": 4.27604310583034e-07, "loss": 0.9800594329833985, "step": 856800 }, { "epoch": 9.866914876928679, "grad_norm": 0.76953125, "learning_rate": 4.2033274676051834e-07, "loss": 0.9967246246337891, "step": 857000 }, { "epoch": 9.869217562003394, "grad_norm": 0.5390625, "learning_rate": 4.1306118293800267e-07, "loss": 0.9913703918457031, "step": 857200 }, { "epoch": 9.87152024707811, "grad_norm": 1.359375, "learning_rate": 4.05789619115487e-07, "loss": 0.9892777252197266, "step": 857400 }, { "epoch": 9.873822932152823, "grad_norm": 0.9765625, "learning_rate": 3.985180552929713e-07, "loss": 1.000076675415039, "step": 857600 }, { "epoch": 9.876125617227538, "grad_norm": 0.53515625, "learning_rate": 3.912464914704557e-07, "loss": 1.00410888671875, "step": 857800 }, { "epoch": 9.878428302302254, "grad_norm": 0.65625, "learning_rate": 3.8397492764794e-07, "loss": 0.971823959350586, "step": 858000 }, { "epoch": 9.880730987376968, "grad_norm": 0.65234375, "learning_rate": 3.767033638254243e-07, "loss": 0.9962834930419922, "step": 858200 }, { "epoch": 9.883033672451683, "grad_norm": 1.1875, "learning_rate": 3.694318000029086e-07, "loss": 0.9885250854492188, "step": 858400 }, { "epoch": 9.885336357526398, "grad_norm": 0.62109375, "learning_rate": 3.6216023618039294e-07, "loss": 0.9724180603027344, "step": 858600 }, { "epoch": 9.887639042601114, "grad_norm": 0.5625, "learning_rate": 3.5488867235787727e-07, "loss": 0.9764485931396485, "step": 858800 }, { "epoch": 9.889941727675827, "grad_norm": 0.7734375, "learning_rate": 3.476171085353616e-07, "loss": 0.9844834899902344, "step": 859000 }, { "epoch": 9.892244412750543, "grad_norm": 0.4453125, "learning_rate": 3.403455447128459e-07, "loss": 0.9847768402099609, "step": 859200 }, { "epoch": 9.894547097825258, "grad_norm": 0.65625, "learning_rate": 3.3307398089033024e-07, "loss": 0.9868364715576172, "step": 859400 }, { "epoch": 9.896849782899972, "grad_norm": 0.87890625, "learning_rate": 3.258024170678146e-07, "loss": 0.9970125579833984, "step": 859600 }, { "epoch": 9.899152467974687, "grad_norm": 0.455078125, "learning_rate": 3.1853085324529895e-07, "loss": 0.9947715759277344, "step": 859800 }, { "epoch": 9.901455153049403, "grad_norm": 0.49609375, "learning_rate": 3.1125928942278327e-07, "loss": 0.995891342163086, "step": 860000 }, { "epoch": 9.903757838124118, "grad_norm": 0.73828125, "learning_rate": 3.039877256002676e-07, "loss": 1.0195358276367188, "step": 860200 }, { "epoch": 9.906060523198832, "grad_norm": 0.80078125, "learning_rate": 2.967161617777519e-07, "loss": 0.9633563232421875, "step": 860400 }, { "epoch": 9.908363208273547, "grad_norm": 0.75, "learning_rate": 2.8944459795523625e-07, "loss": 0.9851063537597656, "step": 860600 }, { "epoch": 9.910665893348263, "grad_norm": 0.8984375, "learning_rate": 2.8217303413272057e-07, "loss": 0.9972560119628906, "step": 860800 }, { "epoch": 9.912968578422976, "grad_norm": 0.59765625, "learning_rate": 2.749014703102049e-07, "loss": 0.965716552734375, "step": 861000 }, { "epoch": 9.915271263497692, "grad_norm": 0.5625, "learning_rate": 2.676299064876893e-07, "loss": 0.9895931243896484, "step": 861200 }, { "epoch": 9.917573948572407, "grad_norm": 0.71875, "learning_rate": 2.603583426651736e-07, "loss": 0.9821286010742187, "step": 861400 }, { "epoch": 9.919876633647123, "grad_norm": 0.671875, "learning_rate": 2.5308677884265793e-07, "loss": 0.998079833984375, "step": 861600 }, { "epoch": 9.922179318721836, "grad_norm": 0.6875, "learning_rate": 2.4581521502014225e-07, "loss": 0.9605708312988281, "step": 861800 }, { "epoch": 9.924482003796552, "grad_norm": 0.49609375, "learning_rate": 2.385436511976266e-07, "loss": 0.9791954040527344, "step": 862000 }, { "epoch": 9.926784688871267, "grad_norm": 0.59375, "learning_rate": 2.312720873751109e-07, "loss": 0.9803323364257812, "step": 862200 }, { "epoch": 9.929087373945983, "grad_norm": 1.0859375, "learning_rate": 2.2400052355259523e-07, "loss": 0.977833251953125, "step": 862400 }, { "epoch": 9.931390059020696, "grad_norm": 0.7421875, "learning_rate": 2.1672895973007955e-07, "loss": 0.9808238220214843, "step": 862600 }, { "epoch": 9.933692744095412, "grad_norm": 0.60546875, "learning_rate": 2.0945739590756388e-07, "loss": 0.9963713073730469, "step": 862800 }, { "epoch": 9.935995429170127, "grad_norm": 1.15625, "learning_rate": 2.021858320850482e-07, "loss": 0.9976137542724609, "step": 863000 }, { "epoch": 9.93829811424484, "grad_norm": 1.0078125, "learning_rate": 1.9491426826253253e-07, "loss": 0.971026611328125, "step": 863200 }, { "epoch": 9.940600799319556, "grad_norm": 0.55078125, "learning_rate": 1.8764270444001688e-07, "loss": 0.9874187469482422, "step": 863400 }, { "epoch": 9.942903484394272, "grad_norm": 0.73046875, "learning_rate": 1.803711406175012e-07, "loss": 0.97000732421875, "step": 863600 }, { "epoch": 9.945206169468987, "grad_norm": 0.83203125, "learning_rate": 1.7309957679498553e-07, "loss": 0.9777810668945313, "step": 863800 }, { "epoch": 9.9475088545437, "grad_norm": 0.5078125, "learning_rate": 1.6582801297246986e-07, "loss": 0.9669603729248046, "step": 864000 }, { "epoch": 9.949811539618416, "grad_norm": 0.68359375, "learning_rate": 1.585564491499542e-07, "loss": 0.9518377685546875, "step": 864200 }, { "epoch": 9.952114224693132, "grad_norm": 0.890625, "learning_rate": 1.5128488532743853e-07, "loss": 0.994540786743164, "step": 864400 }, { "epoch": 9.954416909767847, "grad_norm": 1.0546875, "learning_rate": 1.4401332150492286e-07, "loss": 0.9761511993408203, "step": 864600 }, { "epoch": 9.95671959484256, "grad_norm": 0.59375, "learning_rate": 1.3674175768240718e-07, "loss": 0.9886344909667969, "step": 864800 }, { "epoch": 9.959022279917276, "grad_norm": 0.75, "learning_rate": 1.294701938598915e-07, "loss": 0.9843460083007812, "step": 865000 }, { "epoch": 9.961324964991991, "grad_norm": 1.140625, "learning_rate": 1.2219863003737586e-07, "loss": 0.9988361358642578, "step": 865200 }, { "epoch": 9.963627650066705, "grad_norm": 0.5703125, "learning_rate": 1.1492706621486017e-07, "loss": 0.9724899291992187, "step": 865400 }, { "epoch": 9.96593033514142, "grad_norm": 0.6015625, "learning_rate": 1.076555023923445e-07, "loss": 0.9676179504394531, "step": 865600 }, { "epoch": 9.968233020216136, "grad_norm": 0.89453125, "learning_rate": 1.0038393856982884e-07, "loss": 0.9617569732666016, "step": 865800 }, { "epoch": 9.970535705290851, "grad_norm": 0.82421875, "learning_rate": 9.311237474731316e-08, "loss": 0.9744757843017579, "step": 866000 }, { "epoch": 9.972838390365565, "grad_norm": 1.921875, "learning_rate": 8.584081092479749e-08, "loss": 1.0132231140136718, "step": 866200 }, { "epoch": 9.97514107544028, "grad_norm": 0.640625, "learning_rate": 7.856924710228181e-08, "loss": 0.9756494903564453, "step": 866400 }, { "epoch": 9.977443760514996, "grad_norm": 1.4296875, "learning_rate": 7.129768327976615e-08, "loss": 0.9711592102050781, "step": 866600 }, { "epoch": 9.979746445589711, "grad_norm": 0.57421875, "learning_rate": 6.402611945725048e-08, "loss": 1.0018580627441407, "step": 866800 }, { "epoch": 9.982049130664425, "grad_norm": 0.431640625, "learning_rate": 5.675455563473481e-08, "loss": 1.0008620452880859, "step": 867000 }, { "epoch": 9.98435181573914, "grad_norm": 1.0859375, "learning_rate": 4.948299181221913e-08, "loss": 0.9791983795166016, "step": 867200 }, { "epoch": 9.986654500813856, "grad_norm": 0.82421875, "learning_rate": 4.2211427989703465e-08, "loss": 0.9899475860595703, "step": 867400 }, { "epoch": 9.98895718588857, "grad_norm": 0.84375, "learning_rate": 3.49398641671878e-08, "loss": 0.9756233215332031, "step": 867600 }, { "epoch": 9.991259870963285, "grad_norm": 1.0234375, "learning_rate": 2.7668300344672125e-08, "loss": 0.9905976867675781, "step": 867800 }, { "epoch": 9.993562556038, "grad_norm": 0.62109375, "learning_rate": 2.0396736522156457e-08, "loss": 0.9811268615722656, "step": 868000 }, { "epoch": 9.995865241112716, "grad_norm": 1.03125, "learning_rate": 1.3125172699640784e-08, "loss": 0.9911077880859375, "step": 868200 }, { "epoch": 9.99816792618743, "grad_norm": 0.76171875, "learning_rate": 5.853608877125114e-09, "loss": 0.989971923828125, "step": 868400 }, { "epoch": 10.0, "eval_loss": NaN, "eval_runtime": 431.6936, "eval_samples_per_second": 65.697, "eval_steps_per_second": 32.85, "step": 868560 } ], "logging_steps": 200, "max_steps": 868560, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.814236186142986e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }